Hierarchical Multi-Task Learning Framework for Session-based Recommendations

TL;DR

This paper introduces HierSRec, a hierarchical multi-task learning framework for session-based recommender systems that improves prediction accuracy and interpretability by leveraging auxiliary category prediction tasks.

Contribution

HierSRec is the first to incorporate hierarchical multi-task learning into session-based recommender systems, enhancing accuracy and interpretability.

Findings

HierSRec outperforms existing SBRSs in next-item prediction accuracy.

The candidate generation scheme effectively reduces the item set without sacrificing accuracy.

HierSRec's accuracy with candidate items closely matches that with all items.

Abstract

While session-based recommender systems (SBRSs) have shown superior recommendation performance, multi-task learning (MTL) has been adopted by SBRSs to enhance their prediction accuracy and generalizability further. Hierarchical MTL (H-MTL) sets a hierarchical structure between prediction tasks and feeds outputs from auxiliary tasks to main tasks. This hierarchy leads to richer input features for main tasks and higher interpretability of predictions, compared to existing MTL frameworks. However, the H-MTL framework has not been investigated in SBRSs yet. In this paper, we propose HierSRec which incorporates the H-MTL architecture into SBRSs. HierSRec encodes a given session with a metadata-aware Transformer and performs next-category prediction (i.e., auxiliary task) with the session encoding. Next, HierSRec conducts next-item prediction (i.e., main task) with the category prediction result and session encoding. For scalable inference, HierSRec creates a compact set of candidate items (e.g., 4% of total items) per test example using the category prediction. Experiments show that HierSRec outperforms existing SBRSs as per next-item prediction accuracy on two session-based recommendation datasets. The accuracy of HierSRec measured with the carefully-curated candidate items aligns with the accuracy of HierSRec calculated with all items, which validates the usefulness of our candidate generation scheme via H-MTL.