<![CDATA[chadlee]]>https://blog.csdn.net/yanguang1470zh-cnhttps://blog.csdn.net/<![CDATA[【视觉预训练】《BEIT: BERT Pre-Training of Image Transformers》 ICLR 2022]]>https://blog.csdn.net/yanguang1470/article/details/127119988https://blog.csdn.net/yanguang1470/article/details/127119988yanguang1470Fri, 30 Sep 2022 11:00:57 +0800<![CDATA[【多模态】MoE解决多模态单双塔问题 VLMo: Unifified Vision-Language Pre-Training with Mixture-of-Modality-Experts]]>https://blog.csdn.net/yanguang1470/article/details/126951450https://blog.csdn.net/yanguang1470/article/details/126951450yanguang1470Tue, 20 Sep 2022 13:45:38 +0800<![CDATA[【推荐系统中的Hash 3】Deep Hash：Learning to Embed Categorical Features without Embedding Tables KDD‘21]]>https://blog.csdn.net/yanguang1470/article/details/126457356https://blog.csdn.net/yanguang1470/article/details/126457356yanguang1470Sun, 21 Aug 2022 23:27:14 +0800<![CDATA[【推荐系统中的Hash 2】局部敏感哈希（利用冲突）]]>https://blog.csdn.net/yanguang1470/article/details/126457329https://blog.csdn.net/yanguang1470/article/details/126457329yanguang1470Sun, 21 Aug 2022 23:23:32 +0800<![CDATA[【推荐系统中的Hash 1】Hash Trick：原始数据—＞特征，尽可能避免冲突]]>https://blog.csdn.net/yanguang1470/article/details/126457306https://blog.csdn.net/yanguang1470/article/details/126457306yanguang1470Sun, 21 Aug 2022 23:21:52 +0800<![CDATA[【超长序列建模】美团CIKM‘22：《Sampling Is All You Need on Modeling Long-Term User Behaviors for CTR Prediction》]]>https://blog.csdn.net/yanguang1470/article/details/126331456https://blog.csdn.net/yanguang1470/article/details/126331456yanguang1470Sun, 14 Aug 2022 14:33:55 +0800<![CDATA[【超长序列建模】阿里ETA：《End-to-End User Behavior Retrieval in Click-Through Rate Prediction Model》]]>https://blog.csdn.net/yanguang1470/article/details/126331416https://blog.csdn.net/yanguang1470/article/details/126331416yanguang1470Sun, 14 Aug 2022 14:31:43 +0800<![CDATA[【冷启动】Transform Cold-Start Users into Warm via Fused Behaviors in Large-Scale Recommendation SIGIR‘22]]>https://blog.csdn.net/yanguang1470/article/details/126276376https://blog.csdn.net/yanguang1470/article/details/126276376yanguang1470Wed, 10 Aug 2022 23:20:35 +0800<![CDATA[【超长序列建模】万级别：SIM《Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click]]>https://blog.csdn.net/yanguang1470/article/details/126276355https://blog.csdn.net/yanguang1470/article/details/126276355yanguang1470Wed, 10 Aug 2022 23:18:35 +0800<![CDATA[【超长序列建模】千级别：MINM《Practice on Long Sequential User Behavior Modeling for Click-Through Rate Predictio]]>https://blog.csdn.net/yanguang1470/article/details/126276304https://blog.csdn.net/yanguang1470/article/details/126276304yanguang1470Wed, 10 Aug 2022 23:16:27 +0800<![CDATA[【冷启动】快手《POSO: Personalized Cold Start Modules for Large-scale Recommender Systems》]]>https://blog.csdn.net/yanguang1470/article/details/126112374https://blog.csdn.net/yanguang1470/article/details/126112374yanguang1470Mon, 01 Aug 2022 23:41:11 +0800<![CDATA[【多任务模型】腾讯MFH《Multi-Faceted Hierarchical Multi-Task Learning for a Large Number of Tasks]]>https://blog.csdn.net/yanguang1470/article/details/126112344https://blog.csdn.net/yanguang1470/article/details/126112344yanguang1470Mon, 01 Aug 2022 23:37:57 +0800<![CDATA[【多任务CTR】阿里ESMM：Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conve]]>https://blog.csdn.net/yanguang1470/article/details/126112323https://blog.csdn.net/yanguang1470/article/details/126112323yanguang1470Mon, 01 Aug 2022 23:34:30 +0800<![CDATA[【多任务优化】DWA、DTP、Gradnorm（CVPR 2019、ECCV 2018、 ICML 2018）]]>https://blog.csdn.net/yanguang1470/article/details/125985037https://blog.csdn.net/yanguang1470/article/details/125985037yanguang1470Mon, 25 Jul 2022 22:47:00 +0800<![CDATA[【多任务模型】Progressive Layered Extraction: A Novel Multi-Task Learning Model for Personalized（RecSys‘20）]]>https://blog.csdn.net/yanguang1470/article/details/125984986https://blog.csdn.net/yanguang1470/article/details/125984986yanguang1470Mon, 25 Jul 2022 22:44:31 +0800<![CDATA[【多任务学习】Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts KDD18]]>https://blog.csdn.net/yanguang1470/article/details/125984915https://blog.csdn.net/yanguang1470/article/details/125984915yanguang1470Mon, 25 Jul 2022 22:39:45 +0800<![CDATA[【RS采样】A Gain-Tuning Dynamic Negative Sampler for Recommendation (WWW 2022)]]>https://blog.csdn.net/yanguang1470/article/details/125903456https://blog.csdn.net/yanguang1470/article/details/125903456yanguang1470Thu, 21 Jul 2022 00:23:13 +0800<![CDATA[【GCN-RS】Learning Explicit User Interest Boundary for Recommendation (WWW‘22)]]>https://blog.csdn.net/yanguang1470/article/details/125903419https://blog.csdn.net/yanguang1470/article/details/125903419yanguang1470Thu, 21 Jul 2022 00:12:21 +0800<![CDATA[【GCN-RS】Region or Global? A Principle for Negative Sampling in Graph-based Recommendation (TKDE‘22)]]>https://blog.csdn.net/yanguang1470/article/details/125903162https://blog.csdn.net/yanguang1470/article/details/125903162yanguang1470Thu, 21 Jul 2022 00:10:55 +0800<![CDATA[【GCN-RS】MCL: Mixed-Centric Loss for Collaborative Filtering (WWW‘22)]]>https://blog.csdn.net/yanguang1470/article/details/125903380https://blog.csdn.net/yanguang1470/article/details/125903380yanguang1470Thu, 21 Jul 2022 00:10:03 +0800