Redian新闻
>
CIKM 2022 | 推荐系统相关论文分类整理

CIKM 2022 | 推荐系统相关论文分类整理

公众号新闻


MLNLP社区是国内外知名的机器学习与自然语言处理社区,受众覆盖国内外NLP硕博生、高校老师以及企业研究人员。
社区的愿景是促进国内外自然语言处理,机器学习学术界、产业界和广大爱好者之间的交流和进步,特别是初学者同学们的进步。
转载自 | RUC AI Box
作者 | 孙文奇
机构 | 中国人民大学高瓴人工智能学院
研究方向 | 推荐系统
本文选取了CIKM 2022中86篇长文和26篇应用文,重点对推荐系统相关论文(85篇)按不同的任务场景和研究话题进行分类整理,也对其他热门研究方向(预训练模型、信息检索和知识图谱等,27篇)进行了归类,以供参考。
第31届国际信息与知识管理大会(The 31st ACM International Conference on Information and Knowledge Management, CIKM 2022)计划于2022年10月17日-10月21日以线上线下混合方式召开。ACM CIKM是CCF推荐的B类国际学术会议,是信息检索和数据挖掘领域最重要的学术会议之一。这次会议共录用274篇长文(Full Paper)、91篇应用文(Applied Paper)和196篇短文/资源文(Short / Resource Paper)。官方发布的接收论文列表:
https://www.cikm2022.org/papers-posters
从词云图看今年CIKM的研究热点:根据长文和应用文的标题绘制如下词云图,可以看到今年研究方向主要集中在Recommendation、Retrieval和Knowledge Graph三个方向,也包括Pre-trained Language Model等NLP方向。主要任务包括:Click-Through Rate、Sequential Recommendation、User Modeling等;热门技术包括:Graph Neural Network、Contrastive Learning等,其中基于Sequence和Graph的任务和技术依旧是今年的研究热点。
对于推荐算法的开发与复现,欢迎大家使用推荐系统工具包RecBole(伯乐)。RecBole 是一个基于 PyTorch 实现的,面向研究者的,易于开发与复现的,统一、全面、高效的推荐系统代码库。
  • 工具包:
    https://github.com/RUCAIBox/RecBole
    https://github.com/RUCAIBox/RecBole2.0
  • 数据集:
    https://github.com/RUCAIBox/RecSysDatasets

  • 论文(RecBole 2.0已被CIKM 2022录用为Resource Paper):
    RecBole 2.0: Towards a More Up-to-Date Recommendation Library

1

『目录』

1 按推荐的任务场景划分
  • Click-Through Rate
  • Collaborative Filtering
  • Sequential/Session-based Recommendation
  • Knowledge-Aware Recommendation
  • Social Recommendation
  • News Recommendation
  • Text-Aware Recommendation
  • Conversational Recommender System
  • Cross-domain Recommendation
  • Online Recommendation
  • Group Recommendation
  • Other Tasks
2 按推荐的研究话题划分
  • Debias in Recommender System
  • Fairness in Recommender System
  • Explanation in Recommender System
  • Cold-start in Recommender System
  • Ranking in Recommender System
  • Evaluation
  • Others
3 热门技术在推荐中的应用
  • Graph Neural Network in Recommender System
  • Contrastive Learning in Recommender System
  • Variational Autoencoder in Recommender System
  • Meta/Zero-shot/Few-shot Learning
4 其他研究方向
  • Pre-training
  • Information Retrieval
  • Knowledge Graph


2

『正文』

1、按推荐的任务场景划分
1.1 Click-Through Rate
  1. Towards Understanding the Overfitting Phenomenon of Deep Click-Through Rate Models
  2. Sparse Attentive Memory Network for Click-through Rate Prediction with Long Sequences
  3. Graph Based Long-Term And Short-Term Interest Model for Click-Through Rate Prediction
  4. GRP: A Gumbel-based Rating Prediction Framework for Imbalanced Recommendation
  5. Hierarchically Fusing Long and Short-Term User Interests for Click-Through Rate Prediction in Product Search
  6. OptEmbed: Learning Optimal Embedding Table for Click-through Rate Prediction
  7. Sampling Is All You Need on Modeling Long-Term User Behaviors for CTR Prediction【applied paper】
  8. GIFT: Graph-guIded Feature Transfer for Cold-Start Video Click-Through Rate Prediction【applied paper】
1.2 Collaborative Filtering
  1. Asymmetrical Context-aware Modulation for Collaborative Filtering Recommendation
  2. Dynamic Hypergraph Learning for Collaborative Filtering
  3. NEST: Simulating Pandemic-like Events for Collaborative Filtering by Modeling User Needs Evolution
  4. MDGCF: Multi-Dependency Graph Collaborative Filtering with Neighborhood- and Homogeneous-level Dependencies
  5. ITSM-GCN: Informative Training Sample Mining for Graph Convolution Network-based Collaborative Filtering
1.3 Sequential/Session-based Recommendation
  1. Beyond Learning from Next Item: Sequential Recommendation via Personalized Interest Sustainability
  2. Evolutionary Preference Learning via Graph Nested GRU ODE for Session-based Recommendation
  3. Disentangling Past-Future Modeling in Sequential Recommendation via Dual Networks
  4. Dual-Task Learning for Multi-Behavior Sequential Recommendation
  5. Dually Enhanced Propensity Score Estimation in Sequential Recommendation
  6. Temporal Contrastive Pre-Training for Sequential Recommendation
  7. Storage-saving Transformer for Sequential Recommendations
  8. Time Lag Aware Sequential Recommendation
  9. Hierarchical Item Inconsistency Signal learning for Sequence Denoising in Sequential Recommendation
  10. A Relevant and Diverse Retrieval-enhanced Data Augmentation Framework for Sequential Recommendation【applied paper】
1.4 Knowledge-Aware Recommendation
  1. Improving Knowledge-aware Recommendation with Multi-level Interactive Contrastive Learning
  2. Leveraging Multiple Types of Domain Knowledge for Safe and Effective Drug Recommendation
  3. Accurate Action Recommendation for Smart Home via Two-Level Encoders and Commonsense Knowledge
  4. Knowledge Enhanced Multi-Interest Network for the Generation of Recommendation Candidates【applied paper】
1.5 Social Recommendation
  1. User Recommendation in Social Metaverse with VR
1.6 News Recommendation
  1. DeepVT: Deep View-Temporal Interaction Network for News Recommendation
1.7 Text-Aware Recommendation
  1. Review-Based Domain Disentanglement without Duplicate Users or Contexts for Cross-Domain Recommendation
  2. Improving Text-based Similar Product Recommendation for Dynamic Product Advertising at Yahoo【applied paper】
1.8 Conversational Recommender System
  1. Rethinking Conversational Recommendations: Is Decision Tree All You Need?
  2. Two-level Graph Path Reasoning for Conversational Recommendation with User Realistic Preference
1.9 Cross-domain Recommendation
  1. Contrastive Cross-Domain Sequential Recommendation
  2. Cross-domain Recommendation via Adversarial Adaptation
  3. Gromov-Wasserstein Guided Representation Learning for Cross-Domain Recommendation
  4. FedCDR: Federated Cross-Domain Recommendation for Privacy-Preserving Rating Prediction
  5. Cross-Domain Aspect Extraction using Transformers Augmented with Knowledge Graphs
  6. Adaptive Domain Interest Network for Multi-domain Recommendation【applied paper】
1.10 Online Recommendation
  1. Knowledge Extraction and Plugging for Online Recommendation【applied paper】
  2. SASNet: Stage-aware sequential matching for online travel recommendation【applied paper】
1.11 Group Recommendation
  1. GBERT: Pre-training User representations for Ephemeral Group Recommendation
1.12 Other Tasks
  1. MARIO: Modality-Aware Attention and Modality-Preserving Decoders for Multimedia Recommendation
  2. Target Interest Distillation for Multi-Interest Recommendation
  3. A Multi-Interest Evolution Story: Applying Psychology in Query-based Recommendation for Inferring Customer Intention
  4. HySAGE: A Hybrid Static and Adaptive Graph Embedding Network for Context-Drifting Recommendations
  5. Task Publication Time Recommendation in Spatial Crowdsourcing
  6. AutoMARS: Searching to Compress Multi-Modality Recommendation Systems
  7. MIC: Model-agnostic Integrated Cross-channel Recommender【applied paper】
  8. A Case Study in Educational Recommenders: Recommending Music Partitures at Tomplay【applied paper】
  9. Real-time Short Video Recommendation on Mobile Devices【applied paper】
  10. Scenario-Adaptive and Self-Supervised Model for Multi-Scenario Personalized Recommendation【applied paper】
  11. Multi-Faceted Hierarchical Multi-Task Learning for Recommender Systems【applied paper】
2、按推荐的研究话题划分
2.1 Debias in Recommender System
  1. Quantifying and Mitigating Popularity Bias in Conversational Recommender Systems
  2. Representation Matters When Learning From Biased Feedback in Recommendation
  3. Hard Negatives or False Negatives: Correcting Pooling Bias in Training Neural Ranking Models
  4. Unbiased Learning to Rank with Biased Continuous Feedback
  5. Debiased Balanced Interleaving at Amazon Search【applied paper】
  6. Mitigating Biases in Student Performance Prediction via Attention-Based Personalized Federated Learning【applied paper】
2.2 Fairness in Recommender System
  1. RAGUEL: Recourse-Aware Group Unfairness Elimination
  2. Towards Principled User-side Recommender Systems
2.3 Explanation in Recommender System
  1. Explanation Guided Contrastive Learning for Sequential Recommendation
2.4 Cold-start in Recommender System
  1. Generative Adversarial Zero-Shot Learning for Cold-Start News Recommendation
  2. Addressing Cold Start in Product Search via Empirical Bayes【applied paper】
2.5 Ranking in Recommender System
  1. Rank List Sensitivity of Recommender Systems to Interaction Perturbations
  2. Memory Bank Augmented Long-tail Sequential Recommendation
  3. A Biased Sampling Method for Imbalanced Personalized Ranking
2.6 Evaluation
  1. KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systems
2.7 Others
  1. An Uncertainty-Aware Imputation Framework for Alleviating the Sparsity Problem in Collaborative Filtering
  2. Adapting Triplet Importance of Implicit Feedback for Personalized Recommendation
  3. PROPN: Personalized Probabilistic Strategic Parameter Optimization in Recommendations【applied paper】
  4. UDM: A Unified Deep Matching Framework in Recommender Systems【applied paper】
  5. Approximate Nearest Neighbor Search under Neural Similarity Metric for Large-Scale Recommendation【applied paper】
3、热门技术在推荐中的应用
3.1 Graph Neural Network in Recommender System
  1. SVD-GCN: A Simplified Graph Convolution Paradigm for Recommendation
  2. Automatic Meta-Path Discovery for Effective Graph-Based Recommendation
  3. Spatiotemporal-aware Session-based Recommendation with Graph Neural Networks
  4. Multi-Aggregator Time-Warping Heterogeneous Graph Neural Network for Personalized Micro-video Recommendation
  5. The Interaction Graph Auto-encoder Network Based on Topology-aware for Transferable Recommendation
  6. PlatoGL: Effective and Scalable Deep Graph Learning System for Graph-enhanced Real-Time Recommendation【applied paper】
3.2 Contrastive Learning in Recommender System
  1. Contrastive Learning with Bidirectional Transformers for Sequential Recommendation
  2. Domain-Agnostic Constrastive Representations for Learning from Label Proportions
  3. Multi-level Contrastive Learning Framework for Sequential Recommendation
3.3 Variational Autoencoder in Recommender System
  1. ContrastVAE: Contrastive Variational AutoEncoder for Sequential Recommendation
3.4 Meta/Zero-Shot/Few-Shot Learning
  1. Tiger: Transferable Interest Graph Embedding for Domain-Level Zero-Shot Recommendation
  2. Multimodal Meta-Learning for Cold-Start Sequential Recommendation【applied paper】
4、其他研究方向
4.1 Pre-training
  1. Cognize Yourself: Graph Pre-Training via Core Graph Cognizing and Differentiating
  2. CorpusBrain: Pre-train a Generative Retrieval Model for Knowledge-Intensive Language Tasks
  3. Semorph: A Morphology Semantic Enhanced Pre-trained Model for Chinese Spam Text Detection
  4. Graph Neural Networks Pretraining Through Inherent Supervision for Molecular Property Prediction【applied paper】
  5. Fooling MOSS Detection with Pretrained Language Models【applied paper】
4.2 Information Retrieval
  1. CROLoss: Towards a Customizable Loss for Retrieval Models in Recommender Systems
  2. Contrastive Label Correlation Enhanced Unified Hashing Encoder for Cross-modal Retrieval
  3. Evaluating Interpolation and Extrapolation Performance of Neural Retrieval Models
  4. Detecting Significant Differences Between Information Retrieval Systems via Generalized Linear Models
  5. PLAID: An Efficient Engine for Late Interaction Retrieval
  6. Scattered or Connected? An Optimized Parameter-efficient Tuning Approach for Information Retrieval
  7. SpaDE: Improving Sparse Representations using a Dual Document Encoder for First-stage Retrieval
  8. Dense Retrieval with Entity Views
  9. Approximated Doubly Robust Search Relevance Estimation【applied paper】
  10. Cross-Domain Product Search with Knowledge Graph【applied paper】
4.3 Knowledge Graph
  1. Along the Time: Timeline-traced Embedding for Temporal Knowledge Graph Completion
  2. Explainable Link Prediction in Knowledge Hypergraphs
  3. I Know What You Do Not Know: Knowledge Graph Embedding via Co-distillation Learning
  4. Inductive Knowledge Graph Reasoning for Multi-batch Emerging Entities
  5. Large-scale Entity Alignment via Knowledge Graph Merging, Partitioning and Embedding
  6. Contrastive Knowledge Graph Error Detection
  7. Contrastive Representation Learning for Conversational Question Answering over Knowledge Graphs
  8. DA-Net: Distributed Attention Network for Temporal Knowledge Graph Reasoning
  9. Discovering Fine-Grained Semantics in Knowledge Graph Relations
  10. High-quality Task Division for Large-scale Entity Alignment
  11. Interactive Contrastive Learning for Self-Supervised Entity Alignment
  12. Cognitive Diagnosis focusing on Knowledge Components【applied paper】


技术交流群邀请函

△长按添加小助手

扫描二维码添加小助手微信

请备注:姓名-学校/公司-研究方向
(如:小张-哈工大-对话系统)
即可申请加入自然语言处理/Pytorch等技术交流群

关于我们

MLNLP 社区是由国内外机器学习与自然语言处理学者联合构建的民间学术社区,目前已经发展为国内外知名的机器学习与自然语言处理社区,旨在促进机器学习,自然语言处理学术界、产业界和广大爱好者之间的进步。
社区可以为相关从业者的深造、就业及研究等方面提供开放交流平台。欢迎大家关注和加入我们。

微信扫码关注该文公众号作者

戳这里提交新闻线索和高质量文章给我们。
相关阅读
结束了,就这样疫情结束了汇总了89个系统相关的基本概念!EMNLP 2022大会正式落幕,最佳长论文、最佳短论文等奖项公布好文分享 | 靶向蛋白降解药物(TPD),一个全新的小分子药物时代即将来临!(上)CIKM 2022最佳论文:快手提出移动端实时短视频推荐系统语文学得好,长大不得了!中文分级阅读“天花板”8级上市,5折起!厉害了!!!提示学习(Prompt)用在推荐系统上覆盖四种场景、包含正负向反馈,腾讯、西湖大学等发布推荐系统公开数据集Tenrec美到惊叹!这真是给孩子最好的中文分级读物!浅谈扩散模型的有分类器引导和无分类器引导NeurIPS 2022 | 首个将视觉、语言和音频分类任务进行统一的半监督分类学习基准哥哥背课文分心被妈妈教训,狗子立马挡在前面:不准打他铜死亡研究2022丨研究论文大爆发,这15篇论文及大数据分析帮你理清研究思路巴黎凡尔赛游记 (五)易中天 龙应台等的著作都被禁了一文速览知识增强的对话推荐系统移动端部署推荐系统:快手获数据挖掘顶会CIKM 2022最佳论文国家留学基金管理委员会与美国加州大学欧文分校合作奖学金已开放申请工农兵大学好文分享 | 靶向蛋白降解药物(TPD),一个全新的小分子药物时代即将来临!(下)NeurlPS2022推荐系统论文集锦PIEZO1 2022:约1/3论文发展9+SCI期刊;诺奖加持,研究正扩展至临床各个领域。这13篇论文将点亮你的课题思路!CIKM 2022最佳论文提名:证据感知的文档级关系抽取方法ICLR 2023(投稿)|自然语言处理相关论文分类整理EMNLP 2022 | 主会长文论文分类整理又便宜颜值又高的中文分级绘本铁死亡 2022:SCI论文增速堪比火箭,这20篇论文给你打开研究思路CVPR 2022|达摩院开源低成本大规模分类框架FFCICLR 2023(投稿) | 扩散模型相关论文分类整理国家职业分类增设密码工程技术人员新职业【信息安全三分钟】2022.11.012022年,大厂都在“卷”的推荐系统还有进步空间吗?毛泽东时代工业化时的鞍钢宪法EMNLP 2022最佳长论文、最佳短论文等奖项公布!CIKM 2022最佳论文:融合图注意力机制与预训练语言模型的常识库补全PD-L1/PD-1研究2022丨诺奖加持,论文和基金均火箭速度增长;成果及转化正在其时!大数据分析及19篇论文帮你理清思路
logo
联系我们隐私协议©2024 redian.news
Redian新闻
Redian.news刊载任何文章,不代表同意其说法或描述,仅为提供更多信息,也不构成任何建议。文章信息的合法性及真实性由其作者负责,与Redian.news及其运营公司无关。欢迎投稿,如发现稿件侵权,或作者不愿在本网发表文章,请版权拥有者通知本网处理。