Invariant representation learning for sequential recommendation

TL;DR

This paper introduces Irl4Rec, a novel invariant learning framework for sequential recommendation that effectively identifies and mitigates spurious relationships in user-item sequences, improving recommendation accuracy.

Contribution

The paper proposes a new invariant learning-based framework, Irl4Rec, specifically designed to address spurious relations in sequential recommendation models.

Findings

Outperforms three baseline methods in recommendation accuracy

Effectively detects and mitigates spurious relationships

Ablation study confirms the importance of invariant learning in the model

Abstract

Sequential recommendation involves automatically recommending the next item to users based on their historical item sequence. While most prior research employs RNN or transformer methods to glean information from the item sequence-generating probabilities for each user-item pair and recommending the top items, these approaches often overlook the challenge posed by spurious relationships. This paper specifically addresses these spurious relations. We introduce a novel sequential recommendation framework named Irl4Rec. This framework harnesses invariant learning and employs a new objective that factors in the relationship between spurious variables and adjustment variables during model training. This approach aids in identifying spurious relations. Comparative analyses reveal that our framework outperforms three typical methods, underscoring the effectiveness of our model. Moreover, an ablation study further demonstrates the critical role our model plays in detecting spurious relations.