paper-with-me

홈 › Papers

Learning Twofold Heterogeneous Multi-Task by Sharing Similar Convolution Kernel Pairs

2021-01-29 · Quan Feng, Songcan Chen

Heterogeneous multi-task learning (HMTL) is an important topic in multi-task learning (MTL). Most existing HMTL methods usually solve either scenario where all tasks reside in the same input (feature) space yet unnecessarily the consistent output (label) space or scenario where their input (feature) spaces are heterogeneous while the output (label) space is consistent. However, to the best of our knowledge, there is limited study on twofold heterogeneous MTL (THMTL) scenario where the input and the output spaces are both inconsistent or heterogeneous. In order to handle this complicated scenario, in this paper, we design a simple and effective multi-task adaptive learning (MTAL) network to learn multiple tasks in such THMTL setting. Specifically, we explore and utilize the inherent relationship between tasks for knowledge sharing from similar convolution kernels in individual layers of the MTAL network. Then in order to realize the sharing, we weightedly aggregate any pair of convolutional kernels with their similarity greater than some threshold $\rho$, consequently, our model effectively performs cross-task learning while suppresses the intra-redundancy of the entire network. Finally, we conduct end-to-end training. Our experimental results demonstrate the effectiveness of our method in comparison with the state-of-the-art counterparts.

📄 PDF Abstract BibTeX arXiv:2101.12431

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Task Learning

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs

2025-09-29 · Hao Ban, Kaiyi Ji arxiv

Large language models are often adapted using parameter-efficient techniques such as Low-Rank Adaptation (LoRA), formulated as $y = W_0x + BAx$, where $W_0$ is the pre-trained parameters and $x$ is the input to the adapt…

Multi-view Point Cloud Registration based on Evolutionary Multitasking with Bi-Channel Knowledge Sharing Mechanism

2022-05-06 · Yue Wu, Yibo Liu, Maoguo Gong, Peiran Gong 외

Multi-view point cloud registration is fundamental in 3D reconstruction. Since there are close connections between point clouds captured from different viewpoints, registration performance can be enhanced if these connec…

3D ReconstructionPoint Cloud Registration

Multi-Agent Learning with Heterogeneous Linear Contextual Bandits

2023-09-21 · NeurIPS 2023 11

As trained intelligent systems become increasingly pervasive, multiagent learning has emerged as a popular framework for studying complex interactions between autonomous agents. Yet, a formal understanding of how and whe…

Provably Efficient Multi-Task Reinforcement Learning with Model Transfer

2021-07-19 · NeurIPS 2021 12 · Chicheng Zhang, Zhi Wang

We study multi-task reinforcement learning (RL) in tabular episodic Markov decision processes (MDPs). We formulate a heterogeneous multi-player RL problem, in which a group of players concurrently face similar but not ne…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

ARCO-BO: Adaptive Resource-aware COllaborative Bayesian Optimization for Heterogeneous Multi-Agent Design

2025-10-18 · Zihan Wang, Yi-Ping Chen, Tuba Dolar, Wei Chen arxiv

Modern scientific and engineering design increasingly involves distributed optimization, where agents such as laboratories, simulations, or industrial partners pursue related goals under differing conditions. These agent…

Distributed Optimization