DiffNet++: A Neural Influence and Interest Diffusion Network for Social Recommendation

Wu, Le; Li, Junwei; Sun, Peijie; Hong, Richang; Ge, Yong; Wang, Meng

doi:10.48550/arxiv.2002.00844

Cited by 13 publications

(16 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• DiffNet++ [40]: This is another strong baseline, which adopts GNN and considers both the social influence diffusion and the latent collaborative interests diffusion in social-aware recommendation. The comparison of DICER and the baseline methods are listed in Table 3.…”

Section: Experiments Setupmentioning

confidence: 99%

“…And NGCF [39] proposed a multilayer GNNs which can model the higher-order collaborative signals between users and items during the users and items embedding learning process. As the social relation among users could be naturally formulated as a user-user graph, there are also some works [7,40,41,43] using GNNs to capture social information for recommendation. The Diffnet++ [40] developed a GNN based model to simulate both the social influence and user interest diffusion process.…”

Section: Related Workmentioning

confidence: 99%

“…As the social relation among users could be naturally formulated as a user-user graph, there are also some works [7,40,41,43] using GNNs to capture social information for recommendation. The Diffnet++ [40] developed a GNN based model to simulate both the social influence and user interest diffusion process. And DANSER [43] developed a dual graph attention networks to model the two-fold social effects collaboratively.…”

Section: Related Workmentioning

confidence: 99%

“…The core idea of GNNs is about the propagation and aggregation of information from neighbor nodes [1,4,18], which naturally accord with social recommendations. Several recent works that utilize GNNs for social recommendations [7,40,41,43] have been proposed. For example, the DiffNet++ method [40] developed a GNN based model to simulate both the social influence and user interest diffusion process.…”

Section: Introductionmentioning

confidence: 99%

“…Several recent works that utilize GNNs for social recommendations [7,40,41,43] have been proposed. For example, the DiffNet++ method [40] developed a GNN based model to simulate both the social influence and user interest diffusion process. The DANSER model [43] developed a dual-graph attention network to model the two-fold social effects collaboratively.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Dual Side Deep Context-aware Modulation for Social Recommendation

Zhang

et al. 2021

Proceedings of the Web Conference 2021

View full text Add to dashboard Cite

Social recommendation is effective in improving the recommendation performance by leveraging social relations from online social networking platforms. Social relations among users provide friends' information for modeling users' interest in candidate items and help items expose to potential consumers (i.e., item attraction). However, there are two issues haven't been well-studied: Firstly, for the user interests, existing methods typically aggregate friends' information contextualized on the candidate item only, and this shallow context-aware aggregation makes them suffer from the limited friends' information. Secondly, for the item attraction, if the item's past consumers are the friends of or have a similar consumption habit to the targeted user, the item may be more attractive to the targeted user, but most existing methods neglect the relation enhanced context-aware item attraction.To address the above issues, we proposed DICER (Dual sIde deep Context-awarE modulation for social Recommendation). Specifically, we first proposed a novel graph neural network to model the social relation and collaborative relation, and on top of high-order relations, a dual side deep context-aware modulation is introduced to capture the friends' information and item attraction. Empirical results on two real-world datasets show the effectiveness of the proposed model and further experiments are conducted to help understand how the dual context-aware modulation works.

show abstract

Section: Experiments Setupmentioning

confidence: 99%