Integrating Item Relevance in Training Loss for Sequential Recommender Systems
This work addresses noise issues in sequential recommender systems for users and platforms, but it is incremental as it builds on existing methods with specific enhancements.
The paper tackles noise in sequential recommender systems by proposing a new evaluation protocol and a relevance-aware loss function, resulting in improvements of up to ~1.63% in NDCG@10 and ~1.5% in HR compared to best models.
Sequential Recommender Systems (SRSs) are a popular type of recommender system that learns from a user's history to predict the next item they are likely to interact with. However, user interactions can be affected by noise stemming from account sharing, inconsistent preferences, or accidental clicks. To address this issue, we (i) propose a new evaluation protocol that takes multiple future items into account and (ii) introduce a novel relevance-aware loss function to train a SRS with multiple future items to make it more robust to noise. Our relevance-aware models obtain an improvement of ~1.2% of NDCG@10 and 0.88% in the traditional evaluation protocol, while in the new evaluation protocol, the improvement is ~1.63% of NDCG@10 and ~1.5% of HR w.r.t the best performing models.