2000 character limit reached
Cold-start Bundle Recommendation via Popularity-based Coalescence and Curriculum Heating
Published 5 Oct 2023 in cs.IR and cs.AI | (2310.03813v3)
Abstract: How can we recommend cold-start bundles to users? The cold-start problem in bundle recommendation is crucial because new bundles are continuously created on the Web for various marketing purposes. Despite its importance, existing methods for cold-start item recommendation are not readily applicable to bundles. They depend overly on historical information, even for less popular bundles, failing to address the primary challenge of the highly skewed distribution of bundle interactions. In this work, we propose CoHeat (Popularity-based Coalescence and Curriculum Heating), an accurate approach for cold-start bundle recommendation. CoHeat first represents users and bundles through graph-based views, capturing collaborative information effectively. To estimate the user-bundle relationship more accurately, CoHeat addresses the highly skewed distribution of bundle interactions through a popularity-based coalescence approach, which incorporates historical and affiliation information based on the bundle's popularity. Furthermore, it effectively learns latent representations by exploiting curriculum learning and contrastive learning. CoHeat demonstrates superior performance in cold-start bundle recommendation, achieving up to 193% higher nDCG@20 compared to the best competitor.
- Personalized Bundle List Recommendation. In WWW.
- CB2CF: a neural multiview content-to-collaborative filtering model for completely cold item recommendations. In RecSys.
- Curriculum learning. In ICML.
- BRUCE: Bundle Recommendation Using Contextualized item Embeddings. In RecSys.
- LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation. In ICLR.
- Embedding Factorization Models for Jointly Recommending Items and User Generated Lists. In SIGIR.
- Rating Augmentation with Generative Adversarial Networks towards Accurate Collaborative Filtering. In WWW.
- Bundle Recommendation with Graph Convolutional Networks. In SIGIR.
- Bundle Recommendation and Generation With Graph Neural Networks. IEEE Trans. Knowl. Data Eng. (2023).
- Curriculum Disentangled Recommendation with Noisy Multi-feedback. In NeurIPS.
- Generative Adversarial Framework for Cold-Start Item Recommendation. In SIGIR.
- Matching User with Item Set: Collaborative Bundle Recommendation with Deep Attention Network. In IJCAI.
- A Simple Framework for Contrastive Learning of Visual Representations. In ICML.
- POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashion. In KDD.
- Curriculum Meta-Learning for Next POI Recommendation. In KDD.
- Build Your Own Bundle - A Neural Combinatorial Optimization Method. In MM.
- Personalized Bundle Recommendation in Online Games. In CIKM.
- How to Learn Item Representation for Cold-Start Multimedia Recommendation?. In MM.
- SimCSE: Simple Contrastive Learning of Sentence Embeddings. In EMNLP.
- Learning Image and User Features for Recommendation in Social Networks. In ICCV.
- Density-Based Dynamic Curriculum Learning for Intent Detection. In CIKM.
- Xiangnan He and Tat-Seng Chua. 2017. Neural Factorization Machines for Sparse Predictive Analytics. In SIGIR.
- LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation. In SIGIR.
- A Hierarchical Self-Attentive Model for Recommending User-Generated Item Lists. In CIKM.
- Consistency-Aware Recommendation for User-Generated Item List Continuation. In WSDM.
- Automatic Curriculum Generation by Hierarchical Reinforcement Learning. In ICONIP.
- Bundle MCR: Towards Conversational Bundle Recommendation. In RecSys.
- Accurate bundle matching and generation via multitask learning with partially shared parameters. Plos one (2023).
- Aggregately Diversified Bundle Recommendation via Popularity Debiasing and Configuration-Aware Reranking. In PAKDD.
- Accurate Action Recommendation for Smart Home via Two-Level Encoders and Commonsense Knowledge. In CIKM.
- Data Context Adaptation for Accurate Recommendation with Additional Information. In BigData.
- Diversely Regularized Matrix Factorization for Accurate and Aggregately Diversified Recommendation. In PAKDD.
- Accurate News Recommendation Coalescing Personal and Global Temporal Preferences. In PAKDD.
- PGT: news recommendation coalescing personal and global temporal preferences. Knowl. Inf. Syst. (2021).
- CrossCBR: Cross-view Contrastive Learning for Bundle Recommendation. In KDD.
- Binyamin Manela and Armin Biess. 2022. Curriculum learning with Hindsight Experience Replay for sequential object manipulation tasks. Neural Networks (2022).
- Ruihui Mu. 2018. A Survey of Recommender Systems Based on Deep Learning. IEEE Access (2018).
- Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings. In SIGIR.
- A comparative study of matrix factorization and random walk with restart in recommender systems. In BigData.
- Generating and Personalizing Bundle Recommendations on Steam. In SIGIR.
- Distillation-Enhanced Graph Masked Autoencoders for Bundle Recommendation. In SIGIR.
- BPR: Bayesian Personalized Ranking from Implicit Feedback. In UAI.
- Contrastive Learning with Hard Negative Samples. In ICLR.
- Methods and metrics for cold-start recommendations. In SIGIR.
- Adaptive Feature Sampling for Recommendation with Missing Content Feature Values. In CIKM.
- LARA: Attribute-to-feature Adversarial Learning for New-item Recommendation. In WSDM.
- Revisiting Bundle Recommendation: Datasets, Tasks, Challenges and Opportunities for Intent-aware Product Bundling. In SIGIR.
- Deep content-based music recommendation. In NIPS.
- Representation Learning with Contrastive Predictive Coding. CoRR (2018).
- A Meta-Learning Perspective on Cold-Start Recommendations for Items. In NIPS.
- DropoutNet: Addressing Cold Start in Recommender Systems. In NIPS.
- Towards Representation Alignment and Uniformity in Collaborative Filtering. In KDD.
- Collaborative Deep Learning for Recommender Systems. In KDD.
- Tongzhou Wang and Phillip Isola. 2020. Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere. In ICML.
- A Survey on Curriculum Learning. IEEE Trans. Pattern Anal. Mach. Intell. (2022).
- Towards Personalized Bundle Creative Generation with Contrastive Non-Autoregressive Decoding. In SIGIR.
- Strategy-aware Bundle Recommender System. In SIGIR.
- Contrastive Learning for Cold-Start Recommendation. In MM.
- Self-supervised Graph Learning for Recommendation. In SIGIR.
- SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation. In WWW.
- ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer. In ACL.
- Are Graph Augmentations Necessary?: Simple Graph Contrastive Learning for Recommendation. In SIGIR.
- Multi-task Curriculum Framework for Open-Set Semi-supervised Learning. In ECCV.
- Unifying multi-associations through hypergraph for bundle recommendation. Knowl. Based Syst. (2022).
- Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translation. In AAAI.
- FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling. In NeurIPS.
- Collaborative Knowledge Base Embedding for Recommender Systems. In KDD.
- SuGeR: A Subgraph-based Graph Convolutional Network Method for Bundle Recommendation. In CIKM.
- Multi-view intent disentangle graph networks for bundle recommendation. In AAAI.
- Improving Item Cold-start Recommendation via Model-agnostic Conditional Variational Autoencoder. In SIGIR.
- Contrastive Learning for Debiased Candidate Generation in Large-Scale Recommender Systems. In KDD.
- Contrastive Collaborative Filtering for Cold-Start Item Recommendation. In The Web Conference.
- Recommendation for New Users and New Items via Randomized Training and Mixture-of-Experts Transformation. In SIGIR.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
