Denoising Multi-Interest-Aware Logical Reasoning for Long-Sequence Recommendation

Fei Li, Qingyun Gao, Yizhou Dang, Enneng Yang, Guibing Guo, Jianzhe Zhao, Xingwei Wang

Abstract: Logical reasoning-based recommendation methods employ logical rules to mitigate the adverse effects of noise items in short interaction sequences on recommendation accuracy. However, there are two problems with existing methods: 1) As the length of the interaction sequence increases, introducing more noise items exacerbates the negative impact on logical reasoning, thereby reducing the accuracy of these methods. 2) They are often dominated by the user's single primary interest, which prevents simultaneous consideration of users' multiple-aspect interests in long sequences. To address these issues, we propose a novel dEnoising Multi-Interest-aware Logical rEasoning (EMILE) method for long-sequence recommendation. Specifically, we design a logical rule-based interest extractor that enhances the importance of preferred items in constructing user interests while minimizing the negative impact of disliked items. This extractor effectively mitigates the adverse effects of noise items in long interaction sequences. Furthermore, we propose a novel multi-interest learning strategy that optimizes two new objective functions-interest probability distribution contrastive loss and interest logical reasoning contrastive loss-to ensure the model simultaneously considers multiple-aspect interests. These two objective functions require that the target item is more closely aligned with multiple interests than the single primary interest, both in the probability distribution space and during logical reasoning. Experimental results on four public datasets demonstrate that our method significantly outperforms all compared baselines regarding recommendation accuracy. Code is available at https://github.com/muzi1998/Denoising-Multi-Interest-Aware-Logical-Reasoning.

External IDs:doi:10.1145/3726302.3729944