github.com/thuml/awesome-multi-task-learning Topics adapter machine-learning deep-neural-networks computer-vision deep-learning awesome-list transfer-learning multi-task-learning neural-language-processing multi-domain-learning loss-strategy multi-task-optimization multi-task-architecture Resources Readme ...
An up-to-date list of works on Multi-Task Learning - Awesome-Multi-Task-Learning/README.md at c2c2f752e9b202ffdd3b79a99a8abb9a7d92551a · WeiHongLee/Awesome-Multi-Task-Learning
Awesome Multitask Learning Resources. Contribute to mbs0221-mlsys/Multitask-Learning development by creating an account on GitHub.
GitHub is where people build software. More than 100 million people use GitHub to discover, fork, and contribute to over 420 million projects.
Collaborator Author haoawesome commented Aug 20, 2014 复旦李斌:最右说的应该就是vowpal wabbit中使用的feature hash方法,Ping Li每篇论文都会提到这个,Smola在ICML-09把这个方法用multitask learning,我也把这个方法用于graph控制特征维度。//@鲁东东胖: 有没有具体一点的描述啊 //@夏粉_百度: 在那次Adworkshop...
Activity recognition and machine learning [Activity recognition]|[Machine learning] NOTE:You can directly open the code inGihub Codespaceson the web to run them without downloading! Also, trygithub.dev. 0.Papers (论文) Awesome transfer learning papers (迁移学习文章汇总) ...
Awesome-Multi-Task-Perception Public Notifications Fork 0 Star 0 Code Issues Pull requests Actions Projects Security Insights fjchange/Awesome-Multi-Task-Perceptionmain 1 Branch 0 Tags Code Folders and filesLatest commit fjchange Update BEV.md ...
如果大家对大图数据上高效可扩展的 GNN 和基于图的隐私计算感兴趣,欢迎关注我的 Github,之后会不断更新相关的论文和代码的学习笔记。 https://github.com/XunKaiLi/Awesome-GNN-Researchgithub.com/XunKaiLi/Awesome-GNN-Researchgithub.com/XunKaiLi/Awesome-GNN-Researchgithub.com/XunKaiLi/Awesome-GNN-...
NOTE: You can directly open the code in Gihub Codespaces on the web to run them without downloading! Also, try github.dev.0.Papers (论文)Awesome transfer learning papers (迁移学习文章汇总)Paperweekly: A website to recommend and read paper notes Latest papers:...
Multi-Task Networks With Universe, Group, and Task Feature Learning 文章将任务区分为三个层次: 单个任务。 任务组(task group) 全体任务(task universe) 提出一些类MTL框架,包含并行网络结构、串行网络结构,在 ATIS, Snips和一个自有大数据集上表现良好。