NAIS: Neural Attentive Item Similarity Model for Recommendation

He, Xiangnan; He, Zhankui; Song, Jingkuan; Liu, Zhenguang; Jiang, Yu‐Gang; Chua, Tat-Seng

doi:10.1109/tkde.2018.2831682

Cited by 498 publications

(328 citation statements)

References 41 publications

Supporting

Mentioning

324

Contrasting

Order By: Relevance

“…In this paper, we also propose two novel designs of attention mechanism. Following [7,18], we further explore multi-relational context of given user-URL pair, aiming at discriminating the most important elements towards URL-dependent user preference.…”

Section: Advancements In Recommender Systemmentioning

confidence: 99%

Attributed Multi-Relational Attention Network for Fact-checking URL Recommendation

You

Lee

et al. 2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

To combat fake news, researchers mostly focused on detecting fake news and journalists built and maintained fact-checking sites (e.g., Snopes.com and Politifact.com). However, fake news dissemination has been greatly promoted via social media sites, and these fact-checking sites have not been fully utilized. To overcome these problems and complement existing methods against fake news, in this paper we propose a deep-learning based fact-checking URL recommender system to mitigate impact of fake news in social media sites such as Twitter and Facebook. In particular, our proposed framework consists of a multi-relational attentive module and a heterogeneous graph attention network to learn complex/semantic relationship between user-URL pairs, user-user pairs, and URL-URL pairs. Extensive experiments on a real-world dataset show that our proposed framework outperforms eight state-of-the-art recommendation models, achieving at least 3∼5.3% improvement.

show abstract

Section: Advancements In Recommender Systemmentioning

confidence: 99%

Attributed Multi-Relational Attention Network for Fact-checking URL Recommendation

You

Lee

et al. 2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

show abstract

“…However, existing recommender systems are challenged by the problems of data sparsity and cold start, i.e., most items receive only a few feedbacks (e.g., ratings and clicks) or no feedbacks at all (e.g., for new items). To tackle these problems, the existing approaches usually utilize side information to learn better user/item representations [9,14,16], which then facilitate the learning of user-item interactions, and finally promote the recommendation quality. In many scenarios, knowledge graphs (KGs) can be used to provide general background knowledge as well as rich structural information [11,26,30].…”

Section: Introductionmentioning

confidence: 99%

An end-to-end neighborhood-based interaction model for knowledge-enhanced recommendation

Bai

Zhang

et al. 2019

Proceedings of the 1st International Workshop on Deep Learning Practice for High-Dimensional Sparse Data

View full text Add to dashboard Cite

This paper studies graph-based recommendation, where an interaction graph is constructed built from historical records and is leveraged to alleviate data sparsity and cold start problems. We reveal an early summarization problem in existing graph-based models, and propose Neighborhood Interaction (NI) model to capture each neighbor pair (between user-side and item-side) distinctively. NI model is more expressive and can capture more complicated structural patterns behind user-item interactions. To further enrich node connectivity and utilize high-order structural information, we incorporate extra knowledge graphs (KGs) and adopt graph neural networks (GNNs) in NI, called Knowledge-enhanced Neighborhood Interaction (KNI). Compared with the state-of-the-art recommendation methods, e.g., feature-based, meta path-based, and KG-based models, our KNI achieves superior performance in click-through rate prediction (1.1%-8.4% absolute AUC improvements) and outperforms by a wide margin in top-N recommendation on 4 real world datasets.

show abstract

“…• FISM [20]: This is a state-of-the-art ICF model which characterizes the user with the mean aggregation of the embeddings of his interacted items. • NAIS [16]: This method enhances FISM through a neural attention network. It replaces the mean aggregation of FISM with an attention-based summation.…”

Section: Compared Methodsmentioning

confidence: 99%

“…The idea of ICF is that the user preference on a target item i can be inferred from the similarity of i to all items the user has interacted in the past [16,20,26,31]. Under this case, the relation between items is referred as the collaborative similarity, which measures the co-occurrence in the user interaction history.…”

Section: Related Work 41 Item-based Collaborative Filteringmentioning

confidence: 99%

Relational Collaborative Filtering

Xin

Zhang

et al. 2019

Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval

Self Cite

147

View full text Add to dashboard Cite

Existing item-based collaborative filtering (ICF) methods leverage only the relation of collaborative similarity -i.e., the item similarity evidenced by user interactions like ratings and purchases. Nevertheless, there exist multiple relations between items in real-world scenarios, e.g., two movies share the same director, two products complement with each other, etc. Distinct from the collaborative similarity that implies co-interact patterns from the user's perspective, these relations reveal fine-grained knowledge on items from different perspectives of meta-data, functionality, etc. However, how to incorporate multiple item relations is less explored in recommendation research.In this work, we propose Relational Collaborative Filtering (RCF) to exploit multiple item relations in recommender systems. We find that both the relation type (e.g., shared director) and the relation value (e.g., Steven Spielberg) are crucial in inferring user preference. To this end, we develop a two-level hierarchical attention mechanism to model user preference -the first-level attention discriminates which types of relations are more important, and the second-level attention considers the specific relation values to estimate the contribution of a historical item. To make the item embeddings be reflective of the relational structure between items, we further formulate a task to preserve the item relations, and jointly train it with user preference modeling. Empirical results on two real datasets demonstrate the strong performance of RCF 1 . Furthermore, we also conduct qualitative analyses to show the benefits of explanations brought by RCF's modeling of multiple item relations. CCS CONCEPTS• Information systems → Recommender systems; Retrieval models and ranking; Novelty in information retrieval.

show abstract

NAIS: Neural Attentive Item Similarity Model for Recommendation

Cited by 498 publications

References 41 publications

Attributed Multi-Relational Attention Network for Fact-checking URL Recommendation

Attributed Multi-Relational Attention Network for Fact-checking URL Recommendation

An end-to-end neighborhood-based interaction model for knowledge-enhanced recommendation

Relational Collaborative Filtering

Contact Info

Product

Resources

About