Cold-Start Recommendation

Follow this topic Ask about this topic

Cold-start recommendation studies how to personalize when a new user or item has few or no interactions, a problem that can leave people poorly served and new content undiscovered. Common approaches use text, images, metadata, or language-model features, align them with collaborative-filtering embeddings, and transfer signals across users, items, cohorts, or product domains; graph, generative, and bandit methods offer other ways to infer relevance or learn online. Evaluation increasingly distinguishes strict temporal cold-start tests and retrieval coverage from reranking quality, alongside online measures of engagement and business outcomes. A central tension is that semantic signals can help when behavioral data is sparse but may not match collaborative preferences, while gains for cold items can come at a cost to warm-item accuracy, scalability, or privacy.

Latest papers

27 papers2 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Bridging the Topological Divide: Dual-Branch Graph Distillation with Semantic Priors for Robust Cold-Start Recommendation
Oct 14, 2026Yuanfeng QiuCold-Start Recommendation Collaborative Filtering
The Hong Kong University of Science and Technology (Guangzhou)
Challenges and Solutions for Bandits in the Wild: Warm-Started Mixture Bandits for Cross-Cohort Slate Recommendation
Sep 29, 2026Serafima Lebedeva, Sumantrak Mukherjee, Ali Arshad Sadal +8Multi-Armed Bandits Cold-Start Recommendation
German Research Center for Artificial Intelligence (DFKI), Kaiserslautern · RPTU, Kaiserslautern-Landau · LMU, Munich
Recovering Expert Critic-Sourced Network Adjacency between Musical Artists from Acoustic Distributions: A Construct-Validity Approach
Aug 27, 2026Elena Badillo-Goicoechea, Fengfeng HeCold-Start Recommendation Link Prediction
University of Chicago Chicago, Illinois, USA
Keeping the Index Open: The Recommendation-Side Cost of Shared Search and Recommendation
Aug 25, 2026Theodore Rogers, Joe Standerfer, Dmitrii Timoshenko +3Recommender Systems Cold-Start Recommendation
Amazon Web Services United States
DraftFM: A FoundationModel for Day-Zero Drafting in Magic: The Gathering
Aug 20, 2026Brian WardGame-Playing Agents Cold-Start Recommendation
Independent Researcher
POI Recommendation with LLM-Augmented Multi-Graph Learning and Contrastive Alignment
Aug 17, 2026Burak Tamer, Wolfram Höpken, Zehui Wang +1Recommender Systems Multimodal Graph Learning
Institute for Digital Transformation - University of Applied Sciences Ravensburg-Weingarten, Germany
LLM-Derived Priors for Thompson Sampling in Cold-Start Comment Recommendation
Aug 4, 2026Eugene Lee, Oseong Choi, Byungsoo Kang +1Thompson Sampling Cold-Start Recommendation
NAVER WEBTOON South Korea
Kairos: Numerically Robust News Recommendation under Item Cold-Start via Cholesky-based LinUCB
Jul 29, 2026Finn HertschCold-Start Recommendation Recommender Systems
DHBW Ravensburg, School of Business, Data Science and AI, Marienplatz 2, 88212 Ravensburg, Germany
PinEqualizer: Full Funnel Content Exploration and Debiasing System at Pinterest
Jul 24, 2026Olafur Gudmundsson, Bo Zhao, Huayi Liao +15Cold-Start Recommendation Information Retrieval
Pinterest, Inc. San Francisco, USA
Can Generative Recommendation Reach Cold Items? A Temporal Perspective on Semantic-ID Generation
Jul 23, 2026Jie Peng, Yanping Zheng, Zhewei Zhe +3Semantic ID Recommendation Sequential Recommendation
Renmin University of China · Beijing, China · Alibaba
Bridging the Information Gap: Semantic Densification and Hindsight Distillation for Cold-Start Prediction
Jul 19, 2026Hao Duong Le, Yifei Gao, Huan Li +4Cold-Start Recommendation Conversion Rate Prediction
Tsinghua University Beijing, China · Meituan Beijing, China
ViHoRec: A Quality-Controlled Vietnamese Hotel Recommendation Dataset and Cold-Start Benchmark
Jul 14, 2026Minh Hoang NguyenCold-Start Recommendation Recommender Systems
Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam
Proximity Features: Privacy-Compliant Cold-Start Personalization at Airbnb
Jul 14, 2026Wei Jiang, Bin Xu, Hui Gao +6Cold-Start Recommendation Privacy-Preserving ML
Airbnb Inc. San Francisco, USA
SISA-Rec: A Semantically Integrated Sequential Recommender with Contrastive Alignment
Jul 13, 2026Soohan Abbasi, Shahid Munir Shah, Rafia Shaikh +1Sequential Recommendation Cold-Start Recommendation
Department of Computer Science, DHA Suffa University, Karachi, Sindh, Pakistan · Department of Computer Science, SZABIST, Pakistan · National University of Computer and Emerging Sciences (FAST), Karachi, Sindh, Pakistan +1
Diagnosing and Mitigating Retrieval Bottlenecks in LLM-Based Cold-Start Recommendation
Jun 29, 2026Zhe Dong, Fang Qin, Manish Shah +1Cold-Start Recommendation LLM Reranking
University of Maine at Presque Isle · Stanford University · 2Stanford University +2
Denoising Implicit Feedback for Cold-start Recommendation
Jun 17, 2026Gaode Chen, Shicheng Wang, Shikun Li +8Cold-Start Recommendation Noisy-Label Learning
Kuaishou Technology Beijing, China · Hong Kong Baptist University Hong Kong, China · Institute of Information Engineering, Chinese Academy of Sciences Beijing, China
VCG: A Multimodal Retrieval Framework for E-Commerce Video Feeds under Extreme Cold-Start Conditions
Jun 17, 2026Katya Mirylenka, Egor Malykh, Mahdyar Ravanbakhsh +10Multimodal IR Cold-Start Recommendation
TU Wien, Vienna, Austria · Zalando Switzerland AG, Zurich, Switzerland · Zalando SE, Berlin, Germany
DiffCold: A Diffusion-based Generative Model for Cold-Start Item Recommendation
Jun 10, 2026Kangning Zhang, Yingjie Qin, Weinan Zhang +2Cold-Start Recommendation Recommender Systems
Shanghai Jiao Tong University, Shanghai, China · Xiaohongshu Inc., Shanghai, China
Mind the Gap: Bridging Behavioral Silos with LLMs in Multi-Vertical Recommendations
Jun 4, 2026Nimesh Sinha, Raghav Saboo, Martin Wang +1Cold-Start Recommendation Cross-Domain Recommendation
DoorDash Inc. San Francisco, California, USA
Bridging the Semantic-Collaborative Gap: An Asymmetric Graph Architecture for Cold-Start Item Recommendation
Jun 4, 2026Anh Truong, John Trenkle, Yuanbo Chen +4Cold-Start Recommendation Graph Representation Learning
Tubi San Francisco, USA · Kumo AI San Francisco, USA
Representation Curriculum: Stagewise Training for Robust Ranking and Allocation
Jun 3, 2026Ehsan Ebrahimzadeh, Sina Baharlouei, Abraham BagherjeiranCold-Start Recommendation Representation Learning
eBay Search Ranking and Monetization San Jose, California, USA
FLUID: From Ephemeral IDs to Multimodal Semantic Codes for Industrial-Scale Livestreaming Recommendation
May 20, 2026Xinhang Yuan, Zexi Huang, Anjia Cao +6Semantic ID Recommendation Cold-Start Recommendation
TikTok · ByteDance
Towards Sustainable Growth: A Multi-Value-Aware Retrieval Framework for E-Commerce Search
May 18, 2026Yifan Wang, Yixuan Wang, YiDan Liang +2Cold-Start Recommendation E-Commerce Search
Taobao & Tmall Group of Alibaba · HangZhou, China
Pseudo Label NCF for Sparse OHC Recommendation: Dual Representation Learning and the Separability Accuracy Trade off
Mar 25, 2026Pronob Kumar Barman, Tera L. Reynolds, James FouldsCollaborative Filtering Cold-Start Recommendation
Department of Information Systems, University of Maryland, Baltimore County, Baltimore, Maryland, USA
GenRecEdit: Adapting Model Editing for Generative Recommendation with Cold-Start Items
Mar 15, 2026Chenglei Shen, Teng Shi, Weijie Yu +2Generative Recommendation Cold-Start Recommendation
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China · School of Information Technology and Management, University of International Business and Economics, Beijing, China
IDProxy: CTR Prediction with Multimodal LLMs for Cold-Start Recommendation at Xiaohongshu
Mar 2, 2026Yubin Zhang, Haiming Xu, Guillaume Salha-Galvan +6Cold-Start Recommendation Multimodal Embedding
Xiaohongshu Inc. Shanghai, China · Shanghai Jiao Tong University Shanghai, China · Fudan University Shanghai, China
Trinity: A Scenario-Aware Recommendation Framework for Large-Scale Cold-Start Users
Feb 28, 2026Wenhao Zheng, Wang Lu, Fangshuang Tang +4Cross-Domain Recommendation Cold-Start Recommendation
Mircosoft Corp, Redmond, WA, USA

Oct 14, 2026J/K move · Enter open · S save

Bridging the Topological Divide: Dual-Branch Graph Distillation with Semantic Priors for Robust Cold-Start Recommendation

Yuanfeng Qiu

The Hong Kong University of Science and Technology (Guangzhou)

Cold-Start Recommendation Collaborative Filtering Multimodal Recommendation Knowledge Distillation

Open paper AskPDF arXiv

Graph Collaborative Filtering models have achieved remarkable success in recommendation systems. However, they inherently suffer from a catastrophic representation collapse in strict cold-start scenarios due to the topological isolation of unobserved items. While integrating multi-modal semantic features offers a potential remedy, directly mapping isolated semantic attributes into a globally topology-driven collaborative space frequently precipitates representation degradation and optimization conflicts. To bridge this fundamental structural divide, we propose DualGCN, an innovative Dual-Branch Graph Knowledge Distillation Framework. Operating under a decoupled two-stage training paradigm, DualGCN first constructs a robust collaborative teacher network where item representations are anchored by a topology-smoothed semantic prior, effectively reshaping the latent manifold. Subsequently, a semantic student branch employs a residual mapping mechanism and a magnitude-agnostic cosine distillation objective to achieve high-fidelity cross-modal alignment without disrupting established collaborative signals. Furthermore, we introduce a dynamic norm reconstruction mechanism to rigorously calibrate the physical scales of novel and warm items during global retrieval. Extensive experiments across three real-world benchmark datasets demonstrate that DualGCN significantly outperforms state-of-the-art baselines in strict cold-start scenarios while comprehensively preserving recommendation accuracy for highly active items.