Awesome Multi-Task LearningA curated list of datasets, codebases, and papers on Multi-Task Learning (MTL), from a Machine Learning perspective.This project greatly appreciates the surveys below, which have been incredibly helpful.We welcome your contributions! If you find any mistakes or omissions...
半监督/自监督学习 | Semi/Self-Supervised Learning 对比学习 | Contrastive Learning 表示学习 | Representation Learning (Embedding) 度量学习 | Metric Learning 强化学习 | Reinforcement Learning 迁移学习 | Transfer Learning 元学习 | Meta-learning 多任务学习 | Multi-task Learning 不平衡/长尾学习 | Imbalan...
论文标题:Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning 论文标题:PaLI: A Jointly-Scaled Multilingual Language-Image Model 论文标题:Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation 论文标题:See, Plan, Predict: Language-guided Cognitive ...
CS330: Deep Multi-Task and Meta-Learning Homepage Rich Caruana's (terribly out-of-date) Home Page Massimiliano Pontil - UCL Jiayu Zhou | Machine Learning at Michigan State University Yu Zhang (张宇) - HKUST Tong Zhang (张潼)- Tencent AI Lab ...
CugLM (MLM + NSP + CLM): "Multi-task Learning based Pre-trained Language Model for Code Completion", 2020-12, ASE 2020, [paper] UniXcoder (MLM + NSP + CLM + Span Corruption + Contrastive Learning + Code2Text): "UniXcoder: Unified Cross-Modal Pre-training for Code Representation", 20...
Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems, (2019),Fei Mi, Minlie Huang, Jiyong Zhang, Boi Faltings.[pdf] MIND: Model Independent Neural Decoder, (2019),Yihan Jiang, Hyeji Kim, Himanshu Asnani, Sreeram Kannan.[pdf] ...
Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution Deep Burst Super-Resolution Learning the Non-Differentiable Optimization for Blind Super-Resolution Light Field Super-Resolution With Zero-Shot Learning ...
2. Deep Residual Learning for Weakly-Supervised Relation Extraction (Huang /EMNLP 2017) 本文从之前研究的一层CNN扩展到了更深的CNN网络(9层),使用的是在图像领域非常有效的ResNet。residual learning将低层和高层表示直接连接,还能解决deep networks的梯度消失问题。本文使用shortcut connection。每个block都是一个...
A Multi-task Selected Learning Approach for Solving 3D Bin Packing Problem. Arxiv, 2018. paper Duan, Lu and Hu, Haoyuan and Qian, Yu and Gong, Yu and Zhang, Xiaodong and Xu, Yinghui and Wei, Jiangwen. Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization Al...
Patel, Rama Chellappa .HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition .[J] arXiv preprint arXiv:1603.01249. Upal Mahbub, Vishal M. Patel, Deepak Chandra, Brandon Barbello, Rama Chellappa .Partial Face Detection ...