M2TRec: Metadata-aware Multi-task Transformer for Large-scale and Cold-start free Session-based Recommendations

TL;DR

M2TRec is a metadata-aware multi-task transformer that improves session-based recommendations, especially for cold-start and sparse items, by learning item representations from metadata rather than individual embeddings.

Contribution

The paper introduces M2TRec, a novel item-ID free model that leverages item metadata and multi-task learning to enhance scalability and performance in large-scale, sparse, and cold-start scenarios.

Findings

Significant performance improvements on sparse items.

Effective handling of cold-start and unpopular items.

Faster convergence due to multi-task training.

Abstract

Session-based recommender systems (SBRSs) have shown superior performance over conventional methods. However, they show limited scalability on large-scale industrial datasets since most models learn one embedding per item. This leads to a large memory requirement (of storing one vector per item) and poor performance on sparse sessions with cold-start or unpopular items. Using one public and one large industrial dataset, we experimentally show that state-of-the-art SBRSs have low performance on sparse sessions with sparse items. We propose M2TRec, a Metadata-aware Multi-task Transformer model for session-based recommendations. Our proposed method learns a transformation function from item metadata to embeddings, and is thus, item-ID free (i.e., does not need to learn one embedding per item). It integrates item metadata to learn shared representations of diverse item attributes. During inference, new or unpopular items will be assigned identical representations for the attributes they share with items previously observed during training, and thus will have similar representations with those items, enabling recommendations of even cold-start and sparse items. Additionally, M2TRec is trained in a multi-task setting to predict the next item in the session along with its primary category and subcategories. Our multi-task strategy makes the model converge faster and significantly improves the overall performance. Experimental results show significant performance gains using our proposed approach on sparse items on the two datasets.