MGAT: Multimodal Graph Attention Network for Recommendation

Tao, Zhulin; Wei, Yinwei; Wang, Xiang; He, Xiangnan; Huang, Xianglin; Chua, Tat-Seng

doi:10.1016/j.ipm.2020.102277

Cited by 136 publications

(45 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, Yang et al [16] and Chen et al [17] clustered the users into several groups according to their historical item interactions and separately captured the common preferences of users in each group. Recently, due to the great performance of graph convolutional networks, many approaches have resorted to constructing a graph of users and items according to their historical interactions, and exploring the high-order connectivity from user-item interaction [5], [6], [7], [18], [19]. For example, Wang et al [7] served users and items as nodes and their interaction histories as edges between nodes.…”

Section: Related Workmentioning

confidence: 99%

Dual Preference Distribution Learning for Item Recommendation

Duan¹,

Song²,

Zheng³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Recommender systems can automatically recommend users items that they probably like, for which the goal is to represent the user and item as well as model their interaction. Existing methods have primarily learned the user's preferences and item's features with vectorized representations, and modeled the user-item interaction by the similarity of their representations. In fact, the user's different preferences are related and capturing such relations could better understand the user's preferences for a better recommendation. Toward this end, we propose to represent the user's preference with multi-variant Gaussian distribution, and model the user-item interaction by calculating the probability density at the item in the user's preference distribution. In this manner, the mean vector of the Gaussian distribution is able to capture the center of the user's preferences, while its covariance matrix captures the relations of these preferences. In particular, in this work, we propose a dual preference distribution learning framework (DUPLE), which captures the user's preferences to both the items and attributes by a Gaussian distribution, respectively. As a byproduct, identifying the user's preference to specific attributes enables us to provide the explanation of recommending an item to the user. Extensive quantitative and qualitative experiments on six public datasets show that DUPLE achieves the best performance over all state-of-the-art recommendation methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Dual Preference Distribution Learning for Item Recommendation

Duan¹,

Song²,

Zheng³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Tao et al. (2020) propose MGAT as a new multimodal graph attention network, which represents information propagation within individual graphs, while leveraging the gated attention mechanism to identify varying importance scores of different modalities to user preference. However, to the best of our knowledge, graphs for association rules have not been explored in tourism recommender systems.…”

Section: Related Workmentioning

confidence: 99%

“…In particular, association rule networks have shown potential for personalised recommendation by distinguishing personal interests and preferences by capturing complex interaction patterns in user behaviours. Tao et al (2020) propose MGAT as a new multimodal graph attention network, which represents information propagation within individual graphs, while leveraging the gated attention mechanism to identify varying importance scores of different modalities to user preference. However, to the best of our knowledge, graphs for association rules have not been explored in tourism recommender systems.…”

Section: Rel Ated Workmentioning

confidence: 99%

Building k‐partite association graphs for finding recommendation patterns from questionnaire data

Maduako

Gong

2021

Transactions in GIS

View full text Add to dashboard Cite

show abstract

“…However, these models limit to explore underlying relationships among users and items, since only direct user-item interactions are taken into consideration. More recently, inspired by the success of graph convolutional networks (GCNs) [13,19,21,36], some efforts [30,32,33,38,40] have been made to organize user behaviors as a bipartite user-item graph and integrate multi-hop neighbors into representations. Such GCN-based recommender models benefit from powerful representation ability of GCN and have achieved the state-of-the-art performance.…”

Section: Introductionmentioning

confidence: 99%

Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback

Wei¹,

Wang

Nie³

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

Self Cite

207

201

View full text Add to dashboard Cite

Reorganizing implicit feedback of users as a user-item interaction graph facilitates the applications of graph convolutional networks (GCNs) in recommendation tasks. In the interaction graph, edges between user and item nodes function as the main element of GCNs to perform information propagation and generate informative representations. Nevertheless, an underlying challenge lies in the quality of interaction graph, since observed interactions with lessinterested items occur in implicit feedback (say, a user views micro-videos accidentally). This means that the neighborhoods involved with such false-positive edges will be influenced negatively and the signal on user preference can be severely contaminated. However, existing GCN-based recommender models leave such challenge under-explored, resulting in suboptimal representations and performance.In this work, we focus on adaptively refining the structure of interaction graph to discover and prune potential false-positive edges. Towards this end, we devise a new GCN-based recommender model, Graph-Refined Convolutional Network (GRCN), which adjusts the structure of interaction graph adaptively based on status of model training, instead of remaining the fixed structure. In particular, a graph refining layer is designed to identify the noisy edges with the high confidence of being false-positive interactions, and consequently prune them in a soft manner. We then apply a graph convolutional layer on the refined graph to distill informative signals on user preference. Through extensive experiments on three datasets for micro-video recommendation, we validate the rationality and effectiveness of our GRCN. Further in-depth analysis presents how the refined graph benefits the GCNbased recommender model.

show abstract

MGAT: Multimodal Graph Attention Network for Recommendation

Cited by 136 publications

References 9 publications

Dual Preference Distribution Learning for Item Recommendation

Dual Preference Distribution Learning for Item Recommendation

Building k‐partite association graphs for finding recommendation patterns from questionnaire data

Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback

Contact Info

Product

Resources

About