机器学习
关注
分享
扫一扫
文章平均质量分 81
机器学习相关内容，包括深度学习、广告、RL、因果推断、GNN等
KpLn_HJL
新的一天从认识到自己有多菜开始
展开
专栏收录文章
- 默认排序
- 最新发布
- 最早发布
- 最多阅读
- 最少阅读
-
A Survey on Multi-Task Learning
21-ieee transaction原创 2023-01-29 15:13:34 · 680 阅读 · 0 评论 -
Multi-Agent Cooperative Bidding Games for Multi-Objective Optimization in e-Commercial Sponsored Sea
21-kdd-Multi-Agent Cooperative Bidding Games for Multi-Objective Optimization in e-Commercial Sponsored Search原创 2022-07-08 19:45:39 · 295 阅读 · 1 评论 -
Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability
17-icml-Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observabilityagent用的HDRQN，multi-agent实现通过同时存储agent的trajectory，multi-task实现通过学习一个distilled agent原创 2022-07-08 17:31:53 · 539 阅读 · 0 评论 -
We Know What YouWant: An Advertising Strategy Recommender System for Online Advertising
21-kdd-We Know What YouWant: An Advertising Strategy Recommender System for Online Advertising，粗糙的广告主采纳模型原创 2022-07-07 15:13:50 · 252 阅读 · 0 评论 -
graphSAGE/Inductive Representation Learning on Large Graphs
17-nips-graphSAGE/Inductive Representation Learning on Large Graphs原创 2022-06-13 12:01:38 · 297 阅读 · 0 评论 -
DRN: A Deep Reinforcement Learning Framework for News Recommendation
18-www-DRN: A Deep Reinforcement Learning Framework for News Recommendation用了dqn，reward里额外考虑了用户return原创 2022-04-29 10:17:11 · 295 阅读 · 0 评论 -
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
17-arxiv-MobileNets- Efficient Convolutional Neural Networks for Mobile Vision Applications通过拆解cnn的卷积核（用depth-wise和1x1的卷积核来代替原先卷积核），减小计算cost原创 2022-04-03 13:33:43 · 3272 阅读 · 0 评论 -
Exploring Simple Siamese Representation Learning
21-cvpr-Exploring Simple Siamese Representation Learning，证明siamese网络不需要负样本、大batch、momentum encoder也能有好性能原创 2022-01-11 14:21:27 · 220 阅读 · 1 评论 -
Learning to Embed Categorical Features without Embedding Tables for Recommendation
21-kdd-DHE/Learning to Embed Categorical Features without Embedding Tables for Recommendation原创 2022-01-07 14:58:26 · 842 阅读 · 0 评论 -
Recommending What Video to Watch Next: A Multitask Ranking System
19-recsys-Recommending What Video to Watch Next: A Multitask Ranking System原创 2022-01-04 22:29:06 · 242 阅读 · 0 评论 -
DEAR: Deep Reinforcement Learning for Online Advertising Impression in Recommender Systems
21-aaai-DEAR: Deep Reinforcement Learning for Online Advertising Impression in Recommender Systems原创 2022-01-04 15:19:45 · 889 阅读 · 0 评论 -
esmm/Entire Space Multi-Task Model- An Effective Approach for Estimating Post-Click Conversion Rate
18-sigir-ESMM/Entire Space Multi-Task Model- An Effective Approach for Estimating Post-Click Conversion Rate原创 2022-01-04 13:16:31 · 1568 阅读 · 1 评论 -
mmoe/Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts
18-kdd-mmoe/Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts原创 2021-12-31 11:24:41 · 527 阅读 · 0 评论 -
maddpg/Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
17-nips-maddpg/Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments原创 2021-12-30 19:06:00 · 1450 阅读 · 0 评论 -
a3c/Asynchronous Methods for Deep Reinforcement Learning
16-icml-a3c原创 2021-12-30 15:32:28 · 428 阅读 · 0 评论 -
ddpg/Continuous control with deep reinforcement learning
16-iclr-DDPG/Continuous control with deep reinforcement learning原创 2021-12-29 18:11:27 · 398 阅读 · 0 评论 -
RL简单梳理
rl基础梳理，q-learning，sarsa-lambda，actor-critic原创 2021-12-28 19:18:48 · 403 阅读 · 0 评论 -
SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval
20-sigir-SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval原创 2021-12-17 16:45:35 · 558 阅读 · 0 评论 -
GRN: Generative Rerank Network for Context-wise Recommendation
21-corr-GRN: Generative Rerank Network for Context-wise Recommendation，阿里原创 2021-12-17 11:35:40 · 841 阅读 · 0 评论 -
Revisit Recommender System in the Permutation Prospective
21-arxiv-Revisit Recommender System in the Permutation Prospective，阿里原创 2021-12-17 10:44:52 · 370 阅读 · 0 评论 -
Personalized Re-ranking for Recommendation
19-recsys-Personalized Re-ranking for Recommendation原创 2021-12-16 15:23:01 · 539 阅读 · 0 评论 -
Learning a Deep Listwise Context Model for Ranking Refinement
18-sigir-Learning a Deep Listwise Context Model for Ranking Refinement原创 2021-12-14 16:19:30 · 1414 阅读 · 0 评论 -
Learning to Collaborate: Multi-Scenario Ranking via Multi-Agent Reinforcement Learning
18-www-Learning to Collaborate: Multi-Scenario Ranking via Multi-Agent Reinforcement Learning原创 2021-12-09 16:19:17 · 261 阅读 · 0 评论 -
cs285-lec6-actor-critic
cs285, lec6, actor-critic原创 2021-10-20 22:10:17 · 205 阅读 · 0 评论 -
Debiased Explainable Pairwise Ranking from Implicit Feedback
recsys2021-Debiased Explainable Pairwise Ranking from Implicit Feedback原创 2021-10-18 14:01:37 · 331 阅读 · 0 评论 -
ads distribution bias/shift相关论文
A Feedback Shift Correction in Predicting Conversion Rates under Delayed FeedbackDetecting and Correcting for Label Shift with Black Box PredictorsAddressing Delayed Feedback for Continuous Training with Neural Networks in CTR prediction原创 2021-04-20 11:56:10 · 549 阅读 · 0 评论 -
Contrastive Learning初探
对比学习/contrastive learning相关较经典的paper阅读笔记原创 2021-04-13 10:43:52 · 381 阅读 · 0 评论 -
Disguise Adversarial Networks for Click-through Rate Prediction及其参考
原文的创新点有2个：用GAN做数据增强、在loss中引入互信息以减小cluster margin。相关的文献主要也是这两个方面原创 2021-04-07 13:52:53 · 258 阅读 · 0 评论 -
imbalanced data相关论文
各个领域imbalanced data相关论文，cv/nlp/其他原创 2021-03-31 17:29:35 · 439 阅读 · 0 评论 -
ctr相关论文笔记
ctr相关2015~2021年论文，包含：特征交叉相关原创 2021-03-22 18:51:32 · 472 阅读 · 0 评论 -
graph相关论文阅读笔记
包含graph embedding相关，gnn相关原创 2021-03-05 14:25:08 · 739 阅读 · 0 评论 -
论文阅读笔记
一些阅读过的论文笔记，ml/dl/ctr相关原创 2021-01-04 15:12:41 · 1415 阅读 · 0 评论