Showing papers on "User modeling published in 2021"

Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation

Abstract: Social relations are often used to improve recommendation quality when user-item interaction data is sparse in recommender systems. Most existing social recommendation models exploit pairwise relations to mine potential user preferences. However, real-life interactions among users are very complex and user relations can be high-order. Hypergraph provides a natural way to model high-order relations, while its potentials for improving social recommendation are under-explored. In this paper, we fill this gap and propose a multi-channel hypergraph convolutional network to enhance social recommendation by leveraging high-order user relations. Technically, each channel in the network encodes a hypergraph that depicts a common high-order user relation pattern via hypergraph convolution. By aggregating the embeddings learned through multiple channels, we obtain comprehensive user representations to generate recommendation results. However, the aggregation operation might also obscure the inherent characteristics of different types of high-order connectivity information. To compensate for the aggregating loss, we innovatively integrate self-supervised learning into the training of the hypergraph convolutional network to regain the connectivity information with hierarchical mutual information maximization. Extensive experiments on multiple real-world datasets demonstrate the superiority of the proposed model over the current SOTA methods, and the ablation study verifies the effectiveness and rationale of the multi-channel setting and the self-supervised task. The implementation of our model is available via https://github.com/Coder-Yu/RecQ.

Learning Intents behind Interactions with Knowledge Graph for Recommendation

Abstract: Knowledge graph (KG) plays an increasingly important role in recommender systems. A recent technical trend is to develop end-to-end models founded on graph neural networks (GNNs). However, existing GNN-based models are coarse-grained in relational modeling, failing to (1) identify user-item relation at a fine-grained level of intents, and (2) exploit relation dependencies to preserve the semantics of long-range connectivity. In this study, we explore intents behind a user-item interaction by using auxiliary item knowledge, and propose a new model, Knowledge Graph-based Intent Network (KGIN). Technically, we model each intent as an attentive combination of KG relations, encouraging the independence of different intents for better model capability and interpretability. Furthermore, we devise a new information aggregation scheme for GNN, which recursively integrates the relation sequences of long-range connectivity (i.e., relational paths). This scheme allows us to distill useful information about user intents and encode them into the representations of users and items. Experimental results on three benchmark datasets show that, KGIN achieves significant improvements over the state-of-the-art methods like KGAT [41], KGNN-LS [38], and CKAN [47]. Further analyses show that KGIN offers interpretable explanations for predictions by identifying influential intents and relational paths. The implementations are available at https://github.com/huangtinglin/Knowledge_Graph_based_Intent_Network.

Disentangling User Interest and Conformity for Recommendation with Causal Embedding

Abstract: Recommendation models are usually trained on observational interaction data. However, observational interaction data could result from users’ conformity towards popular items, which entangles users’ real interest. Existing methods tracks this problem as eliminating popularity bias, e.g., by re-weighting training samples or leveraging a small fraction of unbiased data. However, the variety of user conformity is ignored by these approaches, and different causes of an interaction are bundled together as unified representations, hence robustness and interpretability are not guaranteed when underlying causes are changing. In this paper, we present DICE, a general framework that learns representations where interest and conformity are structurally disentangled, and various backbone recommendation models could be smoothly integrated. We assign users and items with separate embeddings for interest and conformity, and make each embedding capture only one cause by training with cause-specific data which is obtained according to the colliding effect of causal inference. Our proposed methodology outperforms state-of-the-art baselines with remarkable improvements on two real-world datasets on top of various backbone models. We further demonstrate that the learned embeddings successfully capture the desired causes, and show that DICE guarantees the robustness and interpretability of recommendation.

Interest-aware Message-Passing GCN for Recommendation

Abstract: Graph Convolution Networks (GCNs) manifest great potential in recommendation. This is attributed to their capability on learning good user and item embeddings by exploiting the collaborative signals from the high-order neighbors. Like other GCN models, the GCN based recommendation models also suffer from the notorious over-smoothing problem – when stacking more layers, node embeddings become more similar and eventually indistinguishable, resulted in performance degradation. The recently proposed LightGCN and LR-GCN alleviate this problem to some extent, however, we argue that they overlook an important factor for the over-smoothing problem in recommendation, that is, high-order neighboring users with no common interests of a user can be also involved in the user’s embedding learning in the graph convolution operation. As a result, the multi-layer graph convolution will make users with dissimilar interests have similar embeddings. In this paper, we propose a novel Interest-aware Message-Passing GCN (IMP-GCN) recommendation model, which performs high-order graph convolution inside subgraphs. The subgraph consists of users with similar interests and their interacted items. To form the subgraphs, we design an unsupervised subgraph generation module, which can effectively identify users with common interests by exploiting both user feature and graph structure. To this end, our model can avoid propagating negative information from high-order neighbors into embedding learning. Experimental results on three large-scale benchmark datasets show that our model can gain performance improvement by stacking more layers and outperform the state-of-the-art GCN-based recommendation models significantly.

CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation

Abstract: Learning user representations based on historical behaviors lies at the core of modern recommender systems. Recent advances in sequential recommenders have convincingly demonstrated high capability in extracting effective user representations from the given behavior sequences. Despite significant progress, we argue that solely modeling the observational behaviors sequences may end up with a brittle and unstable system due to the noisy and sparse nature of user interactions logged. In this paper, we propose to learn accurate and robust user representations, which are required to be less sensitive to (attack on) noisy behaviors and trust more on the indispensable ones, by modeling counterfactual data distribution. Specifically, given an observed behavior sequence, the proposed CauseRec framework identifies dispensable and indispensable concepts at both the fine-grained item level and the abstract interest level. CauseRec conditionally samples user concept sequences from the counterfactual data distributions by replacing dispensable and indispensable concepts within the original concept sequence. With user representations obtained from the synthesized user sequences, CauseRec performs contrastive user representation learning by contrasting the counterfactual with the observational. We conduct extensive experiments on real-world public recommendation benchmarks and justify the effectiveness of CauseRec with multi-aspects model analysis. The results demonstrate that the proposed CauseRec outperforms state-of-the-art sequential recommenders by learning accurate and robust user representations.

Learning Fair Representations for Recommendation: A Graph-based Perspective

Abstract: As a key application of artificial intelligence, recommender systems are among the most pervasive computer aided systems to help users find potential items of interests. Recently, researchers paid considerable attention to fairness issues for artificial intelligence applications. Most of these approaches assumed independence of instances, and designed sophisticated models to eliminate the sensitive information to facilitate fairness. However, recommender systems differ greatly from these approaches as users and items naturally form a user-item bipartite graph, and are collaboratively correlated in the graph structure. In this paper, we propose a novel graph based technique for ensuring fairness of any recommendation models. Here, the fairness requirements refer to not exposing sensitive feature set in the user modeling process. Specifically, given the original embeddings from any recommendation models, we learn a composition of filters that transform each user’s and each item’s original embeddings into a filtered embedding space based on the sensitive feature set. For each user, this transformation is achieved under the adversarial learning of a user-centric graph, in order to obfuscate each sensitive feature between both the filtered user embedding and the sub graph structures of this user. Finally, extensive experimental results clearly show the effectiveness of our proposed model for fair recommendation. We publish the source code at https://github.com/newlei/FairGo.

DiffNet++: A Neural Influence and Interest Diffusion Network for Social Recommendation

Abstract: Social recommendation has emerged to leverage social connections among users for recommendation Early approaches relied on utilizing each user's first-order social neighbors' interests for better user modeling. Recently, we propose a preliminary work of a neural influence Diffusion Network (i.e., DiffNet) to model the recursive social diffusion process for each user, such that the influence diffusion hidden in the higher-order social network is captured. Despite the superior performance of DiffNet, we argue that, as users play a central role in both user-user social network and user-item interest network, only modeling the influence diffusion process would neglect the latent collaborative interests of users hidden in the user-item interest network. To this end, we propose DiffNet++, an improved algorithm of DiffNet that models the neural influence diffusion and interest diffusion in a unified framework. Specifically, DiffNet++ advances DiffNet by injecting both the higher-order user latent interest reflected in the user-item graph and higher-order user influence reflected in the user-user graph for user embedding learning. Furthermore, we design a multi-level attention network that learns how to attentively aggregate user embeddings from different graphs. Finally, extensive experimental results on two real-world datasets clearly show the effectiveness of our proposed model.

Task-adaptive Neural Process for User Cold-Start Recommendation

Abstract: User cold-start recommendation is a long-standing challenge for recommender systems due to the fact that only a few interactions of cold-start users can be exploited. Recent studies seek to address this challenge from the perspective of meta learning, and most of them follow a manner of parameter initialization, where the model parameters can be learned by a few steps of gradient updates. While these gradient-based meta-learning models achieve promising performances to some extent, a fundamental problem of them is how to adapt the global knowledge learned from previous tasks for the recommendations of cold-start users more effectively. In this paper, we develop a novel meta-learning recommender called task-adaptive neural process (TaNP). TaNP is a new member of the neural process family, where making recommendations for each user is associated with a corresponding stochastic process. TaNP directly maps the observed interactions of each user to a predictive distribution, sidestepping some training issues in gradient-based meta-learning models. More importantly, to balance the trade-off between model capacity and adaptation reliability, we introduce a novel task-adaptive mechanism. It enables our model to learn the relevance of different tasks and customize the global knowledge to the task-related decoder parameters for estimating user preferences. We validate TaNP on multiple benchmark datasets in different experimental settings. Empirical results demonstrate that TaNP yields consistent improvements over several state-of-the-art meta-learning recommenders.

Graph Embedding for Recommendation against Attribute Inference Attacks

Abstract: In recent years, recommender systems play a pivotal role in helping users identify the most suitable items that satisfy personal preferences. As user-item interactions can be naturally modelled as graph-structured data, variants of graph convolutional networks (GCNs) have become a well-established building block in the latest recommenders. Due to the wide utilization of sensitive user profile data, existing recommendation paradigms are likely to expose users to the threat of privacy breach, and GCN-based recommenders are no exception. Apart from the leakage of raw user data, the fragility of current recommenders under inference attacks offers malicious attackers a backdoor to estimate users’ private attributes via their behavioral footprints and the recommendation results. However, little attention has been paid to developing recommender systems that can defend such attribute inference attacks, and existing works achieve attack resistance by either sacrificing considerable recommendation accuracy or only covering specific attack models or protected information. In our paper, we propose GERAI, a novel differentially private graph convolutional network to address such limitations. Specifically, in GERAI, we bind the information perturbation mechanism in differential privacy with the recommendation capability of graph convolutional networks. Furthermore, based on local differential privacy and functional mechanism, we innovatively devise a dual-stage encryption paradigm to simultaneously enforce privacy guarantee on users’ sensitive features and the model optimization process. Extensive experiments show the superiority of GERAI in terms of its resistance to attribute inference attacks and recommendation effectiveness.

RetaGNN: Relational Temporal Attentive Graph Neural Networks for Holistic Sequential Recommendation

Abstract: Sequential recommendation (SR) is to accurately recommend a list of items for a user based on her current accessed ones. While new-coming users continuously arrive in the real world, one crucial task is to have inductive SR that can produce embeddings of users and items without re-training. Given user-item interactions can be extremely sparse, another critical task is to have transferable SR that can transfer the knowledge derived from one domain with rich data to another domain. In this work, we aim to present the holistic SR that simultaneously accommodates conventional, inductive, and transferable settings. We propose a novel deep learning-based model, Relational Temporal Attentive Graph Neural Networks (RetaGNN), for holistic SR. The main idea of RetaGNN is three-fold. First, to have inductive and transferable capabilities, we train a relational attentive GNN on the local subgraph extracted from a user-item pair, in which the learnable weight matrices are on various relations among users, items, and attributes, rather than nodes or edges. Second, long-term and short-term temporal patterns of user preferences are encoded by a proposed sequential self-attention mechanism. Third, a relation-aware regularization term is devised for better training of RetaGNN. Experiments conducted on MovieLens, Instagram, and Book-Crossing datasets exhibit that RetaGNN can outperform state-of-the-art methods under conventional, inductive, and transferable settings. The derived attention weights also bring model explainability.

Hierarchical Personalized Federated Learning for User Modeling

Abstract: User modeling aims to capture the latent characteristics of users from their behaviors, and is widely applied in numerous applications. Usually, centralized user modeling suffers from the risk of privacy leakage. Instead, federated user modeling expects to provide a secure multi-client collaboration for user modeling through federated learning. Existing federated learning methods are mainly designed for consistent clients, which cannot be directly applied to practical scenarios, where different clients usually store inconsistent user data. Therefore, it is a crucial demand to design an appropriate federated solution that can better adapt to user modeling tasks, and however, meets following critical challenges: 1) Statistical heterogeneity. The distributions of user data in different clients are not always independently identically distributed which leads to personalized clients; 2) Privacy heterogeneity. User data contains both public and private information, which have different levels of privacy. It means we should balance different information to be shared and protected; 3) Model heterogeneity. The local user models trained with client records are heterogeneous which need flexible aggregation in the server. In this paper, we propose a novel client-server architecture framework, namely Hierarchical Personalized Federated Learning (HPFL) to serve federated learning in user modeling with inconsistent clients. In the framework, we first define hierarchical information to finely partition the data with privacy heterogeneity. On this basis, the client trains a user model which contains different components designed for hierarchical information. Moreover, client processes a fine-grained personalized update strategy to update personalized user model for statistical heterogeneity. Correspondingly, the server completes a differentiated component aggregation strategy to flexibly aggregate heterogeneous user models in the case of privacy and model heterogeneity. Finally, we conduct extensive experiments on real-world datasets, which demonstrate the effectiveness of the HPFL framework.

FeedRec: News Feed Recommendation with Various User Feedbacks.

Abstract: Personalized news recommendation techniques are widely adopted by many online news feed platforms to target user interests. Learning accurate user interest models is important for news recommendation. Most existing methods for news recommendation rely on implicit feedbacks like click behaviors for inferring user interests and model training. However, click behaviors are implicit feedbacks and usually contain heavy noise. In addition, they cannot help infer complicated user interest such as dislike. Besides, the feed recommendation models trained solely on click behaviors cannot optimize other objectives such as user engagement. In this paper, we present a news feed recommendation method that can exploit various kinds of user feedbacks to enhance both user interest modeling and recommendation model training. In our method we propose a unified user modeling framework to incorporate various explicit and implicit user feedbacks to infer both positive and negative user interests. In addition, we propose a strong-to-weak attention network that uses the representations of stronger feedbacks to distill positive and negative user interests from implicit weak feedbacks for accurate user interest modeling. Besides, we propose a multi-feedback model training framework by jointly training the model in the click, finish and dwell time prediction tasks to learn an engagement-aware feed recommendation model. Extensive experiments on real-world dataset show that our approach can effectively improve the model performance in terms of both news clicks and user engagement.

The relationship between user types and gamification designs

Abstract: Gamification has been discussed as a standout approach to improve user experience, with different studies showing that users can have different preferences over game elements according to their user types. However, relatively less is known how different kinds of users may react to different types of gamification. Therefore, in this study ( $$N=331$$ ) we investigate how user orientation (Achiever, Disruptor, Free Spirit, Philanthropist, Player, and Socializer) is associated with the preference for and perceived sense of accomplishment from different gamification designs. Beyond singular associations between the user orientation and the gamification designs, the findings indicate no comprehensive and consistent patterns of associations. From the six user orientations, five presented significant associations: Socializer orientation was positively associated with Social, Fictional, and Personal designs, while negatively associated with Performance design; Player orientation was positively associated with Social (Accomplishment), Personal, and Ecological designs, while negatively associated with the Social design (Preference); Disruptor orientation was positively associated with Social design; Achiever orientation was positively associated with Performance and Social designs; and Free Spirit orientation was negatively associated with Social design. Based on the results, we provide recommendations on how to personalize gamified systems and set further research trajectories on personalized gamification.

How Am I Doing?: Evaluating Conversational Search Systems Offline

Abstract: As conversational agents like Siri and Alexa gain in popularity and use, conversation is becoming a more and more important mode of interaction for search. Conversational search shares some features with traditional search, but differs in some important respects: conversational search systems are less likely to return ranked lists of results (a SERP), more likely to involve iterated interactions, and more likely to feature longer, well-formed user queries in the form of natural language questions. Because of these differences, traditional methods for search evaluation (such as the Cranfield paradigm) do not translate easily to conversational search. In this work, we propose a framework for offline evaluation of conversational search, which includes a methodology for creating test collections with relevance judgments, an evaluation measure based on a user interaction model, and an approach to collecting user interaction data to train the model. The framework is based on the idea of “subtopics”, often used to model novelty and diversity in search and recommendation, and the user model is similar to the geometric browsing model introduced by RBP and used in ERR. As far as we know, this is the first work to combine these ideas into a comprehensive framework for offline evaluation of conversational search.

DeepRec: On-device Deep Learning for Privacy-Preserving Sequential Recommendation in Mobile Commerce

Abstract: Sequential recommendation techniques are considered to be a promising way of providing better user experience in mobile commerce by learning sequential interests within user historical interaction behaviors. However, the recently increasing focus on privacy concerns, such as the General Data Protection Regulation (GDPR), can significantly affect the deployment of state-of-the-art sequential recommendation techniques, because user behavior data are no longer allowed to be arbitrarily used without the user’s explicit permission. To address the issue, this paper proposes DeepRec, an on-device deep learning framework of mining interaction behaviors for sequential recommendation without sending any raw data or intermediate results out of the device, preserving user privacy maximally. DeepRec constructs a global model using data collected before GDPR and fine-tunes a personal model continuously on individual mobile devices using data collected after GDPR. DeepRec employs the model pruning and embedding sparsity techniques to reduce the computation and network overhead, making the model training process practical on computation-constraint mobile devices. Evaluation results show that DeepRec can achieve comparable recommendation accuracy to existing centralized recommendation approaches with small computation overhead and up to 10x reduction in network overhead.

A Graph-Enhanced Click Model for Web Search

Abstract: To better exploit search logs and model users' behavior patterns, numerous click models are proposed to extract users' implicit interaction feedback. Most traditional click models are based on the probabilistic graphical model (PGM) framework, which requires manually designed dependencies and may oversimplify user behaviors. Recently, methods based on neural networks are proposed to improve the prediction accuracy of user behaviors by enhancing the expressive ability and allowing flexible dependencies. However, they still suffer from the data sparsity and cold-start problems. In this paper, we propose a novel graph-enhanced click model (GraphCM) for web search. Firstly, we regard each query or document as a vertex, and propose novel homogeneous graph construction methods for queries and documents respectively, to fully exploit both intra-session and inter-session information for the sparsity and cold-start problems. Secondly, following the examination hypothesis, we separately model the attractiveness estimator and examination predictor to output the attractiveness scores and examination probabilities, where graph neural networks and neighbor interaction techniques are applied to extract the auxiliary information encoded in the pre-constructed homogeneous graphs. Finally, we apply combination functions to integrate examination probabilities and attractiveness scores into click predictions. Extensive experiments conducted on three real-world session datasets show that GraphCM not only outperforms the state-of-art models, but also achieves superior performance in addressing the data sparsity and cold-start problems.

A Structured Review of Data Management Technology for Interactive Visualization and Analysis

Abstract: In the last two decades, interactive visualization and analysis have become a central tool in data-driven decision making. Concurrently to the contributions in data visualization, research in data management has produced technology that directly benefits interactive analysis. Here, we contribute a systematic review of 30 years of work in this adjacent field, and highlight techniques and principles we believe to be underappreciated in visualization work. We structure our review along two axes. First, we use task taxonomies from the visualization literature to structure the space of interactions in usual systems. Second, we created a categorization of data management work that strikes a balance between specificity and generality. Concretely, we contribute a characterization of 131 research papers along these two axes. We find that five notions in data management venues fit interactive visualization systems well: materialized views, approximate query processing, user modeling and query prediction, muiti-query optimization, lineage techniques, and indexing techniques. In addition, we find a preponderance of work in materialized views and approximate query processing, most targeting a limited subset of the interaction tasks in the taxonomy we used. This suggests natural avenues of future research both in visualization and data management. Our categorization both changes how we visualization researchers design and build our systems, and highlights where future work is necessary.

Learning Heterogeneous Temporal Patterns of User Preference for Timely Recommendation

Abstract: Recommender systems have achieved great success in modeling user’s preferences on items and predicting the next item the user would consume. Recently, there have been many efforts to utilize time information of users’ interactions with items to capture inherent temporal patterns of user behaviors and offer timely recommendations at a given time. Existing studies regard the time information as a single type of feature and focus on how to associate it with user preferences on items. However, we argue they are insufficient for fully learning the time information because the temporal patterns of user preference are usually heterogeneous. A user’s preference for a particular item may 1) increase periodically or 2) evolve over time under the influence of significant recent events, and each of these two kinds of temporal pattern appears with some unique characteristics. In this paper, we first define the unique characteristics of the two kinds of temporal pattern of user preference that should be considered in time-aware recommender systems. Then we propose a novel recommender system for timely recommendations, called TimelyRec, which jointly learns the heterogeneous temporal patterns of user preference considering all of the defined characteristics. In TimelyRec, a cascade of two encoders captures the temporal patterns of user preference using a proposed attention module for each encoder. Moreover, we introduce an evaluation scenario that evaluates the performance on predicting an interesting item and when to recommend the item simultaneously in top-K recommendation (i.e., item-timing recommendation). Our extensive experiments on a scenario for item recommendation and the proposed scenario for item-timing recommendation on real-world datasets demonstrate the superiority of TimelyRec and the proposed attention modules.

Personalized Approximate Pareto-Efficient Recommendation

Abstract: Real-world recommendation systems usually have different learning objectives and evaluation criteria on accuracy, diversity or novelty. Therefore, multi-objective recommendation (MOR) has been widely explored to jointly model different objectives. Pareto efficiency, where no objective can be further improved without hurting others, is viewed as an optimal situation in multi-objective optimization. Recently, Pareto efficiency model has been introduced to MOR, while all existing scalarization methods only have shared objective weights for all instances. To capture users’ objective-level preferences and enhance personalization in Pareto-efficient recommendation, we propose a novel Personalized Approximate Pareto-Efficient Recommendation (PAPERec) framework for multi-objective recommendation. Specifically, we design an approximate Pareto-efficient learning based on scalarization with KKT conditions that closely mimics Pareto efficiency, where users have personalized weights on different objectives. We propose a Pareto-oriented reinforcement learning module to find appropriate personalized objective weights for each user, with the weighted sum of multiple objectives’ gradients considered in reward. In experiments, we conduct extensive offline and online evaluations on a real-world recommendation system. The significant improvements verify the effectiveness of PAPERec in practice. We have deployed PAPERec on WeChat Top Stories, affecting millions of users. The source codes are released in https://github.com/onepunch-cyber/PAPERec.

Social mining-based clustering process for big-data integration

Abstract: With the development of information technology, ambient intelligence has been combined with various application areas so as to create new convergence service industries. Through IT convergence, human-oriented technologies for improving people’s quality of life has continued to be developed. Healthcare service that has been provided along with the development of various smart IT devices makes it possible to realize more efficient healthcare of people. Therefore, along with such a medical service, the advanced lifecare service for physical and mental health has been demanded. In order to meet the healthcare demands, an advanced healthcare platform has been developed. Lifecare service has been expanded to healthcare, the disease with the highest mortality induced by complications so that the service for disease survivals have been offered. Accordingly, a big-data integration and advanced healthcare platform based on patients’ life logs are developed in order for health service. In this platform, it is possible to establish an optimized model with the knowledge base and predict diseases and complications and judge a degree of risk with the use of information filtering. The conventional filtering based on a data model using scatter life logs makes use of user attribute information only for clustering so that it has low accuracy. Also, in calculating the similarity of actual users, such a method does not apply social relationships. Therefore, this study proposes a social mining based cluster process for big-data integration. The proposed method uses conventional static model information and the information extracted from the social network in order to create reliable user modeling and applies a different level of weight depending on users’ relations. In the clustering process for disease survivals’ health conditions, it is possible to predict their health risk. Based on the risk and expectation of healthcare event occurrence, their health conditions can be improved. Lifecare forecasting model that uses social relation performs social sequence mining using PrefixSpan to complement the weak point that spends a long time to scan it repeatedly in the candidate pattern. For performance evaluation, the social mining based cluster process was compared with a conventional cluster method. More specifically, the estimation accuracy of the conventional model-based cluster method was compared with the accuracy of the social mining based cluster process. As a result, the proposed method in the mining-based healthcare platform had better performance than the conventional model-based cluster method.

A Reinforcement Learning Approach for User Preference-Aware Energy Sharing Systems

Abstract: Energy Sharing Systems (ESS) are envisioned to be the future of power systems. In these systems, consumers equipped with renewable energy generation capabilities are able to participate in an energy market to sell their energy. This paper proposes an ESS that, differently from previous works, takes into account the consumers’ preference, engagement, and bounded rationality. The problem of maximizing the energy exchange while considering such user modeling is formulated and shown to be NP-Hard. To learn the user behavior, two heuristics are proposed: 1) a Reinforcement Learning-based algorithm, which provides a bounded regret and 2) a more computationally efficient heuristic, named BPT- ${K}$ , with guaranteed termination and correctness. A comprehensive experimental analysis is conducted against state-of-the-art solutions using realistic datasets. Results show that including user modeling and learning provides significant performance improvements compared to state-of-the-art approaches. Specifically, the proposed algorithms result in 25% higher efficiency and 27% more transferred energy. Furthermore, the learning algorithms converge to a value less than 5% of the optimal solution in less than 3 months of learning.

One Person, One Model, One World: Learning Continual User Representation without Forgetting

Abstract: Learning user representations is a vital technique toward effective user modeling and personalized recommender systems. Existing approaches often derive an individual set of model parameters for each task by training on separate data. However, the representation of the same user potentially has some commonalities, such as preference and personality, even in different tasks. As such, these separately trained representations could be suboptimal in performance as well as inefficient in terms of parameter sharing. In this paper, we delve on research to continually learn user representations task by task, whereby new tasks are learned while using partial parameters from old ones. A new problem arises since when new tasks are trained, previously learned parameters are very likely to be modified, and as a result, an artificial neural network (ANN)-based model may lose its capacity to serve for well-trained previous tasks forever, this issue is termed catastrophic forgetting. To address this issue, we present Conure the first continual, or lifelong, user representation learner --- i.e., learning new tasks over time without forgetting old ones. Specifically, we propose iteratively removing less important weights of old tasks in a deep user representation model, motivated by the fact that neural network models are usually over-parameterized. In this way, we could learn many tasks with a single model by reusing the important weights, and modifying the less important weights to adapt to new tasks. We conduct extensive experiments on two real-world datasets with nine tasks and show that Conure largely exceeds the standard model that does not purposely preserve such old "knowledge'', and performs competitively or sometimes better than models which are trained either individually for each task or simultaneously by merging all task data.

Future-Aware Diverse Trends Framework for Recommendation

Abstract: In recommender systems, modeling user-item behaviors is essential for user representation learning. Existing sequential recommenders consider the sequential correlations between historically interacted items for capturing users’ historical preferences. However, since users’ preferences are by nature time-evolving and diversified, solely modeling the historical preference (without being aware of the time-evolving trends of preferences) can be inferior for recommending complementary or fresh items and thus hurt the effectiveness of recommender systems. In this paper, we bridge the gap between the past preference and potential future preference by proposing the future-aware diverse trends (FAT) framework. By future-aware, for each inspected user, we construct the future sequences from other similar users, which comprise of behaviors that happen after the last behavior of the inspected user, based on a proposed neighbor behavior extractor. By diverse trends, supposing the future preferences can be diversified, we propose the diverse trends extractor and the time-aware mechanism to represent the possible trends of preferences for a given user with multiple vectors. We leverage both the representations of historical preference and possible future trends to obtain the final recommendation. The quantitative and qualitative results from relatively extensive experiments on real-world datasets demonstrate the proposed framework not only outperforms the state-of-the-art sequential recommendation methods across various metrics, but also makes complementary and fresh recommendations.

Combining Explicit Entity Graph with Implicit Text Information for News Recommendation

Abstract: News recommendation is very crucial for online news services to improve user experience and alleviate information overload. Precisely learning representations of news and users is the core problem in news recommendation. Existing models usually focus on implicit text information to learn corresponding representations, which may be insufficient for modeling user interests. Even if entity information is considered from external knowledge, it may still not be used explicitly and effectively for user modeling. In this paper, we propose a novel news recommendation approach, which combine explicit entity graph with implicit text information. The entity graph consists of two types of nodes and three kinds of edges, which represent chronological order, related and affiliation relationship. Then graph neural network is utilized for reasoning on these nodes. Extensive experiments on a real-world dataset, Microsoft News Dataset (MIND), validate the effectiveness of our proposed approach.

Modeling and Leveraging Analytic Focus During Exploratory Visual Analysis

Abstract: Visual analytics systems enable highly interactive exploratory data analysis. Across a range of fields, these technologies have been successfully employed to help users learn from complex data. However, these same exploratory visualization techniques make it easy for users to discover spurious findings. This paper proposes new methods to monitor a user’s analytic focus during visual analysis of structured datasets and use it to surface relevant articles that contextualize the visualized findings. Motivated by interactive analyses of electronic health data, this paper introduces a formal model of analytic focus, a computational approach to dynamically update the focus model at the time of user interaction, and a prototype application that leverages this model to surface relevant medical publications to users during visual analysis of a large corpus of medical records. Evaluation results with 24 users show that the modeling approach has high levels of accuracy and is able to surface highly relevant medical abstracts.

Education 4.0: AI Empowers Smart Blended Learning Process with Biofeedback

Abstract: This paper describes the teaching model for Education 4.0, that uses elements from different disciplines such as electronic technology, Artificial Intelligence (AI), health, multimodal learning analytics, education, etc. Smart blended learning process for Education 4.0, implements in each phase AI methods such as user modeling, adaptivity, machine learning, chatbots, and semantic text recognition tools to increase learning success and to reduce the dropout rate in examinations. On the one hand, multimodal data, from online course and wearables, enables further statements about the concrete learning situation, and on the other hand, it increases the students' subjective experience of emotional states, their stress perception, well-being or energy level. This paper reports on experiments where the combination of AI, Internet of Things (IoT) and Biofeedback in a smart blended learning process attempt to consider the characteristics of learners better.

HieRec: Hierarchical User Interest Modeling for Personalized News Recommendation

Abstract: User interest modeling is critical for personalized news recommendation. Existing news recommendation methods usually learn a single user embedding for each user from their previous behaviors to represent their overall interest. However, user interest is usually diverse and multi-grained, which is difficult to be accurately modeled by a single user embedding. In this paper, we propose a news recommendation method with hierarchical user interest modeling, named HieRec. Instead of a single user embedding, in our method each user is represented in a hierarchical interest tree to better capture their diverse and multi-grained interest in news. We use a three-level hierarchy to represent 1) overall user interest; 2) user interest in coarse-grained topics like sports; and 3) user interest in fine-grained topics like football. Moreover, we propose a hierarchical user interest matching framework to match candidate news with different levels of user interest for more accurate user interest targeting. Extensive experiments on two real-world datasets validate our method can effectively improve the performance of user modeling for personalized news recommendation.

Truthful Multi-Resource Transaction Mechanism for P2P Task Offloading Based on Edge Computing

Abstract: Peer-to-Peer (P2P) resource sharing promotes local resource-hungry task offloading to other mobile devices and balances the resource consumption between mobile devices. Most of existing P2P task offloading systems aims to solve the resource sharing between one pair exclusively without considering the cost of resource supply and the strategic behaviors of mobile users. In this paper, we propose two user models for the P2P task offloading system: honest user model and strategy user model. For the honest user model, we formulate the resource allocation maximization problem with latency and energy consumption constraints as an Integer Linear Programming. We show that the solution for honest user model can output 189% resource transactions of that for the strategic users. For the strategy user model, we propose a double auction-based P2P task offloading system, and design a truthful multi-resource transaction mechanism to maximize the number of resource transactions. We first group the mobile users based on the connected components to improve the efficiency of double auction. Then we utilize the McAfee Double Auction to price the resource transactions. Finally, we split each winning mobile user of double auction into multiple virtual mobile users, and use the matching approach to calculate the resource allocation. Through both rigorous theoretical analysis and extensive simulations, we demonstrate that the designed multi-resource transaction mechanism satisfies the desirable properties of computational efficiency, individual rationality, budget balance, truthfulness for resource request/supply, and general truthfulness for bid/ask price.