随笔分类 -  Recommender Systems

1 2 3 4 5 ··· 8 下一页
Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction
摘要：目录概Search-based Interest Model (SIM)子序列抽取Exact Search Unit Qi P., Zhu X., Zhou G., Zhang Y., Wang Z., Ren L., Fan Y. and Gai K. Search-based user inte 阅读全文
posted @ 2025-02-26 11:57 馒头and花卷 阅读(6) 评论(0) 推荐(0) 编辑
How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspective
摘要：目录概符号说明Popularity biasq1 和 r 具有高相似度相似度随着维度降低而增加相似度随着训练的变化ReSN: Regulartion with Spectral Norm Lin S., Gao C., Chen J., Zhou 阅读全文
posted @ 2025-02-20 16:24 馒头and花卷 阅读(3) 评论(0) 推荐(0) 编辑
STAR: A Simple Training-free Approach for Recommendations using Large Language Models
摘要：目录概符号说明STARRetrievalRanking最后的结果 Lee D., Kraft A., Jin L., Mehta N., Xu T., Hong L., Chi E. H. and Yi X. STAR: A simple training-free approach for rec 阅读全文
posted @ 2024-10-23 11:03 馒头and花卷 阅读(103) 评论(0) 推荐(0) 编辑
Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendation
摘要：目录概Graph CLSimGCL代码 Yu J., Yin H., Xia X., Chen T., Cui L. and Huang N. Q. V. Are graph augmentations necessary? simple graph contrastive learning for 阅读全文
posted @ 2024-10-16 14:03 馒头and花卷 阅读(25) 评论(0) 推荐(0) 编辑
Long-Sequence Recommendation Models Need Decoupled Embeddings
摘要：目录概Decoupled Attention and Representation Embeddings (DARE) model Feng N., Pang J., Wu J., Chen B., Wang X., Li Q., Hu X., Jiang J. and Long M. Long-s 阅读全文
posted @ 2024-10-06 10:29 馒头and花卷 阅读(85) 评论(0) 推荐(0) 编辑
DCN V2 Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems
摘要：目录概DCN-v2 Wang R., Shivanna R., Cheng D. Z., Jain S., Lin D., Hong L. and Chi E. D. DCN V2: Improved deep & cross network and practical lessons for we 阅读全文
posted @ 2024-08-29 11:19 馒头and花卷 阅读(71) 评论(2) 推荐(1) 编辑
An Attentive Inductive Bias for Sequential Recommendation beyond the Self-Attention
摘要：目录概符号说明BSARec (Beyond Self-Attention for Sequential Recommendation)代码 Shin Y., Choi J., Wi H. and Park N. An attentive inductive bias for sequential r 阅读全文
posted @ 2024-07-07 15:21 馒头and花卷 阅读(111) 评论(0) 推荐(0) 编辑
User Behavior Simulation with Large Language Model based Agents
摘要：目录概RecAgentProfile moduleMemory moduleAction module Wang L, Zhang J., Yang H., Chen Z., Tang J., Zhang Z., Chen X., Lin Y., Sun H., Song R., Zhao W. X 阅读全文
posted @ 2024-07-03 16:19 馒头and花卷 阅读(74) 评论(0) 推荐(0) 编辑
A LLM-based Controllable, Scalable, Human-Involved User Simulator Framework for Conversational Recommender Systems
摘要：目录概CSHI (Controllable, Scalable, and Human-Involved)代码 Zhu L., Huang X. and Sang J. A llm-based controllable, scalable, human-involved user simulator 阅读全文
posted @ 2024-07-02 16:14 馒头and花卷 阅读(60) 评论(0) 推荐(0) 编辑
Towards Universal Sequence Representation Learning for Recommender Systems
摘要：目录概符号说明UniSRec统一的文本表示统一的序列表示Parameter-Efficient Fine-tuning代码 Hou Y., Mu S., Zhao W. X., Li Y., Ding B. and Wen J. Towards Universal Sequence Represen 阅读全文
posted @ 2024-05-28 16:46 馒头and花卷 阅读(54) 评论(0) 推荐(0) 编辑
End-to-end training of Multimodal Model and ranking Model
摘要：目录概主要内容 Deng X., Xu L., Li X., Yu J., Xue E., Wang Z., Zhang D., Liu Z., Song Y., Zhou G., Mou N. and Jiang S. End-to-end training of multimodal model 阅读全文
posted @ 2024-05-28 15:55 馒头and花卷 阅读(301) 评论(0) 推荐(0) 编辑
LGMRec Local and Global Graph Learning for Multimodal Recommendation
摘要：目录概符号说明MotivationLGMRecLocal Graph EmbeddingGlobal Graph EmbeddingFusion代码 Guo Z., Li J., Li G., Wang C., Shi S. and Ruan B. LGMRec: Local and global 阅读全文
posted @ 2024-05-27 11:35 馒头and花卷 阅读(100) 评论(0) 推荐(0) 编辑
Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations
摘要：目录概GRs (Generative Recommenders)任务形式模型设计代码 Zhai J., Liao L., Liu X., Wang Y., Li R., Cao X., Gao L., Gong Z., Gu F., He M., Lu Y. and Shi Y. Actions s 阅读全文
posted @ 2024-05-26 09:40 馒头and花卷 阅读(897) 评论(0) 推荐(2) 编辑
Bridging Language and Items for Retrieval and Recommendation
摘要：目录概BLaIR代码 Hou Y., Li J., He Z., Yan A., Chen X., and McAuley J. Bridging language and items for retrieval and recommendation. 2024. 概 本文提出了一种利用对比损失训练 阅读全文
posted @ 2024-05-23 16:47 馒头and花卷 阅读(52) 评论(0) 推荐(0) 编辑
How to Learn Item Representation for Cold-Start Multimedia Recommendation
摘要：目录概符号说明MotivationMulti-Task Pairwise Ranking (MTPR)代码 Du X., Wang X., He X., Li Z., Tang J. and Chua T. How to learn item representation for cold-star 阅读全文
posted @ 2024-05-11 14:35 馒头and花卷 阅读(33) 评论(0) 推荐(0) 编辑
Lightweight Modality Adaptation to Sequential Recommendation via Correlation Supervision
摘要：目录概符号说明MotivationKnowledge Distillation framework for modality-enriched Sequential Recommenders (KGSR)相似度建模相似度预测训练 Hu H., Liu Q., Li C. and Kan M. Lig 阅读全文
posted @ 2024-05-08 16:21 馒头and花卷 阅读(12) 评论(0) 推荐(0) 编辑
A Revisiting Study of Appropriate Offline Evaluation for Top-N Recommendation Algorithms
摘要：目录概实验设置Evaluation MetricsMetric 的一致性不同的 metrics 导致的算法排名差异Sampled metricsSampled metrics 是否会导致和 full ranking 的 metrics 不同的评价数据集构建数据集的选择和预处理k-core f 阅读全文
posted @ 2024-05-07 10:43 馒头and花卷 阅读(44) 评论(0) 推荐(0) 编辑
A Critical Study on Data Leakage in Recommender System Offline Evaluation
摘要：目录概主要内容数据集统计信息Top-N Recommendation ListRecommendation Accuracy理想的切分方式代码 Ji Y., Sun A., Zhang J. and Li C. A critical study on data leakage in recommen 阅读全文
posted @ 2024-05-05 17:09 馒头and花卷 阅读(15) 评论(0) 推荐(0) 编辑
Do Loyal Users Enjoy Better Recommendations? Understanding Recommender Accuracy from a Time Perspective
摘要：目录概实验设置实验Interaction-based LoyaltyActive Time Period based LoyaltyRecency代码 Ji Y., Sun A., Zhang J. and Li C. Do Loyal Users Enjoy Better Recommendati 阅读全文
posted @ 2024-05-04 11:17 馒头and花卷 阅读(5) 评论(0) 推荐(0) 编辑
Enhancing ID and Text Fusion via Alternative Training in Session-based Recommendation
摘要：目录概MotivationAlterRec代码 Li J., Han H., Chen Z., Shomer H., Jin W., Javari A. and Tang J. Enhancing ID and text fusion via alternative training in sess 阅读全文
posted @ 2024-04-25 13:45 馒头and花卷 阅读(19) 评论(0) 推荐(0) 编辑

1 2 3 4 5 ··· 8 下一页
点击右上角即可分享
微信分享提示