AlignGroup: Learning and Aligning Group Consensus with Member Preferences for Group Recommendation

TL;DR

AlignGroup addresses the group recommendation problem by jointly modeling group consensus and individual member preferences. It introduces a hypergraph neural network to capture intra- and inter-group relations and a self-supervised alignment task to align group consensus with members' common preferences, optimized with a joint LRec and Lalign objective. Empirical results on Mafengwo and CAMRa2011 show state-of-the-art performance for both group and user recommendations, with strong efficiency advantages. The work demonstrates that integrating high-order group signals with alignment-aware learning yields finer-grained and more accurate recommendations for groups and their members.

Abstract

Group activities are important behaviors in human society, providing personalized recommendations for groups is referred to as the group recommendation task. Existing methods can usually be categorized into two strategies to infer group preferences: 1) determining group preferences by aggregating members' personalized preferences, and 2) inferring group consensus by capturing group members' coherent decisions after common compromises. However, the former would suffer from the lack of group-level considerations, and the latter overlooks the fine-grained preferences of individual users. To this end, we propose a novel group recommendation method AlignGroup, which focuses on both group consensus and individual preferences of group members to infer the group decision-making. Specifically, AlignGroup explores group consensus through a well-designed hypergraph neural network that efficiently learns intra- and inter-group relationships. Moreover, AlignGroup innovatively utilizes a self-supervised alignment task to capture fine-grained group decision-making by aligning the group consensus with members' common preferences. Extensive experiments on two real-world datasets validate that our AlignGroup outperforms the state-of-the-art on both the group recommendation task and the user recommendation task, as well as outperforms the efficiency of most baselines.

Figures (9)

• Figure 1: Performance comparison of CubeRec, ConsRec, and our AlignGroup on both group recommendation and user recommendation tasks in terms of Hit Ratio (HR) and Normalized Discounted Cumulative Gain (NDCG) on CAMRa2011.
• Figure 2: AlignGroup overview. We construct a hypergraph neural network for both IntraRL and InterRL to capture group consensus. We further propose a self-supervised alignment task to align group consensus and members' common preferences. Steps (1) and (2) are the group consensus embedding learning and user/item embedding learning components within our hypergraph neural network.
• Figure 3: An illustrative example of the inter-group relations.
• Figure 4: An illustrative example of the user preferences.
• Figure 5: Histograms in dark green show the performance of AlignGroup with both IntraRL and InterRL, and histograms in light green show the performance of AlignGroup w/o InterRL with only IntraRL. The performance metrics are HR@5, HR@10, NDCG@5, and NDCG@10 on both Mafengwo and CAMRa2011 datasets.