Heterogeneous Task

Heterogeneous task learning addresses the challenge of training machine learning models on diverse and inconsistent datasets, encompassing various data types and task objectives simultaneously. Current research focuses on adapting existing architectures like transformers and Gaussian processes, and developing novel algorithms such as meta-learning and federated learning approaches, to effectively handle this heterogeneity, often incorporating techniques like dynamic task assignment and parameter sharing. This field is crucial for advancing AI applications in real-world scenarios, such as smart cities and healthcare, where data is inherently diverse and distributed, enabling more efficient and robust model training across multiple, often conflicting, objectives.

Papers

October 24, 2024

Meta-Learning with Heterogeneous Tasks
Zhaofeng Si, Shu Hu, Kaiyi Ji, Siwei Lyu
Meta Learning Heterogeneous Task

October 3, 2024

Unsupervised Meta-Learning via Dynamic Head and Heterogeneous Task Construction for Few-Shot Classification
Yunchuan Guan, Yu Liu, Ketong Liu, Ke Zhou, Zhiqi Shen
Shot Learning Meta Learning Shot Classification Heterogeneous Task

June 16, 2024

Exploring the Zero-Shot Capabilities of LLMs Handling Multiple Problems at once
Zhengxiang Wang, Jordan Kodner, Owen Rambow
Medical LLM Related Problem Problem Solving New Paradigm Mixed Task Multi Dimensional Evaluation LLM Capability Heterogeneous Task

June 4, 2024

Parameterizing Federated Continual Learning for Reproducible Research
Bart Cox, Jeroen Galjaard, Aditya Shankar, Jérémie Decouchant, Lydia Y. Chen
Continual LEArning Federated Continual Learning Reproducible Research Heterogeneous Task

February 18, 2024

Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources
Jiamu Bai, Daoyuan Chen, Bingchen Qian, Liuyi Yao, Yaliang Li
Fine Tuning Federated Learning LLM Fine Tuning Client Collaboration Heterogeneous Task Federated Tuning

October 13, 2023

Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks
Zixuan Ke, Bing Liu, Wenhan Xiong, Asli Celikyilmaz, Haoran Li
Continual LEArning Catastrophic Forgetting Knowledge Transfer Mixed Task Heterogeneous Task Soft Mask Sub Network

October 4, 2023

Sweeping Heterogeneity with Smart MoPs: Mixture of Prompts for LLM Task Adaptation
Chen Dun, Mirian Hipolito Garcia, Guoqing Zheng, Ahmed Hassan Awadallah, Anastasios Kyrillidis, Robert Sim
Mixture Component Complex Prompt Prompt Tuning Task Specification LLM Adaptation Cleaning Robot Heterogeneous Task Unknown Heterogeneity

August 29, 2023

Heterogeneous Multi-Task Gaussian Cox Processes
Feng Zhou, Quyu Kong, Zhijie Deng, Fengxiang He, Peng Cui, Jun Zhu
Gaussian Process Multi Output Gaussian Process Heterogeneous Task Gaussian Cox Process

May 11, 2023

Musketeer: Joint Training for Multi-task Vision Language Model with Task Explanation Prompts
Zhaoyang Zhang, Yantao Shen, Kunyu Shi, Zhaowei Cai, Jun Fang, Siqi Deng, Hao Yang, Davide Modolo, Zhuowen Tu, Stefano Soatto
Vision Language Model Joint Training Heterogeneous Task Prompt Generated Question

November 18, 2022

A Transformer Framework for Data Fusion and Multi-Task Learning in Smart Cities
Alexander C. DeRieux, Walid Saad, Wangda Zuo, Rachmawan Budiarto, Mochamad Donny Koerniawan, Dwi Novitasari
Transformer Based Multi Task Learning Information Fusion Smart City Transformer Based Framework Fusion Task Heterogeneous Task

September 5, 2022

Prototype-Aware Heterogeneous Task for Point Cloud Completion
Junshu Tang, Jiachen Xu, Jingyu Gong, Haichuan Song, Yuan Xie, Lizhuang Ma
Point Cloud Completion Partial Point Cloud Global Shape Heterogeneous Task

August 23, 2022

Asynchronous Execution of Heterogeneous Tasks in ML-driven HPC Workflows
Vincent R. Pascuzzi, Ozgur O. Kilic, Matteo Turilli, Shantenu Jha
High Performance Computing Heterogeneous Source Scientific Workflow Asynchronous Execution Heterogeneous Task

June 7, 2022

A Benchmark for Federated Hetero-Task Learning
Liuyi Yao, Dawei Gao, Zhen Wang, Yuexiang Xie, Weirui Kuang, Daoyuan Chen, Haohui Wang, Chenhe Dong, Bolin Ding, Yaliang Li
New Benchmark Multi Task Learning MAESTRO Dataset Heterogeneous Federated Learning Unobserved Heterogeneity Multi Task Benchmark Heterogeneous Task

February 25, 2022

Learning Multi-Task Gaussian Process Over Heterogeneous Input Domains
Haitao Liu, Kai Wu, Yew-Soon Ong, Chao Bian, Xiaomo Jiang, Xiaofang Wang
LeArning Abstract Gaussian Process Heterogeneous Domain Map Prior Stochastic Variational Inference Heterogeneous Task

December 10, 2021

PMFL: Partial Meta-Federated Learning for heterogeneous tasks and its applications on real-world medical records
Tianyi Zhang, Shirui Zhang, Ziwei Chen, Dianbo Liu
Financial Application Federated Learning Heterogeneous Data Patient Data Heterogeneous Clinical Federated Machine Learning Heterogeneous Task Federated Meta Learning