{"ID":2895498,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.09403","arxiv_id":"2507.09403","title":"Balancing Semantic Relevance and Engagement in Related Video Recommendations","abstract":"Related video recommendations commonly use collaborative filtering (CF) driven by co-engagement signals, often resulting in recommendations lacking semantic coherence and exhibiting strong popularity bias. This paper introduces a novel multi-objective retrieval framework, enhancing standard two-tower models to explicitly balance semantic relevance and user engagement. Our approach uniquely combines: (a) multi-task learning (MTL) to jointly optimize co-engagement and semantic relevance, explicitly prioritizing topical coherence; (b) fusion of multimodal content features (textual and visual embeddings) for richer semantic understanding; and (c) off-policy correction (OPC) via inverse propensity weighting to effectively mitigate popularity bias. Evaluation on industrial-scale data and a two-week live A/B test reveals our framework's efficacy. We observed significant improvements in semantic relevance (from 51% to 63% topic match rate), a reduction in popular item distribution (-13.8% popular video recommendations), and a +0.04% improvement in our topline user engagement metric. Our method successfully achieves better semantic coherence, balanced engagement, and practical scalability for real-world deployment.","short_abstract":"Related video recommendations commonly use collaborative filtering (CF) driven by co-engagement signals, often resulting in recommendations lacking semantic coherence and exhibiting strong popularity bias. This paper introduces a novel multi-objective retrieval framework, enhancing standard two-tower models to explicit...","url_abs":"https://arxiv.org/abs/2507.09403","url_pdf":"https://arxiv.org/pdf/2507.09403v1","authors":"[\"Amit Jaspal\",\"Feng Zhang\",\"Wei Chang\",\"Sumit Kumar\",\"Yubo Wang\",\"Roni Mittleman\",\"Qifan Wang\",\"Weize Mao\"]","published":"2025-07-12T21:04:25Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.MM\"]","methods":"[]","has_code":false}