paper-with-me

Papers

Beyond Single-Source Cognitive Taskonomy:Multi-Source Task Relations through fMRI Transfer Learning

2026-06-24 · Junfeng Xia, Wendu Li, Mengjiao Zhang, Jie Guo arxiv

Cognitive tasks are organized by shared and specialized neural processes. Masked fMRI reconstruction provides a common self-supervised objective for quantifying transfer relations among task states, but existing reconstruction-based taskonomies mainly study one-to-one transfer from a single source task to a target. Here, we extend an fMRI cognitive taskonomy from single-source to multi-source transfer across 23 Human Connectome Project task states and use Boolean Integer Programming (BIP) to analyze budget-constrained task allocation. We train 1,127 task-specific and transfer models. Single-source transfer is directional and paradigm structured: motor states transfer well within the motor paradigm but provide limited support to most non-motor targets, consistent with a shared sensorimotor execution system and effector-specific representations. Multi-source transfer depends on the composition of the source set, suggesting that many-to-one task relations are not fully captured by pairwise taskonomy alone. Across supervision budgets, BIP repeatedly allocates direct supervision to several 0-back and 2-back working-memory states, although these states are not consistently the strongest individual sources. This pattern may reflect the integration of perceptual, attentional, and executive processes in working-memory tasks. Together, these findings reveal a cross-paradigm-limited motor cluster and working-memory states with high priority under the specified global allocation objective. Our study extends reconstruction-based fMRI taskonomy from one-to-one transfer to many-to-one task relations and budget-constrained task dependencies.

📄 PDF Abstract BibTeX arXiv:2606.26279

Code (0)

등록된 구현이 없습니다.

Tasks

Transfer Learning

Similar Papers 제목 키워드 기반

Uncovering cognitive taskonomy through transfer learning in masked autoencoder-based fMRI reconstruction

2024-05-24 · Youzhi Qu, Junfeng Xia, Xinyao Jian, Wendu Li 외

Data reconstruction is a widely used pre-training task to learn the generalized features for many downstream tasks. Although reconstruction tasks have been applied to neural signal completion and denoising, neural signal…

DenoisingTransfer Learning

CogTaskonomy: Cognitively Inspired Task Taxonomy Is Beneficial to Transfer Learning in NLP

2022-05-01 · ACL 2022 5 · Yifei Luo, Minghui Xu, Deyi Xiong

Is there a principle to guide transfer learning across tasks in natural language processing (NLP)? Taxonomy (Zamir et al., 2018) finds that a structure exists among visual tasks, as a principle underlying transfer learni…

SentenceTransfer Learning

Transfer learning to decode brain states reflecting the relationship between cognitive tasks

2022-06-07 · Youzhi Qu, Xinyao Jian, Wenxin Che, Penghui Du 외

Transfer learning improves the performance of the target task by leveraging the data of a specific source task: the closer the relationship between the source and the target tasks, the greater the performance improvement…

Transfer Learning

Multi-Task Meta Learning: learn how to adapt to unseen tasks

2022-10-13 · Richa Upadhyay, Prakash Chandra Chhipa, Ronald Phlypo, Rajkumar Saini 외

This work proposes Multi-task Meta Learning (MTML), integrating two learning paradigms Multi-Task Learning (MTL) and meta learning, to bring together the best of both worlds. In particular, it focuses simultaneous learni…

Depth EstimationEdge DetectionMeta-LearningMulti-Task Learning+2

Side-Tuning: A Baseline for Network Adaptation via Additive Side Networks

2019-12-31 · ECCV 2020 8 · Jeffrey O. Zhang, Alexander Sax, Amir Zamir, Leonidas Guibas 외

When training a neural network for a desired task, one may prefer to adapt a pre-trained network rather than starting from randomly initialized weights. Adaptation can be useful in cases when training data is scarce, whe…

Imitation LearningIncremental LearningQuestion AnsweringReinforcement Learning+2