关注我们，一起学习~
CIKM 2022的论文已出，笔者整理了其中的推荐系统，点击率以及因果推断相关的论文。今年跨域，图学习还是热点，点击率模型中长短期兴趣的处理是热点。
A Case Study in Educational Recommenders:Recommending Music Partitures at Tomplay【 在 Tomplay 推荐音乐片段 】
A Multi-Interest Evolution Story: Applying Psychology in Query-based Recommendation for Inferring Customer Intention【 在基于查询的推荐中应用心理学以推断客户意图 】
A Relevant and Diverse Retrieval-enhanced Data Augmentation Framework for Sequential Recommendation【 用于序列推荐的相关且多样化的检索增强数据增强框架 】
Adapting Triplet Importance of Implicit Feedback for Personalized Recommendation【 个性化推荐 】
Adaptive Domain Interest Network for Multi-domain Recommendation【 用于多域推荐的自适应域兴趣网络 】
Approximate Nearest Neighbor Search under Neural Similarity Metric for Large-Scale Recommendation【 大规模推荐的神经相似度度量下的近似最近邻搜索 】
Asymmetrical Context-aware Modulation for Collaborative Filtering Recommendation【 用于协同过滤推荐的非对称上下文感知调制 】
AutoMARS: Searching to Compress Multi-Modality Recommendation Systems【 AutoMARS：搜索压缩多模态推荐系统 】
Automatic Meta-Path Discovery for Effective Graph-Based Recommendation【 基于图的有效推荐的自动元路径发现 】
Best practices for top-N recommendation evaluation: Candidate set sampling and Statistical inference techniques【 top-N 推荐评估的最佳实践：候选集抽样和统计推断技术 】
Beyond Learning from Next Item: Sequential Recommendation via Personalized Interest Sustainability【 通过个性化兴趣可持续性的序列推荐 】
CROLoss: Towards a Customizable Loss for Retrieval Models in Recommender Systems【 CROLoss：迈向推荐系统中检索模型的可定制损失 】
ContrastVAE: Contrastive Variational AutoEncoder for Sequential Recommendation【 ContrastVAE：用于序列推荐的对比变分自动编码器 】
Contrastive Cross-Domain Sequential Recommendation【 对比跨域序列推荐 】
Contrastive Learning with Bidirectional Transformers for Sequential Recommendation【 用于序列推荐的双向 Transformer 对比学习 】
Cross-domain Recommendation via Adversarial Adaptation【 通过对抗性适应进行跨域推荐 】
DeepVT: Deep View-Temporal Interaction Network for News Recommendation【 DeepVT：新闻推荐的深度视图-时间交互网络 】
Disentangling Past-Future Modeling in Sequential Recommendation via Dual Networks【 通过双网络解耦序列推荐中的过去未来 】
Dual-Task Learning for Multi-Behavior Sequential Recommendation【 多行为序列推荐的双任务学习 】
Dually Enhanced Propensity Score Estimation in Sequential Recommendation【 序列推荐中的双重增强倾向得分估计 】
Evolutionary Preference Learning via Graph Nested GRU ODE for Session-based Recommendation【 通过图嵌套 GRU ODE 进行进化偏好学习，用于基于会话的推荐 】
Explanation Guided Contrastive Learning for Sequential Recommendation【 序列推荐的解释引导对比学习 】
FedCDR: Federated Cross-Domain Recommendation for Privacy-Preserving Rating Prediction【 FedCDR：用于隐私保护评级预测的联合跨域推荐 】
GBERT: Pre-training User representations for Ephemeral Group Recommendation【 GBERT：为临时组推荐预训练用户表示 】
GRP: A Gumbel-based Rating Prediction Framework for Imbalanced Recommendation【 GRP：基于 Gumbel 的不平衡推荐评级预测框架 】
Generative Adversarial Zero-Shot Learning for Cold-Start News Recommendation【 冷启动新闻推荐的生成对抗零样本学习 】
Gromov-Wasserstein Guided Representation Learning for Cross-Domain Recommendation【 Gromov-Wasserstein 引导表征学习的跨域推荐 】
Hierarchical Item Inconsistency Signal learning for Sequence Denoising in Sequential Recommendation【 序列推荐中序列去噪的分层商品不一致信号学习 】
HySAGE: A Hybrid Static and Adaptive Graph Embedding Network for Context-Drifting Recommendations【 HySAGE：用于上下文漂移推荐的混合静态和自适应图嵌入网络 】
Improving Knowledge-aware Recommendation with Multi-level Interactive Contrastive Learning【 通过多层次交互式对比学习改进知识感知推荐 】
Improving Text-based Similar Product Recommendation for Dynamic Product Advertising at Yahoo【 改进雅虎动态产品广告的基于文本的相似产品推荐 】
Knowledge Enhanced Multi-Interest Network for the Generation of Recommendation Candidates【 用于生成推荐候选的知识增强多兴趣网络 】
Knowledge Extraction and Plugging for Online Recommendation【 在线推荐的知识抽取与插入 】
KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systems【 KuaiRec：用于评估推荐系统的完全观察数据集和见解 】
Leveraging Multiple Types of Domain Knowledge for Safe and Effective Drug Recommendation【 利用多种领域知识进行安全有效的药物推荐 】
MARIO: Modality-Aware Attention and Modality-Preserving Decoders for Multimedia Recommendation【 MARIO：用于多媒体推荐的模态感知注意力和模态保留解码器 】
MIC:Model-agnostic Integrated Cross-channel Recommender【 MIC：与模型无关的集成跨渠道推荐系统 】
Memory Bank Augmented Long-tail Sequential Recommendation【 记忆库增强长尾序列推荐 】
Multi-Aggregator Time-Warping Heterogeneous Graph Neural Network for Personalized Micro-video Recommendation【 用于个性化微视频推荐的多聚合器时间扭曲异构图神经网络 】
Multi-Faceted Hierarchical Multi-Task Learning for Recommender Systems【 推荐系统的多方面分层多任务学习 】
Multi-level Contrastive Learning Framework for Sequential Recommendation【 序列推荐的多层次对比学习框架 】
Multimodal Meta-Learning for Cold-Start Sequential Recommendation【 冷启动序列推荐的多模态元学习 】
PROPN: Personalized Probabilistic Strategic Parameter Optimization in Recommendations【 PROPN：推荐中的个性化概率策略参数优化 】
PlatoGL: Effective and Scalable Deep Graph Learning System for Graph-enhanced Real-Time Recommendation【 PlatoGL：用于图增强实时推荐的有效且可扩展的深度图学习系统 】
Quantifying and Mitigating Popularity Bias in Conversational Recommender Systems【 量化和减轻会话推荐系统中的流行度偏差 】
Rank List Sensitivity of Recommender Systems to Interaction Perturbations【 推荐系统对交互扰动的排名列表敏感性 】
Real-time Short Video Recommendation on Mobile Devices【 移动端实时短视频推荐 】
Representation Matters When Learning From Biased Feedback in Recommendation【 从推荐中的有偏偏反馈中学习时，表征很重要 】
Rethinking Conversational Recommendations: Is Decision Tree All You Need?【 重新思考对话推荐：决策树！！ 】
Review-Based Domain Disentanglement without Duplicate Users or Contexts for Cross-Domain Recommendation【 跨域推荐 】
SASNet: Stage-aware sequential matching for online travel recommendation【 SASNet：在线旅游推荐的阶段感知序列匹配 】
SVD-GCN: A Simplified Graph Convolution Paradigm for Recommendation【 SVD-GCN：用于推荐的简化图卷积范式 】
Scenario-Adaptive and Self-Supervised Model for Multi-Scenario Personalized Recommendation【 多场景个性化推荐的场景自适应自监督模型 】
Spatiotemporal-aware Session-based Recommendation with Graph Neural Networks【 使用图神经网络的时空感知基于会话的推荐 】
Storage-saving Transformer for Sequential Recommendations【 用于序列推荐的节省存储的Transformer 】
Target Interest Distillation for Multi-Interest Recommendation【 多兴趣推荐的目标兴趣蒸馏 】
Temporal Contrastive Pre-Training for Sequential Recommendation【 序列推荐的时间对比预训练 】
The Interaction Graph Auto-encoder Network Based on Topology-aware for Transferable Recommendation【 基于拓扑感知的可迁移推荐交互图自动编码器网络 】
Tiger: Transferable Interest Graph Embedding for Domain-Level Zero-Shot Recommendation【 Tiger：用于域级零样本推荐的可迁移兴趣图嵌入 】
Time Lag Aware Sequential Recommendation【 延时感知序列推荐 】
Towards Principled User-side Recommender Systems【 迈向有原则的用户侧推荐系统 】
Two-level Graph Path Reasoning for Conversational Recommendation with User Realistic Preference【 具有用户现实偏好的会话推荐的两级图路径推理 】
UDM: A Unified Deep Matching Framework in Recommender Systems【 UDM：推荐系统中的统一深度匹配框架 】
User Recommendation in Social Metaverse with VR【 VR的用户推荐 】
点击率估计
GIFT: Graph-guIded Feature Transfer for Cold-Start Video Click-Through Rate Prediction【 GIFT：用于冷启动视频点击率预测的图引导特征迁移 】
Graph Based Long-Term And Short-Term Interest Model for Click-Through Rate Prediction【 用于点击率预测的基于图的长期和短期兴趣模型 】
Hierarchically Fusing Long and Short-Term User Interests for Click-Through Rate Prediction in Product Search【 分层融合长期和短期用户兴趣以进行产品搜索中的点击率预测 】
OptEmbed: Learning Optimal Embedding Table for Click-through Rate Prediction【 OptEmbed：学习点击率预测的最优嵌入表 】
Sparse Attentive Memory Network for Click-through Rate Prediction with Long Sequences【 用于长序列点击率预测的稀疏注意力记忆网络 】
Towards Understanding the Overfitting Phenomenon of Deep Click-Through Rate Models【 了解深度点击率模型的过拟合现象 】
因果推断，因果效应
E-Commerce Promotions Personalization via Online Multiple-Choice Knapsack with Uplift Modeling【 通过带有uplift建模的在线的电子商务促销个性化 】
MEMENTO: Neural Model for Estimating Individual Treatment Effects for Multiple Treatments【 MEMENTO：用于估计多干预的ITE的神经模型 】
Adaptive Multi-Source Causal Inference from Observational Data【 来自观测数据的自适应多源因果推断 】
Bootstrap-based Causal Structure Learning【 基于 Bootstrap 的因果结构学习 】
Causal Learning Empowered OD Prediction for Urban Planning【 因果学习赋能城市规划 】
Causal Relationship over Knowledge Graphs【 知识图谱上的因果关系 】
Dynamic Causal Collaborative Filtering【 动态因果协同过滤 】
Estimating Causal Effects on Networked Observational Data via Representation Learning【 通过表征学习估计网络观测数据的因果效应 】
交流群：点击“联系作者”--备注“研究方向-公司或学校”
欢迎|论文宣传|合作交流
往期推荐
[KDD'22 | 超图上也能学习因果效应？
2022-09-18
[CIKM'22 | EC4SRec：可解释引导的对比学习用于序列推荐
2022-09-12
[CIKM'22「阿里」CROLoss: 一种推荐系统中检索模型的可定制损失函数
2022-09-11
[CIKM'22 | 序列推荐中的多层次对比学习框架
2022-09-04
长按关注，更多精彩
点个在看你最好看