A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation

Wu, Le; He, Xiangnan; Wang, Xiang; Zhang, Kun; Wang, Meng

doi:10.1109/tkde.2022.3145690

Cited by 147 publications

(68 citation statements)

References 258 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the early days, accuracy is commonly used to evaluate the quality of recommender systems [45]. In addition to accuracy, diversity and novelty have also been extensively studied since one single metric cannot comprehensively evaluate the performances of recommendations [11,18].…”

Section: Related Workmentioning

confidence: 99%

Investigating Accuracy-Novelty Performance for Graph-based Collaborative Filtering

Zhao,

Wu,

Liang

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Recent years have witnessed the great accuracy performance of graph-based Collaborative Filtering (CF) models for recommender systems. By taking the user-item interaction behavior as a graph, these graph-based CF models borrow the success of Graph Neural Networks (GNN), and iteratively perform neighborhood aggregation to propagate the collaborative signals. While conventional CF models are known for facing the challenges of the popularity bias that favors popular items, one may wonder "Whether the existing graph-based CF models alleviate or exacerbate popularity bias of recommender systems?" To answer this question, we first investigate the two-fold performances w.r.t. accuracy and novelty for existing graph-based CF methods. The empirical results show that symmetric neighborhood aggregation adopted by most existing graph-based CF models exacerbate the popularity bias and this phenomenon becomes more serious as the depth of graph propagation increases. Further, we theoretically analyze the cause of popularity bias for graphbased CF. Then, we propose a simple yet effective plugin, namely 𝑟 -𝐴𝑑 𝑗𝑁𝑜𝑟𝑚, to achieve an accuracy-novelty trade-off by controlling the normalization strength in the neighborhood aggregation process. Meanwhile, 𝑟 -𝐴𝑑 𝑗𝑁𝑜𝑟𝑚 can be smoothly applied to the existing graph-based CF backbones without additional computation. Finally, experimental results on three benchmark datasets show that our proposed method can improve novelty without sacrificing accuracy under various graph-based CF backbones. CCS CONCEPTS• Information systems → Novelty in information retrieval.

show abstract

Section: Related Workmentioning

confidence: 99%

Investigating Accuracy-Novelty Performance for Graph-based Collaborative Filtering

Zhao,

Wu,

Liang

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The research on RS has a long history. Early work on RS is either heuristic-based or factorization-based [26].…”

Section: Related Work a Recommender Systems (Rs)mentioning

confidence: 99%

“…Due to the page limit, we only illustrate recent, representative RS. Readers can refer to related surveys [23], [26] for more related work on RS.…”

Section: Related Work a Recommender Systems (Rs)mentioning

confidence: 99%

Shilling Black-box Recommender Systems by Learning to Generate Fake User Profiles

Lin,

Chen,

Zeng

et al. 2022

Preprint

View full text Add to dashboard Cite

Due to the pivotal role of Recommender Systems (RS) in guiding customers towards the purchase, there is a natural motivation for unscrupulous parties to spoof RS for profits. In this paper, we study Shilling Attack where an adversarial party injects a number of fake user profiles for improper purposes. Conventional Shilling Attack approaches lack attack transferability (i.e., attacks are not effective on some victim RS models) and/or attack invisibility (i.e., injected profiles can be easily detected). To overcome these issues, we present Leg-UP, a novel attack model based on the Generative Adversarial Network. Leg-UP learns user behavior patterns from real users in the sampled "templates" and constructs fake user profiles. To simulate real users, the generator in Leg-UP directly outputs discrete ratings. To enhance attack transferability, the parameters of the generator are optimized by maximizing the attack performance on a surrogate RS model. To improve attack invisibility, Leg-UP adopts a discriminator to guide the generator to generate undetectable fake user profiles. Experiments on benchmarks have shown that Leg-UP exceeds state-of-the-art Shilling Attack methods on a wide range of victim RS models. The source code of our work is available at: https://github.com/XMUDM/ShillingAttack.

show abstract

“…Generally speaking, modern recommender systems usually employ two main components to predict users' preferences: user and item embedding learning, followed by the user-item interaction modeling [7,14,15,46]. Compared to users' rating records, the utilization of the auxiliary textual reviews in review-based recommendation can also be categorized into these two classes: 1) Better user/item representation learning by aggregating user (item) reviews, 2) User-item interaction modeling with each user-item review record.…”

Section: Introductionmentioning

confidence: 99%

A Review-aware Graph Contrastive Learning Framework for Recommendation

Shuai,

Zhang,

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Most modern recommender systems predict users' preferences with two components: user and item embedding learning, followed by the user-item interaction modeling. By utilizing the auxiliary review information accompanied with user ratings, many of the existing review-based recommendation models enriched user/item embedding learning ability with historical reviews or better modeled user-item interactions with the help of available user-item target reviews. Though significant progress has been made, we argue that current solutions for review-based recommendation suffer from two drawbacks. First, as review-based recommendation can be naturally formed as a user-item bipartite graph with edge features from corresponding user-item reviews, how to better exploit this unique graph structure for recommendation? Second, while most current models suffer from limited user behaviors, can we exploit the unique self-supervised signals in the review-aware graph to guide two recommendation components better? To this end, in this paper, we propose a novel Review-aware Graph Contrastive Learning (RGCL) framework for review-based recommendation. Specifically, we first construct a review-aware user-item graph with feature-enhanced edges from reviews, where each edge feature is composed of both the user-item rating and the corresponding review semantics. This graph with feature-enhanced edges can help attentively learn each neighbor node weight for user and item representation learning. After that, we design two additional contrastive learning tasks (i.e., Node Discrimination and Edge Discrimination) to provide self-supervised signals for the two components in recommendation process. Finally, extensive experiments over five benchmark datasets demonstrate the superiority of our proposed RGCL compared to the state-of-the-art baselines.

show abstract

A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation

Cited by 147 publications

References 258 publications

Investigating Accuracy-Novelty Performance for Graph-based Collaborative Filtering

Investigating Accuracy-Novelty Performance for Graph-based Collaborative Filtering

Shilling Black-box Recommender Systems by Learning to Generate Fake User Profiles

A Review-aware Graph Contrastive Learning Framework for Recommendation

Contact Info

Product

Resources

About