Multi Task Learning

Multi-task learning (MTL) aims to improve model efficiency and generalization by training a single model to perform multiple related tasks simultaneously. Current research focuses on addressing challenges like task interference and optimization difficulties, exploring architectures such as Mixture-of-Experts (MoE), low-rank adaptors, and hierarchical models to enhance performance and efficiency across diverse tasks. MTL's significance lies in its potential to improve resource utilization and create more robust and adaptable AI systems, with applications spanning various fields including natural language processing, computer vision, and scientific modeling.

Papers

May 19, 2022

May 17, 2022

When to Use Multi-Task Learning vs Intermediate Fine-Tuning for Pre-Trained Encoder Transfer Learning
Orion Weller, Kevin Seppi, Matt Gardner
Natural Language Processing Multi Task Learning Pre Trained

May 12, 2022

Multi Task Learning For Zero Shot Performance Prediction of Multilingual Models
Kabir Ahuja, Shanu Kumar, Sandipan Dandapat, Monojit Choudhury
Language Model Zero Shot Multi Task Learning Multilingual Model Zero Shot Transfer Multilingual Transformer

May 8, 2022

Scheduled Multi-task Learning for Neural Chat Translation
Yunlong Liang, Fandong Meng, Jinan Xu, Yufeng Chen, Jie Zhou
Multi Task Learning Dialogue Task

May 6, 2022

Explaining the Effectiveness of Multi-Task Learning for Efficient Knowledge Extraction from Spine MRI Reports
Arijit Sehanobish, McCullen Sandora, Nabila Abraham, Jayashri Pawar, Danielle Torres, Anasuya Das, Murray Becker, Richard Herzog, Benjamin Odry, Ron Vianu
Multi Task Learning Knowledge Extraction Multi Task Model Spinal X Ray Radiology Report Datasets Multi Tasking Model

May 5, 2022

What is Right for Me is Not Yet Right for You: A Dataset for Grounding Relative Directions via Multi-Task Learning
Jae Hee Lee, Matthias Kerzel, Kyra Ahrens, Cornelius Weber, Stefan Wermter
Data Set Multi Task Learning Visual Question Answering Interpretable Direction Spatial Relation

April 30, 2022

FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings
Cheng-Te Li, Cheng Hsu, Yang Zhang
Multi Task Learning Sequential Recommendation Fairness Intervention Preference Representation Recommendation Fairness Fairness Aware Graph Fairness Aware Recommendation

April 29, 2022

Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time-Series Forecast
Jens Schreiber, Stephan Vogt, Bernhard Sick
Multi Task Learning Related Task Temporal Convolutional Network Renewable Energy Task Embeddings Solar Data

April 28, 2022

UniTE: Unified Translation Evaluation
Yu Wan, Dayiheng Liu, Baosong Yang, Haibo Zhang, Boxing Chen, Derek F. Wong, Lidia S. Chao
Machine Translation Multi Task Learning Translation Quality Unified Pre Training

April 27, 2022

SkillSpan: Hard and Soft Skill Extraction from English Job Postings
Mike Zhang, Kristian Nørgaard Jensen, Sif Dam Sonniks, Barbara Plank
Language Model Multi Task Learning Job Market Skill Extraction Implicit Target Span Non Cognitive Skill

April 26, 2022

Multi-task Learning for Concurrent Prediction of Thermal Comfort, Sensation, and Preference
Betty Lala, Hamada Rizk, Srikant Manas Kala, Aya Hagishima
Multi Task Learning Preference Feedback Joint predictioN Thermal Comfort

April 23, 2022

Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning
Vishakh Padmakumar, Leonard Lausen, Miguel Ballesteros, Sheng Zha, He He, George Karypis
Multi Task Learning Integral Role Task Transferability Multi Task Training Multi Task Representation

April 18, 2022

Multi-task Deep Neural Networks for Massive MIMO CSI Feedback
Boyuan Zhang, Haozhen Li, Xin Liang, Xinyu Gu, Lin Zhang
Multi Task Learning Multi Task Multiple Input Multiple Output Massive MIMO Feedback Network

April 16, 2022

Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners
Shashank Gupta, Subhabrata Mukherjee, Krishan Subudhi, Eduardo Gonzalez, Damien Jose, Ahmed H. Awadallah, Jianfeng Gao
Multi Task Learning Multi Task Mixture of Expert Sparse Network Multi Task Model

April 15, 2022

In-BoXBART: Get Instructions into Biomedical Multi-Task Learning
Mihir Parmar, Swaroop Mishra, Mirali Purohit, Man Luo, M. Hassan Murad, Chitta Baral
Multi Task Learning Multi Task Human Instruction Single Task Biomedical NLP Task

April 14, 2022

April 11, 2022

MIME: Adapting a Single Neural Network for Multi-task Inference with Memory-efficient Dynamic Pruning
Abhiroop Bhattacharjee, Yeshwanth Venkatesha, Abhishek Moitra, Priyadarshini Panda
Multi Task Learning Single Neural Network Energy Efficient Inference Random Access Memory Multi Task Inference

April 9, 2022

Efficient Extraction of Pathologies from C-Spine Radiology Reports using Multi-Task Learning
Arijit Sehanobish, Nathaniel Brown, Ishita Daga, Jayashri Pawar, Danielle Torres, Anasuya Das, Murray Becker, Richard Herzog, Benjamin Odry, Ron Vianu
Multi Task Learning NLP Field Multitask Learning Multi Task Model Spinal X Ray Pathological Feature Efficient Extraction

Multi Task Learning

Papers

Improving Multi-Task Generalization via Regularizing Spurious Correlation

Flexible Modeling and Multitask Learning using Differentiable Tree Ensembles

When to Use Multi-Task Learning vs Intermediate Fine-Tuning for Pre-Trained Encoder Transfer Learning

Multi Task Learning For Zero Shot Performance Prediction of Multilingual Models

Scheduled Multi-task Learning for Neural Chat Translation

Explaining the Effectiveness of Multi-Task Learning for Efficient Knowledge Extraction from Spine MRI Reports

What is Right for Me is Not Yet Right for You: A Dataset for Grounding Relative Directions via Multi-Task Learning

FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings

Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time-Series Forecast

UniTE: Unified Translation Evaluation

SkillSpan: Hard and Soft Skill Extraction from English Job Postings

Multi-task Learning for Concurrent Prediction of Thermal Comfort, Sensation, and Preference

Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning

Multi-task Deep Neural Networks for Massive MIMO CSI Feedback

Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners

In-BoXBART: Get Instructions into Biomedical Multi-Task Learning

A Unified Multi-task Learning Framework for Multi-goal Conversational Recommender Systems

Leveraging convergence behavior to balance conflicting tasks in multi-task learning

MIME: Adapting a Single Neural Network for Multi-task Inference with Memory-efficient Dynamic Pruning

Efficient Extraction of Pathologies from C-Spine Radiology Reports using Multi-Task Learning