Learning to Drop: Robust Graph Neural Network via Topological Denoising

Luo, Dongsheng; Cheng, Wei; Yu, Wenchao; Zong, Bo; Ni, Jingchao; Chen, Haifeng; Zhang, Xiang

doi:10.1145/3437963.3441734

Cited by 181 publications

(159 citation statements)

References 12 publications

Supporting

Mentioning

131

Contrasting

Order By: Relevance

“…Recently, considerable literature has arisen around the central theme of Graph Structure Learning (GSL), which targets at jointly learning an optimized graph structure and corresponding representations. There are three categories of GSL methods: metric learning [5,22,37], probabilistic modeling [8,25,48], and direct optimization approaches [9,17,42].…”

Section: Deep Graph Structure Learningmentioning

confidence: 99%

Mining Latent Structures for Multimedia Recommendation

Zhang

Zhu

Liu

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

106

View full text Add to dashboard Cite

Multimedia content is of predominance in the modern Web era. Investigating how users interact with multimodal items is a continuing concern within the rapid development of recommender systems. The majority of previous work focuses on modeling useritem interactions with multimodal features included as side information. However, this scheme is not well-designed for multimedia recommendation. Specifically, only collaborative item-item relationships are implicitly modeled through high-order item-user-item relations. Considering that items are associated with rich contents in multiple modalities, we argue that the latent semantic item-item structures underlying these multimodal contents could be beneficial for learning better item representations and further boosting recommendation. To this end, we propose a LATent sTructure mining method for multImodal reCommEndation, which we term LAT-TICE for brevity. To be specific, in the proposed LATTICE model, we devise a novel modality-aware structure learning layer, which learns item-item structures for each modality and aggregates multiple modalities to obtain latent item graphs. Based on the learned latent graphs, we perform graph convolutions to explicitly inject high-order item affinities into item representations. These enriched item representations can then be plugged into existing collaborative filtering methods to make more accurate recommendations. Extensive experiments on three real-world datasets demonstrate the superiority of our method over state-of-the-art multimedia recommendation methods and validate the efficacy of mining latent item-item relationships from multimodal features.

show abstract

Section: Deep Graph Structure Learningmentioning

confidence: 99%

Mining Latent Structures for Multimedia Recommendation

Zhang

Zhu

Liu

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

106

View full text Add to dashboard Cite

show abstract

“…Edge pruning. As for graph-based CF models, the edge pruning method used in [34], [35] provides an alternative way to augment the output embeddings. With the user-item bipartite graph, we randomly prune a certain proportion of edges from the graph in each batch.…”

Section: Historical Embedding Embedding Dropout Edge Pruningmentioning

confidence: 99%

SelfCF: A Simple Framework for Self-supervised Collaborative Filtering

Zhou¹,

Sun²,

Liu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Collaborative filtering (CF) is widely used to learn an informative latent representation of a user or item from observed interactions. Existing CF-based methods commonly adopt negative sampling to discriminate different items. That is, observed user-item pairs are treated as positive instances; unobserved pairs are considered as negative instances and are sampled under a defined distribution for training. Training with negative sampling on large datasets is computationally expensive. Further, negative items should be carefully sampled under the defined distribution, in order to avoid selecting an observed positive item in the training dataset. Unavoidably, some negative items sampled from the training dataset could be positive in the test set. Recently, self-supervised learning (SSL) has emerged as a powerful tool to learn a model without negative samples. In this paper, we propose a self-supervised collaborative filtering framework (SELFCF), that is specially designed for recommender scenario with implicit feedback. The proposed SELFCF framework simplifies the Siamese networks and can be easily applied to existing deep-learning based CF models, which we refer to as backbone networks. The main idea of SELFCF is to augment the output embeddings generated by backbone networks, because it is infeasible to augment raw input of user/item ids. We propose and study three output perturbation techniques that can be applied to different types of backbone networks including both traditional CF models and graph-based models. The framework enables learning informative representations of users and items without negative samples, and is agnostic to the encapsulated backbones. By encapsulating two popular recommendation models into the framework, our experiments on three datasets show that the best performance of our framework is comparable or better than the supervised counterpart. We also show that SELFCF can boost up the performance by up to 8.93% on average, compared with another self-supervised framework as the baseline. Source codes are available at: https://github.com/enoche/SelfCF.

show abstract

“…Performing data denoising in a task-dependent fashion is a promising strategy to alleviate the adverse impact of noisy information. For example, kicking out task-irrelevant edges have been validated to enhance the performance of node classification [13,37]. Very recently, [20] chose to remove the irrelevant historical records for better sequential recommendation.…”

Section: Graph Denoisingmentioning

confidence: 99%

Concept-Aware Denoising Graph Neural Network for Micro-Video Recommendation

Liu

Tian

et al. 2021

Proceedings of the 30th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Recently, micro-video sharing platforms such as Kuaishou and Tiktok have become a major source of information for people's lives. Thanks to the large traffic volume, short video lifespan and streaming fashion of these services, it has become more and more pressing to improve the existing recommender systems to accommodate these challenges in a cost-effective way. In this paper, we propose a novel concept-aware denoising graph neural network (named Conde) for micro-video recommendation. Conde consists of a three-phase graph convolution process to derive user and micro-video representations: warm-up propagation, graph denoising and preference refinement. A heterogeneous tripartite graph is constructed by connecting user nodes with video nodes, and video nodes with associated concept nodes, extracted from captions and comments of the videos. To address the noisy information in the graph, we introduce a user-oriented graph denoising phase to extract a subgraph which can better reflect the user's preference. Despite the main focus of micro-video recommendation in this paper, we also show that our method can be generalized to other types of tasks. Therefore, we also conduct empirical studies on a well-known public E-commerce dataset. The experimental results suggest that the proposed Conde achieves significantly better recommendation performance than the existing state-of-the-art solutions. CCS CONCEPTS• Information systems → Recommender systems.

show abstract

Learning to Drop: Robust Graph Neural Network via Topological Denoising

Cited by 181 publications

References 12 publications

Mining Latent Structures for Multimedia Recommendation

Mining Latent Structures for Multimedia Recommendation

SelfCF: A Simple Framework for Self-supervised Collaborative Filtering

Concept-Aware Denoising Graph Neural Network for Micro-Video Recommendation

Contact Info

Product

Resources

About