推荐算法最前沿 |
您所在的位置:网站首页 › 经典推荐算法有哪些 › 推荐算法最前沿 |
作者 | 学派 来源 | https://zhuanlan.zhihu.com/p/261077109 编辑 | 海边的拾遗者公众号 本文仅作学术交流,如有侵权,请联系后台删除 KDD(https://www.kdd.org/kdd2020/)是推荐领域一个顶级的国际会议。本次接收的论文按照推荐系统应用场景可以大致划分为:CTR预估、TopN推荐、对话式推荐、序列推荐等。同时,GNN、强化学习、多任务学习、迁移学习、AutoML、元学习在推荐系统的落地应用也成为当下的主要研究点。此届会议有很大一部分来自工业界的论文,包括Google、Microsoft、Criteo、Spotify以及国内大厂阿里、百度、字节、华为、滴滴等。 CTR Prediction1. AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction 【华为诺亚】 简介:本文采用AutoML的搜索方法选择重要性高的二次特征交互项、去除干扰项,提升FM、DeepFM这类模型的准确率。 论文:arxiv.org/abs/2003.1123 2. Category-Specific CNN for Visual-aware CTR Prediction at JD.com 【京东】 论文:arxiv.org/abs/2006.1033 3. Towards Automated Neural Interaction Discovering for Click-Through Rate Prediction 【Facebook】 论文:arxiv.org/abs/2007.0643 Graph-based Recommendation1. A Framework for Recommending Accurate and Diverse Items Using Bayesian Graph Convolutional Neural Networks 【华为诺亚】 2. An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph 【Amazon】 论文:arxiv.org/abs/2007.0021 3. M2GRL: A Multi-task Multi-view Graph Representation Learning Framework for Web-scale Recommender Systems 【阿里】 简介:本文通过关联多个视角的图(item-item图、item-shop图、shop-shop图等)增强item表征,用于item召回。 论文:arxiv.org/abs/2005.1011 4. Handling Information Loss of Graph Neural Networks for Session-based Recommendation 5. Interactive Path Reasoning on Graph for Conversational Recommendation 论文:arxiv.org/abs/2007.0019 6. A Dual Heterogeneous Graph Attention Network to Improve Long-Tail Performance for Shop Search in E-Commerce 【阿里】 7. Gemini: A Novel and Universal Heterogeneous Graph Information Fusing Framework for Online Recommendations 【滴滴】 Conversational Recommendation1. Evaluating Conversational Recommender Systems via User Simulation 论文:arxiv.org/abs/2006.0873 2. Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion 论文:arxiv.org/abs/2007.0403 3. Interactive Path Reasoning on Graph for Conversational Recommendation 论文:arxiv.org/abs/2007.0019 CF and Top-N Recommendation1. Dual Channel Hypergraph Collaborative Filtering 【百度】 笔记:blog.csdn.net/weixin_42 2. Probabilistic Metric Learning with Adaptive Margin for Top-K Recommendation 【华为诺亚】 3. Controllable Multi-Interest Framework for Recommendation 【阿里】 论文:arxiv.org/abs/2005.0934 4. Embedding-based Retrieval in Facebook Search 【Facebook】 论文:arxiv.org/abs/2006.1163 5. On Sampling Top-K Recommendation Evaluation Embedding and Representation1. Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems 【Facebook】 论文:arxiv.org/abs/1909.0210 2. PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest 【Pinterest】 论文:arxiv.org/abs/2007.0363 3. SimClusters: Community-Based Representations for Heterogeneous Recommendations at Twitter 【Twitter】 4. Time-Aware User Embeddings as a Service 【Yahoo】 论文:astro.temple.edu/~tuf28 Sequential Recommendation1. Disentangled Self-Supervision in Sequential Recommenders 【阿里】 论文:http://pengcui.thumedialab.com/papers/Disen... 2. Handling Information Loss of Graph Neural Networks for Session-based Recommendation 3. Maximizing Cumulative User Engagement in Sequential Recommendation: An Online Optimization Perspective 【阿里】 论文:arxiv.org/pdf/2006.0452 RL for Recommendation1. Jointly Learning to Recommend and Advertise 【字节跳动】 论文:arxiv.org/abs/2003.0009 2. BLOB: A Probabilistic Model for Recommendation that Combines Organic and Bandit Signals 【Criteo】 3. Joint Policy-Value Learning for Recommendation 【Criteo】 论文:researchgate.net/public Multi-Task Learning1. Privileged Features Distillation at Taobao Recommendations 【阿里】 论文:arxiv.org/abs/1907.0517 Transfer Learning1. Learning Transferrable Parameters for Long-tailed Sequential User Behavior Modeling 【Salesforce】 2. Semi-supervised Collaborative Filtering by Text-enhanced Domain Adaptation 【阿里】 论文:arxiv.org/abs/2007.0708 AutoML for Recommendation1. Neural Input Search for Large Scale Recommendation Models 【Google】 论文:arxiv.org/abs/1907.0447 2. Towards Automated Neural Interaction Discovering for Click-Through Rate Prediction 【Facebook】 论文:arxiv.org/abs/2007.0643 Federated Learning1. FedFast: Going Beyond Average for Faster Training of Federated Recommender Systems Evaluation1. Counterfactual Evaluation of Slate Recommendations with Sequential Reward Interactions 【Netflix, Spotify】 论文:arxiv.org/abs/2007.1298 2. Evaluating Conversational Recommender Systems via User Simulation 论文:arxiv.org/abs/2006.0873 3. 【Best Paper Award】On Sampled Metrics for Item Recommendation 【Google】 4. On Sampling Top-K Recommendation Evaluation Debiasing1. Debiasing Grid-based Product Search in E-commerce 【Etsy】 论文:public.asu.edu/~rguo12/ 2. Counterfactual Evaluation of Slate Recommendations with Sequential Reward Interactions 【Netflix, Spotify】 论文:arxiv.org/abs/2007.1298 3. Attribute-based Propensity for Unbiased Learning in Recommender Systems: Algorithm and Case Studies 【Google】 论文:research.google/pubs/pu POI Recommendation1. Geography-Aware Sequential Location Recommendation 【Microsoft】 论文:staff.ustc.edu.cn/~lian Cold-Start Recommendation1. MAMO: Memory-Augmented Meta-Optimization for Cold-start Recommendation 论文:arxiv.org/abs/2007.0318 2. Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation 论文:https://ink.library.smu.edu.sg/cgi/... Others1. Improving Recommendation Quality in Google Drive 【Google】 论文:research.google/pubs/pu 2. Temporal-Contextual Recommendation in Real-Time 【Amazon】 论文:https://assets.amazon.science/96/71/... |
今日新闻 |
推荐新闻 |
CopyRight 2018-2019 办公设备维修网 版权所有 豫ICP备15022753号-3 |