Session-based recommendation, which aims to predict the user's immediate next action based on anonymous sessions, is a key task in many online services (e.g., e-commerce, media streaming). Recently, Self-Attention Network (SAN) has achieved significant success in various sequence modeling tasks without using either recurrent or convolutional network. However, SAN lacks local dependencies that exist over adjacent items and limits its capacity for learning contextualized representations of items in sequences. In this paper, we propose a graph contextualized self-attention model (GC-SAN), which utilizes both graph neural network and self-attention mechanism, for session-based recommendation. In GC-SAN, we dynamically construct a graph structure for session sequences and capture rich local dependencies via graph neural network (GNN). Then each session learns long-range dependencies by applying the self-attention mechanism. Finally, each session is represented as a linear combination of the global preference and the current interest of that session. Extensive experiments on two real-world datasets show that GC-SAN outperforms state-of-the-art methods consistently.

/pdf/graph-contextualized-self-attention-network-for-session-36cv52ian8.pdf

Graph contextualized self-attention network for session-based recommendation

Microblog has been a popular media platform for reporting and propagating news. However, fake news spreading on microblogs would severely jeopardize its public credibility. To identify the truthfulness of news on microblogs, images are very crucial content. In this paper, we explore the key role of image content in the task of automatic news verification on microblogs. Existing approaches to news verification depend on features extracted mainly from the text content of news tweets, while image features for news verification are often ignored. According to our study, however, images are very popular and have a great influence on microblogs news propagation. In addition, fake and real news events have different image distribution patterns. Therefore, we propose several visual and statistical features to characterize these patterns visually and statistically for detecting fake news. Experiments on a real-world multimedia dataset collected from Sina Weibo validate the effectiveness of our proposed image features. The news verification performance of our method outperforms baseline methods. To the best of our knowledge, this is the first attempt that systematically explores image features on news verification task.

Novel Visual and Statistical Image Features for Microblogs News Verification

Owing to the superiority of GNN in learning on graph data and its efficacy in capturing collaborative signals and sequential patterns, utilizing GNN techniques in recommender systems has gain increasing interests in academia and industry. In this survey, we provide a comprehensive review of the most recent works on GNN-based recommender systems. We proposed a classification scheme for organizing existing works. For each category, we briefly clarify the main issues, and detail the corresponding strategies adopted by the representative models. We also discuss the advantages and limitations of the existing strategies. Furthermore, we suggest several promising directions for future researches. We hope this survey can provide readers with a general understanding of the recent progress in this field, and shed some light on future developments.

Graph Neural Networks in Recommender Systems: A Survey

How do humans recognize the action "opening a book" ? We argue that there are two important cues: modeling temporal shape dynamics and modeling functional relationships between humans and objects. In this paper, we propose to represent videos as space-time region graphs which capture these two important cues. Our graph nodes are defined by the object region proposals from different frames in a long range video. These nodes are connected by two types of relations: (i) similarity relations capturing the long range dependencies between correlated objects and (ii) spatial-temporal relations capturing the interactions between nearby objects. We perform reasoning on this graph representation via Graph Convolutional Networks. We achieve state-of-the-art results on both Charades and Something-Something datasets. Especially for Charades, we obtain a huge 4.4% gain when our model is applied in complex environments.

Videos as Space-Time Region Graphs.

Recommender system (RS) targets at providing accurate item recommendations to users with respect to their preferences; it has been widely employed in various online applications for addressing the problem of information explosion and improving user experience. In the past decades, while tremendous efforts have been made in enhancing the performance of RSs, some long-standing challenges, such as data sparsity, cold start, and result diversity, are unaddressed. Along this line, an emerging research trend is to exploit the rich semantic information contained in the knowledge graph (KG); it has been proven to be an effective way to enhance the capability of RSs. To this end, we provide a focused survey on KG-based RS via a holistic perspective of both technologies and applications. Specifically, firstly, we briefly review the core concepts and classical algorithms of the RSs and KGs. Secondly, we comprehensively introduce the representative and state-of-the-art works in this field based on different strategies of exploiting KGs for RSs. Meanwhile, we also summarize some typical application scenarios of KG-based RSs, for facilitating the hands-on practices of corresponding algorithms. Finally, we present our opinions on the prospects of KG-based RS and suggest some future research directions in this area.

/pdf/a-survey-on-knowledge-graph-based-recommender-systems-2mm7glxyn0.pdf

A survey on knowledge graph-based recommender systems

Social media is emerging as a new mainstream means of interacting around online media. Social influence mining in social networks is therefore of critical importance in real-world applications such as friend suggestion and photo recommendation. Social media is inherently multimodal, including rich types of user contributed content and social link information. Most of the existing research suffers from two limitations: 1) only utilizing the textual information, and/or 2) only analyzing the generic influence but ignoring the more important topic-level influence. To address these limitations, in this paper we develop a novel Topic-Sensitive Influencer Mining (TSIM) framework in interest-based social media networks. Specifically, we take Flickr as the study platform. People in Flickr interact with each other through images. TSIM aims to find topical influential users and images. The influence estimation is determined with a hypergraph learning approach. In the hypergraph, the vertices represent users and images, and the hyperedges are utilized to capture multi-type relations including visual-textual content relations among images, and social links between users and images. Algorithmwise, TSIM first learns the topic distribution by leveraging user-contributed images, and then infers the influence strength under different topics for each node in the hypergraph. Extensive experiments on a real-world dataset of more than 50 K images and 70 K comment/favorite links from Flickr have demonstrated the effectiveness of our proposed framework. In addition, we also report promising results of friend suggestion and photo recommendation via TSIM on the same dataset.

Topic-Sensitive Influencer Mining in Interest-Based Social Media Networks via Hypergraph Learning

Nowadays, with the rapid development of social media, there is a great deal of news produced every day. How to detect fake news automatically from a large of multimedia posts has become very important for people, the government and news recommendation sites. However, most of the existing approaches either extract features from the text of the post which is a single modality or simply concatenate the visual features and textual features of a post to get a multimodal feature and detect fake news. Most of them ignore the background knowledge hidden in the text content of the post which facilitates fake news detection. To address these issues, we propose a novel Knowledge-driven Multimodal Graph Convolutional Network (KMGCN) to model the semantic representations by jointly modeling the textual information, knowledge concepts and visual information into a unified framework for fake news detection. Instead of viewing text content as word sequences normally, we convert them into a graph, which can model non-consecutive phrases for better obtaining the composition of semantics. Besides, we not only convert visual information as nodes of graphs but also retrieve external knowledge from real-world knowledge graph as nodes of graphs to provide complementary semantics information to improve fake news detection. We utilize a well-designed graph convolutional network to extract the semantic representation of these graphs. Extensive experiments on two public real-world datasets illustrate the validation of our approach.

Fake News Detection via Knowledge-driven Multimodal Graph Convolutional Networks

The wide dissemination and misleading effects of online rumors on social media have become a critical issue concerning the public and government. Detecting and regulating social media rumors is important for ensuring users receive truthful information and maintaining social harmony. Most of the existing rumor detection methods focus on inferring clues from media content and social context, which largely ignores the rich knowledge information behind the highly condensed text which is useful for rumor verification. Furthermore, existing rumor detection models underperform on unseen events because they tend to capture lots of event-specific features in seen data which cannot be transferred to newly emerged events. In order to address these issues, we propose a novel Multimodal Knowledge-aware Event Memory Network (MKEMN) which utilizes the Multi-modal Knowledge-aware Network (MKN) and Event Memory Network (EMN) as building blocks for social media rumor detection. Specifically, the MKN learns the multi-modal representation of the post on social media and retrieves external knowledge from real-world knowledge graph to complement the semantic representation of short texts of posts and takes conceptual knowledge as additional evidence to improve rumor detection. The EMN extracts event-invariant features of events and stores them into global memory. Given an event representation, the EMN takes it as a query to retrieve the memory network and output the corresponding features shared among events. With the additional information provided by EMN, our model can learn robust representations of events and consistently perform well on the newly emerged events. Extensive experiments on two Twitter benchmark datasets demonstrate that our rumor detection method achieves much better results than state-of-the-art methods.

Multi-modal Knowledge-aware Event Memory Network for Social Media Rumor Detection

Compared with the traditional recommendation system, sequential recommendation holds the ability of capturing the evolution of users' dynamic interests. Many previous studies in sequential recommendation focus on the accuracy of predicting the next item that a user might interact with, while generally ignore providing explanations why the item is recommended to the user. Appropriate explanations are critical to help users adopt the recommended item, and thus improve the transparency and trustworthiness of the recommendation system. In this paper, we propose a novel Explainable Interaction-driven User Modeling (EIUM) algorithm to exploit Knowledge Graph (KG) for constructing an effective and explainable sequential recommender. Qualified semantic paths between specific user-item pair are extracted from KG. Encoding those semantic paths and learning the importance scores for each path provides the path-wise explanation for the recommendation system. Different from traditional item- level sequential modeling methods, we capture the interaction-level user dynamic preferences by modeling the sequential interactions. It is a high- level representation which contains auxiliary semantic information from KG. Furthermore, we adopt a joint learning manner for better representation learning by employing multi-modal fusion, which benefits from the structural constraints in KG and involves three kinds of modalities. Extensive experiments on the large-scale dataset show the better performance of our approach in making sequential recommendations in terms of both accuracy and explainability.

Explainable Interaction-driven User Modeling over Knowledge Graph for Sequential Recommendation

The sequential recommendation is an important task for online user-oriented services, such as purchasing products, watching videos, and social media consumption. Recent work usually used RNN-based methods to derive an overall embedding of the whole behavior sequence, which fails to discriminate the significance of individual user behaviors and thus decreases the recommendation performance. Besides, RNN-based encoding has fixed size and makes further recommendation application inefficient and inflexible. The online sequential behaviors of a user are generally heterogeneous, polysemous, and dynamically context-dependent. In this paper, we propose a unified Contextual Self-Attention Network (CSAN) to address the three properties. Heterogeneous user behaviors are considered in our model that are projected into a common latent semantic space. Then the output is fed into the feature-wise self-attention network to capture the polysemy of user behaviors. In addition, the forward and backward position encoding matrices are proposed to model dynamic contextual dependency. Through extensive experiments on two real-world datasets, we demonstrate the superior performance of the proposed model compared with other state-of-the-art algorithms.

https://dl.acm.org/doi/pdf/10.1145/3240508.3240609

Quan Fang

Papers

Topic-Sensitive Influencer Mining in Interest-Based Social Media Networks via Hypergraph Learning

Fake News Detection via Knowledge-driven Multimodal Graph Convolutional Networks

Multi-modal Knowledge-aware Event Memory Network for Social Media Rumor Detection

Explainable Interaction-driven User Modeling over Knowledge Graph for Sequential Recommendation

CSAN: Contextual Self-Attention Network for User Sequential Recommendation