awesome-multi-task-learning
github.com/thuml/awesome-multi-task-learning ↗A curated list of DATASETS, CODEBASES and PAPERS on Multi-Task Learning (MTL), from Machine Learning perspective.
838
GitHub Stars
220
Curated Resources
8
Categories
4 hours ago
Last Refreshed
SurveyBenchmark & DatasetCodebaseArchitectureOptimizationTask Relationship Learning: Grouping, Tree (Hierarchy) & CascadingTheoryMisc
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me distillation resources from awesome-multi-task-learning"
Installation instructions →What's inside
Misc
- 12-in-1: Multi-Task Vision and Language Representation Learning
- A Unified Perspective on Multi-Domain and Multi-Task Learning
- BAM! Born-Again Multi-Task Networks for Natural Language Understanding
- Federated Multi-Task Learning
- Modular Universal Reparameterization: Deep Multi-task Learning Across Diverse Domains
- MultiMAE: Multi-modal Multi-task Masked Autoencoders
Survey
- A Comparison of Loss Weighting Strategies for Multi task Learning in Deep Neural Networks
- An Overview of Multi-Task Learning in Deep Neural Networks
- A Survey on Multi-Task Learning
- Empirical Evaluation of Multi-task Learning in Deep Neural Networks for Natural Language Processing
- Multi-Task Learning for Dense Prediction Tasks: A Survey
- Multi-task learning for natural language processing in the 2020s: Where are we going?
Task Relationship Learning: Grouping, Tree (Hierarchy) & Cascading
- A Convex Formulation for Learning Task Relationships in Multi-Task Learning
- A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks
- A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks
- A Tree-Structured Multi-Task Model Recommender
- Attributes for Improved Attributes: A Multi-Task Network Utilizing Implicit and Explicit Relationships for Facial Attribute Classification
- Automated Search for Resource-Efficient Branched Multi-Task Networks
Optimization
- Actor-Mimic: Deep Multitask and Transfer Reinforcement LearningDistillation
- Adapting Auxiliary Losses Using Gradient SimilarityLoss & Gradient Strategy
- Adaptive Auxiliary Task Weighting for Reinforcement LearningLoss & Gradient Strategy
- Adversarial Multi-task Learning for Text ClassificationAdversarial Training
- A Modulation Module for Multi-task Learning with Applications in Image RetrievalTask Interference
- Attentive Single-Tasking of Multiple TasksAdversarial Training
Architecture
- AdapterFusion: Non-Destructive Task Composition for Transfer LearningModulation & Adapters
- AdapterHub: A Framework for Adapting TransformersModulation & Adapters
- AdaShare: Learning What To Share For Efficient Deep Multi-Task LearningModularity, MoE, Routing & NAS
- An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning SystemsModularity, MoE, Routing & NAS
- A Study of Residual Adapters for Multi-Domain Neural Machine TranslationModulation & Adapters
- Asymmetric Multi-task Learning based on Task Relatedness and ConfidenceOthers
Benchmark & Dataset
- BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask LearningComputer Vision
- Improving Multi-Scenario Learning to Rank in E-commerce by Exploiting Task Relationships in the Label SpaceRecommendation
- Indoor Segmentation and Support Inference from RGBD ImagesComputer Vision
- MTReclibRecommendation
- Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D ScansComputer Vision
- tasksource: Structured Dataset Preprocessing Annotations for Frictionless Extreme Multi-Task Learning and EvaluationNLP
Theory
- Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation
- Deciphering and Optimizing Multi-Task Learning: A Random Matrix Approach
- On the Theory of Transfer Learning: The Importance of Task Diversity
- Understanding and Improving Information Transfer in Multi-Task Learning
Showing a sample of 220 resources. View the full list on GitHub →