NAIS: Neural Attentive Item Similarity Model for Recommendation

By Xiangnan He, Zhankui He, Jingkuan Song, Zhenguang Liu, Yu-Gang Jiang, Tat-seng Chua. IEEE Transactions on Knowledge and Data Engineering, 2018

531 citations recorded by the source corpus.

Item-to-item collaborative filtering (aka.item-based CF) has been long used for building recommender systems in industrial settings, owing to its interpretability and efficiency in real-time personalization. It builds a user's profile as her historically interacted items, recommending new items that are similar to the user's profile. As such, the key to an item-based CF method is in the estimation of item similarities. Early approaches use statistical measures such as cosine similarity and Pearson coefficient to estimate item similarities, which are less accurate since they lack tailored optimization for the recommendation task. In recent years, several works attempt to learn item similarities from data, by expressing the similarity as an underlying model and estimating model parameters by optimizing a recommendation-aware objective function. While extensive efforts have been made to use shallow linear models for learning item similarities, there has been relatively less work exploring nonlinear neural network models for item-based CF. In this work, we propose a neural network model named Neural Attentive Item Similarity model (NAIS) for item-based CF. The key to our design of NAIS is an attention network, which is capable of distinguishing which historical items in a user profile are more important for a prediction. Compared to the state-of-the-art item-based CF method Factored Item Similarity Model (FISM) [1] , our NAIS has stronger representation power with only a few additional parameters brought by the attention network. Extensive experiments on two public benchmarks demonstrate the effectiveness of NAIS. This work is the first attempt that designs neural network models for item-based CF, opening up new research possibilities for future developments of neural recommender systems.

Subfields: Artificial Intelligence, Information Systems, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/833a6052983fa55181b92516d0e1097d74585c58

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xiangnan He
2. Xiang Wang
3. Tat-seng Chua
4. Fuli Feng
5. Yongfeng Zhang
6. Xu Chen
7. Wayne Xin Zhao
8. Meng Wang

In Information Systems

1. Xiangnan He
2. Xiang Wang
3. Tat-seng Chua
4. Yongfeng Zhang
5. Fuli Feng
6. Xu Chen
7. Meng Wang
8. Le Wu

In Management Science and Operations Research

1. Xiangnan He
2. Xiang Wang
3. Tat-seng Chua
4. Meng Wang
5. Fuli Feng
6. Le Wu
7. Yongfeng Zhang
8. Kun Zhang

Citations in the corpus

• Self-supervised Graph Learning for Recommendation (2020, background): “Some followon studies [18, 23] enrich the single ID with interaction history for learning better representations.”
• Cross-domain Recommendation Without Sharing User-relevant Data (2019, unknown): “As mentioned above, motivated by item-based CF [13, 17], which encodes the historical interaction behaviors of a user to enrich the user representation, we fuse the transferred item embeddings {q′j |y t u j = 1} into an additional user embedding su .”
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation (2020, background): “t can improve the quality of embedding. For example, SVD++ [25] demonstrates the benefits of user interaction history in predicting user numerical ratings, and Neural Attentive Item Similarity (NAIS) [18] differentiates the importance of items in the interaction history and shows improvements in pre”
• Adversarial Distillation for Efficient Recommendation with External Knowledge (2018, methodology): “So instead of leveraging Vanilla LSTM, we introduce an attention mechanism, which has been verified to be effective in many areas [4, 13, 46].”
• AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks (2018, background): “Attention is first proposed in the context of neural machine translation [2] and has been proved effective in a variety of tasks such as question answering [35], text summarization [30], and recommender systems [14, 33, 43].”
• RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms (2020, background): “(2016) SASRec Kang and McAuley (2018) NARM Li et al.”
• Disentangled Graph Collaborative Filtering (2020, background): “that, later studies like SVD++ [19], FISM [16], NAIS [11], and ACF [3] view personal history of a user as her features, and integrate embeddings of historical items via the average [16, 19] or attention network [3, 11] as user embeddings, showing promise in representation learning.”
• Robust Federated Recommendation System (2020, methodology): “[16] Xiangnan He, Zhankui He, Jingkuan Song, Zhenguang Liu, Yu-Gang Jiang, and Tat-Seng Chua.”
• A Survey on Accuracy-Oriented Neural Recommendation: From Collaborative Filtering to Information-Rich Recommendation (2021, methodology): “To this end, the Neural Attentive Item Similarity model (NAIS) model [25] revises the attention mechanism to be target item-aware:”
• Deep Item-based Collaborative Filtering for Top-N Recommendation (2018, methodology): “To address this limitation, NAIS is proposed very recently [15], which applies a dynamic weighting strategy on second-order item relations.”
• DiffNet++: A Neural Influence and Interest Diffusion Network for Social Recommendation (2020, methodology): “weights for item similarity in item based collaborative filtering [15].”
• An Attentive Survey of Attention Models (2019, methodology): “User 1 seems to have a preference for “cartoon” videos , while user 2 prefers videos on “animals” [He et al., 2018].”