DIFF: Dual Side-Information Filtering and Fusion for Sequential Recommendation

TL;DR

The paper introduces DIFF, a novel sequential recommendation model that uses frequency-based noise filtering and dual multi-sequence fusion to improve recommendation accuracy, especially in sparse and cold-start scenarios.

Contribution

DIFF is the first to combine frequency domain filtering with dual multi-sequence fusion for enhanced side-information integration in sequential recommendation.

Findings

DIFF outperforms state-of-the-art models by up to 14.1% in Recall@20.

DIFF achieves up to 12.5% improvement in NDCG@20.

The model is more robust in capturing complex item correlations.

Abstract

Side-information Integrated Sequential Recommendation (SISR) benefits from auxiliary item information to infer hidden user preferences, which is particularly effective for sparse interactions and cold-start scenarios. However, existing studies face two main challenges. (i) They fail to remove noisy signals in item sequence and (ii) they underutilize the potential of side-information integration. To tackle these issues, we propose a novel SISR model, Dual Side-Information Filtering and Fusion (DIFF), which employs frequency-based noise filtering and dual multi-sequence fusion. Specifically, we convert the item sequence to the frequency domain to filter out noisy short-term fluctuations in user interests. We then combine early and intermediate fusion to capture diverse relationships across item IDs and attributes. Thanks to our innovative filtering and fusion strategy, DIFF is more robust in learning subtle and complex item correlations in the sequence. DIFF outperforms state-of-the-art SISR models, achieving improvements of up to 14.1% and 12.5% in Recall@20 and NDCG@20 across four benchmark datasets.