recommender-systems

Tag

Cards List
#recommender-systems

social media rabbit holes, clusters, and the relative mixing times of random walks

Lobsters Hottest · yesterday Cached

An analysis of Twitter's community structure using domain co-occurrence data and PCA/t-SNE, revealing tight right-wing and diffuse left-wing clusters, with implications for recommender systems and random walk mixing times.

0 favorites 0 likes
#recommender-systems

Generative Optimization for Incentivized Advertising with Global Level Constraints

arXiv cs.LG · 2d ago Cached

This paper proposes GOAL, a constraint-aware generative framework for incentivized advertising that formulates incentive allocation as conditional sequence generation, and introduces SCPO to learn a single generative policy that generalizes across ROI constraints. Experiments show improved long-term revenue and user retention with reduced ROI violations.

0 favorites 0 likes
#recommender-systems

A/B Agent: A Self-Evolving Agent for Strategy Iteration in Industrial A/B Testing

arXiv cs.AI · 2d ago Cached

This paper proposes A/B Agent, a closed-loop agent framework that organizes historical A/B testing knowledge into a hierarchical experience tree, retrieves transferable strategies via multi-path Tree-RAG, and self-evolves through online experiment feedback, achieving a 4.829% GMV improvement in a short-video e-commerce recommendation system.

0 favorites 0 likes
#recommender-systems

RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems

Hugging Face Daily Papers · 2026-07-31 Cached

RecHarness is a bandit-routed agentic harness that automates recommender model optimization by separating direction selection from hypothesis generation, achieving stable improvements and significant gains in an online A/B test.

0 favorites 0 likes
#recommender-systems

Understanding Semantic IDs: From Item Representation to Item Selection in Generative Recommendation

arXiv cs.AI · 2026-07-29 Cached

This paper systematically investigates Semantic IDs (SIDs) in generative recommendation, finding that while SIDs preserve coarse item organization, they lose fine local structure from the encoder. The authors propose Item-Supported Decoding (ISD), a lightweight inference-time method that improves NDCG@10 by up to 31.2% without additional parameters or retraining.

0 favorites 0 likes
#recommender-systems

Proximity Features: Privacy-Compliant Cold-Start Personalization at Airbnb

arXiv cs.LG · 2026-07-15 Cached

This paper introduces Proximity Features, a privacy-compliant system that uses aggregated geo-IP data to personalize recommendations for cold-start users at Airbnb, achieving significant booking lifts in production experiments.

0 favorites 0 likes
#recommender-systems

RouteRec: Strict Evaluation of Recommender-Agent Selection and Aggregation

arXiv cs.CL · 2026-07-14 Cached

RouteRec is a framework for evaluating request-level hard selection versus item-level learned aggregation of heterogeneous recommender agents, including an LLM reranker, under cost constraints. Experiments on MovieLens-1M show that item-level aggregation significantly outperforms request-level selection.

0 favorites 0 likes
#recommender-systems

Mitigating Early Training Collapse in CTR Models

arXiv cs.LG · 2026-07-14 Cached

This paper analyzes the early training collapse phenomenon in deep neural models for click-through rate prediction and proposes mitigation strategies such as sparse feature removal and value filtering, demonstrating improvements on large-scale industrial datasets.

0 favorites 0 likes
#recommender-systems

Beyond expert users: agents should help users construct preferences, not just elicit them

arXiv cs.AI · 2026-07-01 Cached

This paper argues that agents should help users construct preferences rather than assuming well-formed ones, proposing the CoPref model and CoShop benchmark. Evaluations show even frontier models achieve only 56% accuracy due to poor preference expansion.

0 favorites 0 likes
#recommender-systems

Breaking the Filter Bubble: A Semantic Pareto-DQN Framework for Multi-Objective Recommendation

arXiv cs.AI · 2026-06-24 Cached

Proposes a multi-objective reinforcement learning framework combining semantic embeddings with Pareto-DQN to balance engagement, diversity, and fairness in recommendations, mitigating filter bubbles.

0 favorites 0 likes
#recommender-systems

OneRank: Unified Transformer-Native Ranking Architecture for Multi-Task Recommendation

Hugging Face Daily Papers · 2026-06-15 Cached

OneRank proposes a Transformer-native multi-task ranking framework that integrates feature encoding and prediction to reduce inter-task interference and improve ranking performance in recommender systems.

0 favorites 0 likes
#recommender-systems

Trading Engagement for Sustainability: Carbon-Aware Re-ranking for E-commerce Recommendations

arXiv cs.AI · 2026-06-08 Cached

This paper proposes a carbon-aware re-ranking strategy for e-commerce recommendations, using a retrieval-augmented pipeline to estimate product carbon footprints and trading off predicted engagement against sustainability. Evaluated on Amazon Reviews data, substantial carbon reductions are achievable with minimal engagement loss.

0 favorites 0 likes
#recommender-systems

τ-Rec: A Verifiable Benchmark for Agentic Recommender Systems

Hugging Face Daily Papers · 2026-06-08 Cached

τ-Rec is a verifiable benchmark for agentic recommender systems that replaces subjective LLM-as-a-judge evaluations with verifiable rewards and controlled dialogue constraints, revealing steep reliability cliffs across leading models where even the best achieves only ~57% pass@1.

0 favorites 0 likes
#recommender-systems

Expand More, Shrink Less: Shaping Effective-Rank Dynamics for Dense Scaling in Recommendation

arXiv cs.LG · 2026-05-25 Cached

This paper proposes RankElastor, a novel architecture that mitigates embedding collapse in dense scaling of recommendation models by introducing parameterized full mixing and GLU-improved P-FFNs, achieving robust scaling and improved performance on large-scale datasets.

0 favorites 0 likes
#recommender-systems

PEARL: Unbiased Percentile Estimation via Contrastive Learning for Industrial-Scale Livestream Recommendation

arXiv cs.LG · 2026-05-22 Cached

PEARL introduces a contrastive percentile approximation framework to mitigate behavioral intensity imbalance in recommender systems, achieving significant gains in engagement metrics in a production livestream platform serving billions of users.

0 favorites 0 likes
← Back to home

Submit Feedback