Personalizing Incremental Video Search with Hybrid Text and ID Embeddings

• URL: http://arxiv.org/abs/2607.13493v1
• Date: Wed, 15 Jul 2026 06:42:50 GMT
• Title: Personalizing Incremental Video Search with Hybrid Text and ID Embeddings
• Abstract summary: We present a personalization system for Apple TV search that combines complementary semantic and collaborative signals at ranking time.<n>Our approach learns two item embedding spaces: (i) a text-based multilingual encoder (TextEmb) fine-tuned on co-engagement triplets via contrastive learning, and (ii) an ID-based collaborative embedding model (IdEmb) trained on interaction-derived positives.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Incremental video search requires high-quality ranking after each keystroke, where intent is often underspecified (e.g., 1-3 character prefixes). We present a personalization system for Apple TV search that combines complementary semantic and collaborative signals at ranking time. Our approach learns two item embedding spaces: (i) a text-based multilingual encoder (TextEmb) fine-tuned on co-engagement triplets via contrastive learning, and (ii) an ID-based collaborative embedding model (IdEmb) trained on interaction-derived positives. At serving time, we construct user representations from recent watch history and inject text- and ID-based user-item cosine similarities into a pairwise XGBoost ranker. We evaluate with temporally held-out offline datasets and a three-week online controlled experiment. Offline, for sessions with user history, the personalized ranker improves NDCG@10 by 2.99% and MRR by 3.30% over the non-personalized baseline. Slice analyses show that personalization is most needed in incremental search, where intent is still forming: on ambiguous prefix queries (1-3 characters), NDCG@10 lift is +8.63%, versus +1.46% on longer, fully specified queries. Longer-history users benefit more: NDCG lift rises from +2.13% for users with 1-5 history items to +4.37% for users with 51-100, even though baseline relevance is lower for these cohorts (NDCG@10 drops from 0.733 to 0.680), indicating that personalization adds the most value where default ranking underperforms. Online, treatment yields statistically significant gains of +1.14% tap-through rate and +1.23% conversion rate, with a 2.91% improvement in converted-item rank position. We further analyze coverage-precision trade-offs between semantic and collaborative embeddings via ablations isolating each signal, and evaluate embedding quality on a held-out corpus with LLM-judged similarity labels to reduce click/exposure bias.

Related papers

• An Embarrassingly Simple Graph Heuristic Reveals Shortcut-Solvable Benchmarks for Sequential Recommendation [50.09718257952108]
  Sequentialsolv has increasingly shifted toward generative recommenders that combine sequential patterns with semantic item information.<n>These methods are often evaluated on a small set of widely used benchmarks, raising a key question: do these benchmarks actually require the advanced modeling capabilities that modern generative recommenders claim to provide?<n>We conduct a benchmark audit with an intentionally simple graph. Starting from only the last one or two items, it retrieves candidates from a few-hop item-transition graph and ranks them by item-feature similarity.
  arXiv  Detail & Related papers  (2026-05-08T02:00:11Z)
• Putting HUMANS first: Efficient LAM Evaluation with Human Preference Alignment [53.72927532626824]
  We show that subsets of just 50 examples (0.3% of data) can achieve over 0.93 Pearson correlation with full benchmark scores.<n>To better predict preferences, we trained regression models on these selected subsets, achieving 0.98 correlation.<n>This demonstrates that in regression modeling, well-curated subsets outpredict the full benchmark, showing quality over quantity.
  arXiv  Detail & Related papers  (2026-04-20T00:57:31Z)
• GAAMA: Graph Augmented Associative Memory for Agents [0.0]
  GAAMA is a graph-augmented associative memory system that constructs a concept-mediated hierarchical knowledge graph.<n>On the LoCoMo-10 benchmark (1,540 questions across 10 multi-session conversations), GAAMA achieves 78.9% mean reward, outperforming a tuned RAG baseline.
  arXiv  Detail & Related papers  (2026-03-29T23:33:38Z)
• PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory [56.81126490418336]
  Personalization is one of the next milestones in advancing AI capability and alignment.<n> PersonaMem-v2 simulates 1,000 realistic user-chatbot interactions on 300+ scenarios, 20,000+ user preferences, and 128k-token context windows.<n>We train Qwen3-4B to outperforms GPT-5, reaching 53% accuracy in implicit personalization.
  arXiv  Detail & Related papers  (2025-12-07T06:48:23Z)
• Robust Relevance Feedback for Interactive Known-Item Video Search [30.382002857815497]
  We introduce a pairwise relative judgment feedback that improves the stability of top-k selections.<n>We decompose user perception into multiple sub-perceptions, each represented as an independent embedding space.<n>We develop a predictive user model that estimates the combination of sub-perceptions based on each user feedback instance.
  arXiv  Detail & Related papers  (2025-05-21T05:31:49Z)
• Mind the Gap! Static and Interactive Evaluations of Large Audio Models [55.87220295533817]
  Large Audio Models (LAMs) are designed to power voice-native experiences.<n>This study introduces an interactive approach to evaluate LAMs and collect 7,500 LAM interactions from 484 participants.
  arXiv  Detail & Related papers  (2025-02-21T20:29:02Z)
• Aligning LLMs with Individual Preferences via Interaction [51.72200436159636]
  We train large language models (LLMs) that can ''interact to align''<n>We develop a multi-turn preference dataset containing 3K+ multi-turn conversations in tree structures.<n>For evaluation, we establish the ALOE benchmark, consisting of 100 carefully selected examples and well-designed metrics to measure the customized alignment performance during conversations.
  arXiv  Detail & Related papers  (2024-10-04T17:48:29Z)
• Generalized Contrastive Learning for Multi-Modal Retrieval and Ranking [2.5238707656136694]
  Generalized Contrastive Learning (GCL) is a training framework designed to learn from continuous ranking scores beyond binary relevance.<n>GCL encodes both relevance and ranking information into a unified embedding space by applying ranking scores to the loss function.
  arXiv  Detail & Related papers  (2024-04-12T15:30:03Z)
• Temporal Interest Network for User Response Prediction [33.95334897033641]
  We propose a Temporal Interest Network (TIN) to capture the semantic-temporal correlation simultaneously between behaviors and the target. TIN has been successfully deployed in production since October 2023, serving the WeChat Moments traffic.
  arXiv  Detail & Related papers  (2023-08-15T05:48:44Z)
• Using Multi-Encoder Fusion Strategies to Improve Personalized Response Selection [2.8360662552057323]
  We propose a suite of fusion strategies that capture the interaction between persona, emotion, and entailment information of utterances. We train a BERT-based model which outperforms the previous methods by margins larger than 2.3 % on original personas and 1.9 % on revised personas.
  arXiv  Detail & Related papers  (2022-08-20T04:13:27Z)
• Adversarial Retriever-Ranker for dense text retrieval [51.87158529880056]
  We present Adversarial Retriever-Ranker (AR2), which consists of a dual-encoder retriever plus a cross-encoder ranker. AR2 consistently and significantly outperforms existing dense retriever methods. This includes the improvements on Natural Questions R@5 to 77.9%(+2.1%), TriviaQA R@5 to 78.2%(+1.4), and MS-MARCO MRR@10 to 39.5%(+1.3%)
  arXiv  Detail & Related papers  (2021-10-07T16:41:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.