[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

Click-through rate prediction is an essential task in industrial applications, such as online advertising. Recently deep learning based models have been proposed, which follow a similar Embedding&MLP paradigm. In these methods large scale sparse input features are first mapped into low dimensional embedding vectors, and then transformed into fixed-length vectors in a group-wise manner, finally concatenated together to fed into a multilayer perceptron (MLP) to learn the nonlinear relations among features. In this way, user features are compressed into a fixed-length representation vector, in regardless of what candidate ads are. The use of fixed-length vector will be a bottleneck, which brings difficulty for Embedding&MLP methods to capture user's diverse interests effectively from rich historical behaviors. In this paper, we propose a novel model: Deep Interest Network (DIN) which tackles this challenge by designing a local activation unit to adaptively learn the representation of user interests from historical behaviors with respect to a certain ad. This representation vector varies over different ads, improving the expressive ability of model greatly. Besides, we develop two techniques: mini-batch aware regularization and data adaptive activation function which can help training industrial deep networks with hundreds of millions of parameters. Experiments on two public datasets as well as an Alibaba real production dataset with over 2 billion samples demonstrate the effectiveness of proposed approaches, which achieve superior performance compared with state-of-the-art methods. DIN now has been successfully deployed in the online display advertising system in Alibaba, serving the main traffic.

Deep Interest Network for Click-Through Rate Prediction

In recent years, deep neural networks have been successful in both industry and academia, especially for computer vision tasks. The great success of deep learning is mainly due to its scalability to encode large-scale data and to maneuver billions of model parameters. However, it is a challenge to deploy these cumbersome deep models on devices with limited resources, e.g., mobile phones and embedded devices, not only because of the high computational complexity but also the large storage requirements. To this end, a variety of model compression and acceleration techniques have been developed. As a representative type of model compression and acceleration, knowledge distillation effectively learns a small student model from a large teacher model. It has received rapid increasing attention from the community. This paper provides a comprehensive survey of knowledge distillation from the perspectives of knowledge categories, training schemes, teacher-student architecture, distillation algorithms, performance comparison and applications. Furthermore, challenges in knowledge distillation are briefly reviewed and comments on future research are discussed and forwarded.

Knowledge Distillation: A Survey

The choice of activation functions in deep networks has a significant effect on the training dynamics and task performance. Currently, the most successful and widely-used activation function is the Rectified Linear Unit (ReLU). Although various hand-designed alternatives to ReLU have been proposed, none have managed to replace it due to inconsistent gains. In this work, we propose to leverage automatic search techniques to discover new activation functions. Using a combination of exhaustive and reinforcement learning-based search, we discover multiple novel activation functions. We verify the effectiveness of the searches by conducting an empirical evaluation with the best discovered activation function. Our experiments show that the best discovered activation function, $f(x) = x \cdot \text{sigmoid}(\beta x)$, which we name Swish, tends to work better than ReLU on deeper models across a number of challenging datasets. For example, simply replacing ReLUs with Swish units improves top-1 classification accuracy on ImageNet by 0.9\% for Mobile NASNet-A and 0.6\% for Inception-ResNet-v2. The simplicity of Swish and its similarity to ReLU make it easy for practitioners to replace ReLUs with Swish units in any neural network.

Searching for Activation Functions

To provide more accurate, diverse, and explainable recommendation, it is compulsory to go beyond modeling user-item interactions and take side information into account. Traditional methods like factorization machine (FM) cast it as a supervised learning problem, which assumes each interaction as an independent instance with side information encoded. Due to the overlook of the relations among instances or items (e.g., the director of a movie is also an actor of another movie), these methods are insufficient to distill the collaborative signal from the collective behaviors of users. In this work, we investigate the utility of knowledge graph (KG), which breaks down the independent interaction assumption by linking items with their attributes. We argue that in such a hybrid structure of KG and user-item graph, high-order relations --- which connect two items with one or multiple linked attributes --- are an essential factor for successful recommendation. We propose a new method named Knowledge Graph Attention Network (KGAT) which explicitly models the high-order connectivities in KG in an end-to-end fashion. It recursively propagates the embeddings from a node's neighbors (which can be users, items, or attributes) to refine the node's embedding, and employs an attention mechanism to discriminate the importance of the neighbors. Our KGAT is conceptually advantageous to existing KG-based recommendation methods, which either exploit high-order relations by extracting paths or implicitly modeling them with regularization. Empirical results on three public benchmarks show that KGAT significantly outperforms state-of-the-art methods like Neural FM and RippleNet. Further studies verify the efficacy of embedding propagation for high-order relation modeling and the interpretability benefits brought by the attention mechanism. We release the codes and datasets at https://github.com/xiangwang1223/knowledge_graph_attention_network.

KGAT: Knowledge Graph Attention Network for Recommendation

Click-through rate (CTR) prediction, whose goal is to estimate the probability of a user clicking on the item, has become one of the core tasks in the advertising system. For CTR prediction model, it is necessary to capture the latent user interest behind the user behavior data. Besides, considering the changing of the external environment and the internal cognition, user interest evolves over time dynamically. There are several CTR prediction methods for interest modeling, while most of them regard the representation of behavior as the interest directly, and lack specially modeling for latent interest behind the concrete behavior. Moreover, little work considers the changing trend of the interest. In this paper, we propose a novel model, named Deep Interest Evolution Network (DIEN), for CTR prediction. Specifically, we design interest extractor layer to capture temporal interests from history behavior sequence. At this layer, we introduce an auxiliary loss to supervise interest extracting at each step. As user interests are diverse, especially in the e-commerce system, we propose interest evolving layer to capture interest evolving process that is relative to the target item. At interest evolving layer, attention mechanism is embedded into the sequential structure novelly, and the effects of relative interests are strengthened during interest evolution. In the experiments on both public and industrial datasets, DIEN significantly outperforms the state-of-the-art solutions. Notably, DIEN has been deployed in the display advertisement system of Taobao, and obtained 20.7% improvement on CTR.

/pdf/deep-interest-evolution-network-for-click-through-rate-5f6x3fkn7l.pdf

Deep Interest Evolution Network for Click-Through Rate Prediction

Estimating post-click conversion rate (CVR) accurately is crucial for ranking systems in industrial applications such as recommendation and advertising. Conventional CVR modeling applies popular deep learning methods and achieves state-of-the-art performance. However it encounters several task-specific problems in practice, making CVR modeling challenging. For example, conventional CVR models are trained with samples of clicked impressions while utilized to make inference on the entire space with samples of all impressions. This causes a sample selection bias problem. Besides, there exists an extreme data sparsity problem, making the model fitting rather difficult. In this paper, we model CVR in a brand-new perspective by making good use of sequential pattern of user actions, i.e., impression -> click -> conversion. The proposed Entire Space Multi-task Model (ESMM) can eliminate the two problems simultaneously by i) modeling CVR directly over the entire space, ii) employing a feature representation transfer learning strategy. Experiments on dataset gathered from Taobao's recommender system demonstrate that ESMM significantly outperforms competitive methods. We also release a sampling version of this dataset to enable future research. To the best of our knowledge, this is the first public dataset which contains samples with sequential dependence of click and conversion labels for CVR modeling.

https://dl.acm.org/doi/pdf/10.1145/3209978.3210104

Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate

Click-through rate (CTR) prediction is critical for industrial applications such as recommender system and online advertising. Practically, it plays an important role for CTR modeling in these applications by mining user interest from rich historical behavior data. Driven by the development of deep learning, deep CTR models with ingeniously designed architecture for user interest modeling have been proposed, bringing remarkable improvement of model performance over offline metric. However, great efforts are needed to deploy these complex models to online serving system for realtime inference, facing massive traffic request. Things turn to be more difficult when it comes to long sequential user behavior data, as the system latency and storage cost increase approximately linearly with the length of user behavior sequence. In this paper, we face directly the challenge of long sequential user behavior modeling and introduce our hands-on practice with the co-design of machine learning algorithm and online serving system for CTR prediction task. (i) From serving system view, we decouple the most resource-consuming part of user interest modeling from the entire model by designing a separate module named UIC (User Interest Center). UIC maintains the latest interest state for each user, whose update depends on realtime user behavior trigger event, rather than on traffic request. Hence UIC is latency free for realtime CTR prediction. (ii) From machine learning algorithm view, we propose a novel memory-based architecture named MIMN (Multi-channel user Interest Memory Network) to capture user interests from long sequential behavior data, achieving superior performance over state-of-the-art models. MIMN is implemented in an incremental manner with UIC module. Theoretically, the co-design solution of UIC and MIMN enables us to handle the user interest modeling with unlimited length of sequential behavior data. Comparison between model performance and system efficiency proves the effectiveness of proposed solution. To our knowledge, this is one of the first industrial solutions that are capable of handling long sequential user behavior data with length scaling up to thousands. It now has been deployed in the display advertising system in Alibaba.

Practice on Long Sequential User Behavior Modeling for Click-Through Rate Prediction

This paper proposes a new chaotic image encryption scheme, which employs Josephus traversing and mixed chaotic map. The scheme consists of three processes: key stream generation process; three-round scrambling process; and one-round diffusion process. The proposed mathematical model is applied for the key stream generator in the first process. The initial values and parameters are sensitive to both the secret keys in the new scheme and plain images. The second process employs the Josephus traversing in scrambling; then the rows and columns of pixels are exchanged. The third process can modify the pixel gray-level values and crack the strong correlations between adjacent pixels simultaneously. The initial conditions for chaotic systems are derived using external secret keys by applying some algebraic transformations to the key. Security analysis indicates that the new scheme is effective, which can resist common attacks.

Xiaoqiang Zhu

Papers

Deep Interest Network for Click-Through Rate Prediction

Deep Interest Evolution Network for Click-Through Rate Prediction

Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate

Practice on Long Sequential User Behavior Modeling for Click-Through Rate Prediction

An Image Encryption Algorithm Based on Josephus Traversing and Mixed Chaotic Map