Neural Graph Collaborative Filtering

By Xiang Wang, Xiangnan He, Meng Wang, Fuli Feng, Tat-seng Chua. Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2019

3,905 citations recorded by the source corpus.

Learning vector representations (aka. embeddings) of users and items lies at the core of modern recommender systems. Ranging from early matrix factorization to recently emerged deep learning based methods, existing efforts typically obtain a user's (or an item's) embedding by mapping from pre-existing features that describe the user (or the item), such as ID and attributes. We argue that an inherent drawback of such methods is that, the collaborative signal, which is latent in user-item interactions, is not encoded in the embedding process. As such, the resultant embeddings may not be sufficient to capture the collaborative filtering effect. In this work, we propose to integrate the user-item interactions - more specifically the bipartite graph structure - into the embedding process. We develop a new recommendation framework Neural Graph Collaborative Filtering (NGCF), which exploits the user-item graph structure by propagating embeddings on it. This leads to the expressive modeling of high-order connectivity in user-item graph, effectively injecting the collaborative signal into the embedding process in an explicit manner. We conduct extensive experiments on three public benchmarks, demonstrating significant improvements over several state-of-the-art models like HOP-Rec [39] and Collaborative Memory Network [5]. Further analysis verifies the importance of embedding propagation for learning better user and item representations, justifying the rationality and effectiveness of NGCF. Codes are available at https://github.com/xiangwang1223/neural_graph_collaborative_filtering.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Systems

View Paper: https://www.semanticscholar.org/paper/c5f5f179d80a3bf9b4f29750283a87eaca42e91b

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

In Computer Vision and Pattern Recognition

In Information Systems

Citations in the corpus

Sequential Recommendation with Graph Neural Networks (2021, background): “[29] further proposed the general solution for implicit recommendation task.”
A Survey on Accuracy-Oriented Neural Recommendation: From Collaborative Filtering to Information-Rich Recommendation (2021, background): “Thus, a natural extension is to mine the [20], PMLAM [21], pQCF [22], FAWMF [23] User Interacted items+UID (Free Embed+Heuristic Agg) Item IID (Free Embed) SVD++ [24] User Interacted items (Free Embed+Heuristic Agg) Item IID (Free Embed) NAIS [25] User Interacted items+UID (Free Embed+Heuristic Agg)”
Communication-efficient federated learning via knowledge distillation (2021, neutral): “T he boom of deep learning in recent years has greatly bene ﬁ ted humans in various ﬁ elds such as intelligent healthcare 1 and personalized web applications 2 .”
HGNN+: General Hypergraph Neural Networks (2022, methodology): “For collaborative filtering task, in [19] Wang et al.”
Denoising Implicit Feedback for Recommendation (2020, methodology): “The users and items with extremely sparse interactions are removed to ensure the data quality based on the experience of former work [20, 31].”
RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms (2020, neutral): “NGCF [72] SIGIR 2019 Gowalla, Yelp, Amazon”
Mining Latent Structures for Multimedia Recommendation (2021, methodology): “Inspired by the recent surge of graph neural networks [16, 21, 35], Wang et al. [36] propose to model user-item relationships as bipartite graphs and inject high-order interactions into the embedding process to learn better representations.”
XSimGCL: Towards Extremely Simple Graph Contrastive Learning for Recommendation (2022, background): “Among numerous variants of GNNs, GCN [39] is the most prevalent one and drives many state-of-the-art graph neural recommendation models such as NGCF [54], LightGCN [28], LR-GCCF [55] and LCF [56].”
Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning (2022, methodology): “In general, GNN-based collaborative filtering methods [9, 31, 32] produce informative representations for users and items based on the aggregation scheme, which can be formulated to two stages:”
Graph Neural Networks for Recommender System (2022, methodology): “The development of recommender systems generally includes three stages, shallow models [16, 18], neural network (NN) -based models [9, 11, 13], and GNN-based models [2, 7, 12, 21].”
When large language models meet personalization: perspectives of challenges and opportunities (2023, positive): “Deep learning-based methods offer approaches to capture high-order interactions by employing techniques like attention mechanisms [17], [18] and graph based networks [19] to mining complex relationships between user and item.”
Representation Learning with Large Language Models for Recommendation (2023, methodology): “Following the similar settings in [35, 42, 44] for data preprocessing, we filter out interactions with ratings below 2 for the Amazon-book and below 3 for the Yelp.”
Causal Intervention for Leveraging Popularity Bias in Recommendation (2021, methodology): “Following previous work [42], we take 10-core filtering to make sure that each user and each item have at least 10 interacted records.”
Interest-aware Message-Passing GCN for Recommendation (2021, methodology): “Because the main focus of this work is to study the effects of distinguishing user interests in the graph convolution in the GCN-based recommendation model, we adopt the inner product as previous work [2, 33, 42] for fair comparisons in the empirical studies.”
Disentangled Graph Collaborative Filtering (2020, methodology): “We then apply an graph disentangling module equipped with neighbor routing [25, 29] and embedding propagation [9, 18, 39, 40] mechanisms.”
MMGCN: Multi-modal Graph Convolution Network for Personalized Recommendation of Micro-video (2019, methodology): “Intuitively, the historical behaviors of users reflect personal interests; meanwhile, the user groups can also profile items [38, 41].”
Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach (2020, methodology): “Some of recent works on GCN based recommendation models focused on the spatial domain (Wu, Liu, and Yang 2018; Wang et al. 2019; Berg, Kipf, and Welling 2018; Ying et al. 2018).”
Heterogeneous Graph Structure Learning for Graph Neural Networks (2021, methodology): “…graph data, has drawn increasing attention and is widely applied to node classiﬁcation (Kipf and Welling 2017; Velickovic et al. 2018; Xu et al. 2019), graph classiﬁcation (Duvenaud et al. 2015; Lee, Lee, and Kang 2019), and recommendation (Ying et al. 2018; Fan et al. 2019b; Wang et al. 2019a).”