Multi-view Intent Disentangle Graph Networks for Bundle Recommendation

TL;DR

This paper introduces MIDGN, a novel graph network model that effectively disentangles user intents from global and local views in bundle recommendation, improving accuracy by over 10% and 26%.

Contribution

MIDGN is the first to simultaneously disentangle user intents from global and local perspectives in bundle recommendation, enhancing interpretability and performance.

Findings

MIDGN outperforms state-of-the-art methods by over 10.7% and 26.8%.

Disentangling intents from multiple views improves recommendation accuracy.

Contrast learning enhances intent representation quality.

Abstract

Bundle recommendation aims to recommend the user a bundle of items as a whole. Nevertheless, they usually neglect the diversity of the user's intents on adopting items and fail to disentangle the user's intents in representations. In the real scenario of bundle recommendation, a user's intent may be naturally distributed in the different bundles of that user (Global view), while a bundle may contain multiple intents of a user (Local view). Each view has its advantages for intent disentangling: 1) From the global view, more items are involved to present each intent, which can demonstrate the user's preference under each intent more clearly. 2) From the local view, it can reveal the association among items under each intent since items within the same bundle are highly correlated to each other. To this end, we propose a novel model named Multi-view Intent Disentangle Graph Networks (MIDGN), which is capable of precisely and comprehensively capturing the diversity of the user's intent and items' associations at the finer granularity. Specifically, MIDGN disentangles the user's intents from two different perspectives, respectively: 1) In the global level, MIDGN disentangles the user's intent coupled with inter-bundle items; 2) In the Local level, MIDGN disentangles the user's intent coupled with items within each bundle. Meanwhile, we compare the user's intents disentangled from different views under the contrast learning framework to improve the learned intents. Extensive experiments conducted on two benchmark datasets demonstrate that MIDGN outperforms the state-of-the-art methods by over 10.7% and 26.8%, respectively.