SetMIR: Multi-Interest Retrieval as Set Prediction

• URL: http://arxiv.org/abs/2608.30251v1
• Date: Mon, 31 Aug 2026 05:02:02 GMT
• Title: SetMIR: Multi-Interest Retrieval as Set Prediction
• Abstract summary: We propose SetMIR, which treats multi-interest retrieval as a set prediction problem.<n>SetMIR encodes a user's behavior history with a transformer and uses K learnable queries to decode a set of user interests.<n>On Snap's Dynamic Product Ads (DPA) data, SetMIR outperforms four learned multi-interest retrievers on every metric.
• Score: 39.3332626215578
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Embedding-based retrieval is at the core of industrial recommender systems, but a single user embedding is often too limited to capture a user's diverse interests. Multi-interest retrieval addresses this by using multiple user embeddings, yet existing methods still suffer from two issues: interest collapse, where different embeddings learn the same interest, and static dispatch, where serving uses a fixed retrieval budget even when some embeddings are unnecessary. We propose SetMIR, which treats multi-interest retrieval as a set prediction problem. SetMIR encodes a user's behavior history with a transformer and uses K learnable queries to decode a set of user interests, each producing a retrieval embedding and a presence score. During training, Hungarian matching assigns targets to queries one-to-one, so matched queries learn distinct interests and the presence head learns which queries are active. At serving time, SetMIR uses presence scores and query-level Non-Maximum Suppression (NMS) to issue only active, non-redundant ANN queries. On Snap's Dynamic Product Ads (DPA) data, SetMIR outperforms four learned multi-interest retrievers on every metric while issuing 33% fewer ANN queries per request. Deployed as a new retrieval source in the DPA production stack, SetMIR lifts overall CVR by 3.1%, while lifting CTR by 44% and CVR by 51% over the item-to-item retrieval source with the same item embeddings, ANN index, and retrieval quota.

Related papers

• MULTI3IR: A Benchmark for Multi-perspective Multi-domain Multi-modal Information Retrieval [42.63487516145706]
  We introduce Multi$3$IR, a benchmark that evaluates how well retrievers cover the multifaceted perspectives of open-ended queries.<n>It comprises 104.9K Stack Exchange queries, each annotated with perspective descriptions that capture the query's implicit viewpoints.<n>We also propose SPIN, a parameter- and label-efficient method that learns noise vectors to steer embeddings toward diverse yet meaningful semantic directions.
  arXiv  Detail & Related papers  (2026-08-31T15:19:26Z)
• Not All Inputs Are Valid: Towards Open-Set Video Moment Retrieval Using Language [82.18047702848021]
  Video Moment Retrieval (VMR) targets to retrieve the specific moment corresponding to a sentence query from an untrimmed video.<n>To this end, we creatively explore a brand-new VMR setting termed Open-Set Video Moment Retrieval (OS-VMR)<n>In this paper, we make the first attempt to step toward OS-VMR and propose a novel model textOpenVMR, which first distinguishes ID and OOD queries based on the normalizing flow technology.
  arXiv  Detail & Related papers  (2026-05-28T11:57:14Z)
• LITTA: Late-Interaction and Test-Time Alignment for Visually-Grounded Multimodal Retrieval [0.0]
  LITTA is a query-expansion-centric retrieval framework for evidence page retrieval.<n>Given a user query, LITTA generates complementary query variants using a large language model.<n>Candidates from expanded queries are aggregated through reciprocal rank fusion to improve evidence coverage.
  arXiv  Detail & Related papers  (2026-03-10T13:25:39Z)
• Beyond Caption-Based Queries for Video Moment Retrieval [60.31221310786333]
  We investigate degradation of VMR methods when trained on caption-based queries but evaluated on search queries.<n>We introduce three benchmarks by modifying the textual queries in three public VMR datasets.<n>Our approach improves performance on search queries by up to 14.82% mAP_m, and up to 21.83% mAP_m on multi-moment search queries.
  arXiv  Detail & Related papers  (2026-03-02T20:06:41Z)
• Rethinking ANN-based Retrieval: Multifaceted Learnable Index for Large-scale Recommendation System [46.70111672855811]
  MultiFaceted Learnable Index (MFLI) is a scalable, real-time retrieval paradigm that learns multifaceted item embeddings and indices within a unified framework.<n>MFLI improves recall on engagement tasks by up to 11.8%, cold-content delivery by up to 57.29%, and semantic relevance by 13.5% compared with prior state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-02-18T01:31:29Z)
• MultiConIR: Towards multi-condition Information Retrieval [38.864056667809095]
  MultiConIR is a benchmark designed to evaluate retrieval and reranking models under nuanced multi-condition query scenarios.<n>Most retrievers and rerankers exhibit severe performance degradation as query complexity increases.<n>This work delves into the factors contributing to reranker performance deterioration and examines how condition positioning within queries affects similarity assessment.
  arXiv  Detail & Related papers  (2025-03-11T05:02:03Z)
• Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent [92.5712549836791]
  Multimodal Retrieval Augmented Generation (mRAG) plays an important role in mitigating the "hallucination" issue inherent in multimodal large language models (MLLMs)<n>We propose the first self-adaptive planning agent for multimodal retrieval, OmniSearch.
  arXiv  Detail & Related papers  (2024-11-05T09:27:21Z)
• OmniSearchSage: Multi-Task Multi-Entity Embeddings for Pinterest Search [2.917688415599187]
  We present OmniSearchSage, a versatile and scalable system for understanding search queries, pins, and products for Pinterest search. We jointly learn a unified query embedding coupled with pin and product embeddings, leading to an improvement of $>8%$ relevance, $>7%$ engagement, and $>5%$ ads CTR.
  arXiv  Detail & Related papers  (2024-04-25T00:10:25Z)
• Session-Aware Query Auto-completion using Extreme Multi-label Ranking [61.753713147852125]
  We take the novel approach of modeling session-aware query auto-completion as an e Multi-Xtreme Ranking (XMR) problem. We adapt a popular XMR algorithm for this purpose by proposing several modifications to the key steps in the algorithm. Our approach meets the stringent latency requirements for auto-complete systems while leveraging session information in making suggestions.
  arXiv  Detail & Related papers  (2020-12-09T17:56:22Z)

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.