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

July 8, 2022

GCN-based Multi-task Representation Learning for Anomaly Detection in Attributed Networks
Venus Haghighi, Behnaz Soltani, Adnan Mahmood, Quan Z. Sheng, Jian Yang
Anomaly Detection Multi Task Learning Community Detection Based Anomaly Detection Multi View Representation Learning Multi Task Representation Attributed Network

July 6, 2022

Knowing Earlier what Right Means to You: A Comprehensive VQA Dataset for Grounding Relative Directions via Multi-Task Learning
Kyra Ahrens, Matthias Kerzel, Jae Hee Lee, Cornelius Weber, Stefan Wermter
Multi Task Learning Visual Question Answering Spatial Reasoning Interpretable Direction Medical Visual Question Answering

July 3, 2022

ABAW: Learning from Synthetic Data & Multi-Task Learning Challenges
Dimitrios Kollias
Synthetic Data Multi Task Learning Expression Classification Valence Arousal Estimation Action Unit Detection ABAW Challenge

July 2, 2022

Speech Emotion: Investigating Model Representations, Multi-Task Learning and Knowledge Distillation
Vikramjit Mitra, Hsiang-Yun Sherry Chien, Vasudha Kowtha, Joseph Yitan Cheng, Erdrin Azemi
Knowledge Distillation Multi Task Learning Pre Trained Speech Model Speech Emotion Valence Prediction Model Representation Emotion Estimation Dimensional Emotion Recognition

June 28, 2022

Personalized Keyword Spotting through Multi-task Learning
Seunghan Yang, Byeonggeun Kim, Inseop Chung, Simyung Chang
Multi Task Learning Speaker Verification Keyword Spotting

June 24, 2022

Burst2Vec: An Adversarial Multi-Task Approach for Predicting Emotion, Age, and Origin from Vocal Bursts
Atijit Anuchitanukul, Lucia Specia
Multi Task Learning Multi Task Speech Based Age Emotion Prediction Vocal Burst

June 22, 2022

Multi-task twin support vector machine with Universum data
Hossein Moosaei, Fatemeh Bazikar, Milan Hladík
Multi Task Learning Multi Task MAESTRO Dataset Support Vector Machine Multi Task Learning Framework Learning Task

June 21, 2022

Semantics-Depth-Symbiosis: Deeply Coupled Semi-Supervised Learning of Semantics and Depth
Nitin Bansal, Pan Ji, Junsong Yuan, Yi Xu
Semantic Segmentation Semi Supervised Learning Multi Task Learning Large Depth Attention Module Semantics Surfaced Cross Channel Attention

June 19, 2022

Learning Multi-Task Transferable Rewards via Variational Inverse Reinforcement Learning
Se-Wook Yoo, Seung-Woo Seo
LeArning Abstract Multi Task Learning Reward Function Variational Empowerment

June 17, 2022

DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learning
Ivan Lopes, Tuan-Hung Vu, Raoul de Charette
Semantic Segmentation Multi Task Learning Multi Task Model Multi Task Dense Prediction Attention Based Correlation Module Cross Task Attention

June 16, 2022

Learning to Teach Fairness-aware Deep Multi-task Learning
Arjun Roy, Eirini Ntoutsi
LeArning Abstract Multi Task Learning Fairness Accuracy Fairness Aware Learning Pf Agp

June 8, 2022

Learning to Generate Prompts for Dialogue Generation through Reinforcement Learning
Hsuan Su, Pohan Chi, Shih-Cheng Huang, Chung Ho Lam, Saurav Sahay, Shang-Tse Chen, Hung-yi Lee
Language Model Reinforcement Learning LeArning Abstract Multi Task Learning Complex Prompt Dialogue Generation Prompt Based Learning Dialogue Model

June 7, 2022

June 1, 2022

RMT-Net: Reject-aware Multi-Task Network for Modeling Missing-not-at-random Data in Financial Credit Scoring
Qiang Liu, Yingtao Luo, Shu Wu, Zhen Zhang, Xiangnan Yue, Hong Jin, Liang Wang
Multi Task Learning Multi Task Classification Task Biased Datasets ATAC Net Credit Scoring Missingness Pattern

May 31, 2022

Compressed Hierarchical Representations for Multi-Task Learning and Task Clustering
João Machado de Freitas, Sebastian Berg, Bernhard C. Geiger, Manfred Mücke
Multi Task Learning Compressed Representation Task Agnostic Representation Task Representation Task Specific Representation Task Clustering

May 28, 2022

May 22, 2022

All Birds with One Stone: Multi-task Text Classification for Efficient Inference with One Forward Pass
Jiaxin Huang, Tianqi Liu, Jialu Liu, Adam D. Lelkes, Cong Yu, Jiawei Han
Multi Task Learning Efficient Inference Bird Specie Forward Pas STONE Deterioration Pattern Multi Task Transformer N Task

May 20, 2022

DELATOR: Money Laundering Detection via Multi-Task Learning on Large Transaction Graphs
Henrique S. Assumpção, Fabrício Souza, Leandro Lacerda Campos, Vinícius T. de Castro Pires, Paulo M. Laurentys de Almeida, Fabricio Murai
Multi Task Learning Money Laundering Transaction Graph

Multi Task Learning

Papers

GCN-based Multi-task Representation Learning for Anomaly Detection in Attributed Networks

Knowing Earlier what Right Means to You: A Comprehensive VQA Dataset for Grounding Relative Directions via Multi-Task Learning

ABAW: Learning from Synthetic Data & Multi-Task Learning Challenges

Speech Emotion: Investigating Model Representations, Multi-Task Learning and Knowledge Distillation

Personalized Keyword Spotting through Multi-task Learning

Burst2Vec: An Adversarial Multi-Task Approach for Predicting Emotion, Age, and Origin from Vocal Bursts

Multi-task twin support vector machine with Universum data

Semantics-Depth-Symbiosis: Deeply Coupled Semi-Supervised Learning of Semantics and Depth

Learning Multi-Task Transferable Rewards via Variational Inverse Reinforcement Learning

DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learning

Learning to Teach Fairness-aware Deep Multi-task Learning

Learning to Generate Prompts for Dialogue Generation through Reinforcement Learning

A Benchmark for Federated Hetero-Task Learning

Quantitative Stock Investment by Routing Uncertainty-Aware Trading Experts: A Multi-Task Learning Approach

RMT-Net: Reject-aware Multi-Task Network for Modeling Missing-not-at-random Data in Financial Credit Scoring

Compressed Hierarchical Representations for Multi-Task Learning and Task Clustering

Multi-Task Learning with Multi-Query Transformer for Dense Prediction

Automatic Expert Selection for Multi-Scenario and Multi-Task Search

All Birds with One Stone: Multi-task Text Classification for Efficient Inference with One Forward Pass

DELATOR: Money Laundering Detection via Multi-Task Learning on Large Transaction Graphs