General Item Representation Learning for Cold-start Content Recommendations
It addresses the challenge of recommending new items with limited interaction data for users in recommendation systems, though it appears incremental as it builds on existing content-based approaches.
The paper tackles the cold-start item recommendation problem by proposing a domain-agnostic item representation learning framework that uses multimodal alignment without classification labels, achieving better preservation of fine-grained user taste than state-of-the-art baselines in experiments on movie and news benchmarks.
Cold-start item recommendation is a long-standing challenge in recommendation systems. A common remedy is to use a content-based approach, but rich information from raw contents in various forms has not been fully utilized. In this paper, we propose a domain/data-agnostic item representation learning framework for cold-start recommendations, naturally equipped with multimodal alignment among various features by adopting a Transformer-based architecture. Our proposed model is end-to-end trainable completely free from classification labels, not just costly to collect but suboptimal for recommendation-purpose representation learning. From extensive experiments on real-world movie and news recommendation benchmarks, we verify that our approach better preserves fine-grained user taste than state-of-the-art baselines, universally applicable to multiple domains at large scale.