Hierarchical prompt learning for multi-task learning

Y Liu, Y Lu, H Liu, Y An, Z Xu, Z Yao… - Proceedings of the …, 2023 - openaccess.thecvf.com
Vision-language models (VLMs) can effectively transfer to various vision tasks via prompt
learning. Real-world scenarios often require adapting a model to multiple similar yet distinct …

Hypervolume maximization: A geometric view of pareto set learning

X Zhang, X Lin, B Xue, Y Chen… - Advances in Neural …, 2023 - proceedings.neurips.cc
This paper presents a novel approach to multiobjective algorithms aimed at modeling the
Pareto set using neural networks. Whereas previous methods mainly focused on identifying …

Multi-task learning with multi-query transformer for dense prediction

Y Xu, X Li, H Yuan, Y Yang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Previous multi-task dense prediction studies developed complex pipelines such as multi-
modal distillations in multiple stages or searching for task relational contexts for each task …

Multi-task graph neural architecture search with task-aware collaboration and curriculum

Y Qin, X Wang, Z Zhang, H Chen… - Advances in neural …, 2024 - proceedings.neurips.cc
Graph neural architecture search (GraphNAS) has shown great potential for automatically
designing graph neural architectures for graph related tasks. However, multi-task GraphNAS …

Multi-task learning with knowledge distillation for dense prediction

Y Xu, Y Yang, L Zhang - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
While multi-task learning (MTL) has become an attractive topic, its training usually poses
more difficulties than the single-task case. How to successfully apply knowledge distillation …

Efficient controllable multi-task architectures

A Aich, S Schulter… - Proceedings of the …, 2023 - openaccess.thecvf.com
We aim to train a multi-task model such that users can adjust the desired compute budget
and relative importance of task performances after deployment, without retraining. This …

Dynamic neural network for multi-task learning searching across diverse network topologies

W Choi, S Im - Proceedings of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
In this paper, we present a new MTL framework that searches for structures optimized for
multiple tasks with diverse graph topologies and shares features among tasks. We design a …

Tunable convolutions with parametric multi-loss optimization

M Maggioni, T Tanay, F Babiloni… - Proceedings of the …, 2023 - openaccess.thecvf.com
Behavior of neural networks is irremediably determined by the specific loss and data used
during training. However it is often desirable to tune the model at inference time based on …

Controllable Multi-Objective Re-ranking with Policy Hypernetworks

S Chen, Y Wang, Z Wen, Z Li, C Zhang… - Proceedings of the 29th …, 2023 - dl.acm.org
Multi-stage ranking pipelines have become widely used strategies in modern recommender
systems, where the final stage aims to return a ranked list of items that balances a number of …

Bi-Level Multiobjective Evolutionary Learning: A Case Study on Multitask Graph Neural Topology Search

C Wang, L Jiao, J Zhao, L Li, X Liu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
The construction of machine learning models involves many bi-level multiobjective
optimization problems (BL-MOPs), where upper-level (UL) candidate solutions must be …