Task Transferability Estimation

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, against 1 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 20

All topics

Edge Accuracy Is Not Enough: Why Dynamics-Learned Structure Fails to Transfer to Inverse Problems
Oct 7, 2026Nicholas Tan Jerome, Fangnian WangInverse Problems Graph Structure Learning
Institute for Data Processing and Electronics (IPE) Karlsruhe Institute of Technology (KIT) Karlsruhe, Germany · Institute for Thermal Energy Technology and Safety (ITES) Karlsruhe Institute of Technology (KIT) Karlsruhe, Germany
Zero-Compute Cross-Lingual Transferability Estimation Using Typological Feature Proxies
Sep 30, 2026Dalton Raphael Harmsen, Swier Garst, Thomas van Osch +2Task Transferability Estimation Linguistic Typology
AMOR/e Lab, Eindhoven University of Technology, Eindhoven, The Netherlands · SURF, Amsterdam, The Netherlands
AssayRouter: Historical Utility Priors for Frozen Molecular Predictor Routing
Sep 29, 2026Dong Xu, Zhangfan Yang, Jiantao Wu +5Adaptive Model Routing Task Transferability Estimation
School of Artificial Intelligence, Shenzhen University · EasternDawn · School of Computer Science, University of Nottingham Ningbo
Evo2Team: When Do Evolved Skills Transfer? From Selection to Deployment
Sep 28, 2026Renxiang Wang, Jiaming CuiMulti-Agent Coordination Task Transferability Estimation
Virginia Tech, Blacksburg, VA
From Regional to Global: Transfer Learning for Atmospheric Transport Emulators
Sep 20, 2026Jeff Clark, Elena Fillola, Nawid Keshtmand +2Surrogate Modeling Task Transferability Estimation
School of Engineering Mathematics and Technology, University of Bristol, UK · School of Chemistry, University of Bristol, UK
Structuring occupational accident narratives for cross-sector safety analysis: Transferability of accident-process role classification
Sep 18, 2026Aho Yapi, Pierre Latouche, Arnaud Guillin +1Document Information Extraction Task Transferability Estimation
Laboratoire de Mathématiques Blaise Pascal (UMR 6620 CNRS), Université Clermont Auvergne, 3, Place Vasarely, Aubière, 63178, France · LYF SAS, Cikaba, 4 rue Eric de Cromières, Clermont-Ferrand, 63000, France · Institut Universitaire de France (IUF), Paris, France
EconSkills: Studying Skill Transfer and Retrieval for Web Agents on Live Economic Data
Sep 17, 2026Yinzhu Quan, Zefang LiuTask Transferability Estimation LLM Agent Skill Learning
Georgia Institute of Technology Atlanta, GA, USA · Capital One San Jose, CA, USA
BrainTaskonomy: Learning How to Pretrain and What to Transfer in fMRI Foundation Models
Sep 9, 2026Junfeng Xia, Wenhao Ye, Junxiang Zhang +3Medical Imaging Foundation Models fMRI Foundation Models
Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen, China · Department of Computer Science, University of Warwick, The UK · Omni-Intelligence, Shenzhen, China +1
Quantifying geographic domain shift to decouple the geospatial transferability of human mobility flow generation models
Aug 21, 2026Zhiyong Zhou, Song Gao, Qianheng Zhang +2Spatial Generalization Task Transferability Estimation
GeoDS Lab, Department of Geography, University of Wisconsin-Madison, Madison, WI, USA · School of Earth Sciences & Zhejiang Key Laboratory of Geographic Information Science, Zhejiang University, Hangzhou, China
Robustness of transferability estimation metrics for medical imaging
Aug 7, 2026Niclas Claßen, Théo Sourget, Dovile Juodelyte +2Medical Image Analysis Task Transferability Estimation
IT University of Copenhagen, Denmark
Domain Shift in Echocardiography: Interpretable Quantification and Prediction of Cross-Dataset Left Ventricular Segmentation
Jul 22, 2026Soroush Elyasi, Nasim Dadashi Serej, Julie Wall +1Ultrasound Image Segmentation Distribution Shift
THRIVE Centre, School of Computing and Engineering, University of West London, London, UK · School of Computing and Engineering, University of West London, London, UK
Topology-Driven Transferability Estimation for 3D Medical Vision Foundation Models
Jul 5, 2026Jiaqi Tang, Shaoyang Zhang, Fandong Zhang +3Medical Imaging Foundation Models 3D Medical Imaging
National Institute of Health Data Science, Peking University, Beijing, China · Institute of Medical Technology, Peking University, Beijing, China · State Key Laboratory of General Artificial Intelligence, Peking University, Beijing, China +2
Unveiling Transferability in Trajectory Prediction via Latent Scene Embeddings
Jun 29, 2026Theodor Westny, David Axelsson, Björn Olofsson +1Representational Similarity Analysis Multi-Agent Trajectory Prediction
Division of Vehicular Systems, Linköping University, Linköping, Sweden · Department of Automatic Control, Lund University, Lund, Sweden
The Geometry of Updates: Fisher Alignment at Vocabulary Scale
Jun 25, 2026John SweeneyTask Transferability Estimation Transfer Learning
Sideplane AI
Beyond Single-Source Cognitive Taskonomy:Multi-Source Task Relations through fMRI Transfer Learning
Jun 24, 2026Junfeng Xia, Wendu Li, Mengjiao Zhang +1Task Transferability Estimation Cross-Domain Transfer Learning
Department of Biomedical Engineering, Southern University of Science and Technology Shenzhen, China
The Cross-Architecture Substrate: A Domain-Transcendent, Calibration-Surviving Geometric Invariant of Modern Vision Encoders
Jun 5, 2026Yousef RadwanTask Transferability Estimation Cross-Domain Transfer Learning
KAUST
Learning Transfers: Kan Extensions for Neural Invariants
May 30, 2026Luciano MelodiaNeural Representation Geometry Task Transferability Estimation
Friedrich-Alexander Universität Erlangen-Nürnberg
LWM-CDE: A Representation Space for Wireless Data Reasoning and Transferability
May 22, 2026Sadjad Alikhani, Akshay Malhotra, Shahab Hamidi-Rad +1Contrastive Learning Representational Similarity Analysis
School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ 85281 USA · InterDigital, Inc., USA
RADAR: Relative Angular Divergence Across Representations
May 21, 2026Xavier Cadet, Mateusz Nowak, Peter ChinRepresentation Geometry Task Transferability Estimation
Dartmouth College
Model Specific Task Similarity for Vision Language Model Selection via Layer Conductance
Feb 1, 2026Wei Yang, Hong Xie, Tao Tan +3VLM Evaluation Vision-Language Models
School of AI and Data Science USTC

Oct 7, 2026, cs.LGJ/K move · Enter open · S save

Edge Accuracy Is Not Enough: Why Dynamics-Learned Structure Fails to Transfer to Inverse Problems

Nicholas Tan Jerome, Fangnian Wang

Institute for Data Processing and Electronics (IPE) Karlsruhe Institute of Technology (KIT) Karlsruhe, Germany · Institute for Thermal Energy Technology and Safety (ITES) Karlsruhe Institute of Technology (KIT) Karlsruhe, Germany

Inverse Problems Graph Structure Learning Task Transferability Estimation

Open paper AskPDF arXiv

A natural strategy for inverse problems with scarce labelled data is to transfer relational structure learned from abundant forward-simulation data. We show this strategy fails systematically, even when it satisfies the standard theoretical justification for why structure should help. We prove that approximate structure provides estimation-error benefits whenever the edge error satisfies

Δ< n^2 - kn

, reducing sample complexity from

O(n^2)

O(kn+Δ)

. Structure learned via Neural Relational Inference (NRI) from dynamics prediction satisfies this condition, yet on a source-localisation task across 180 CFD-simulated hydrogen-leak scenarios and 180 acoustic scenarios, it degrades performance by 116% and 201% relative to a flexible, task-optimised attention baseline, while a physics-based prior (Green's function) degrades by only 69-72%. Four independent lines of evidence show this is not a tuning failure: NRI improves only 0.5% when given 18x more training data (versus 16.6% for the task-optimised baseline,

p<0.001

); performance is insensitive to the NRI edge threshold across a wide range; the dynamics-learned graph overlaps the task-optimal graph on only 6% of edges; and two further dynamics-derived structure estimators (correlation- and mutual-information-based) show no measurable benefit over a structure-free baseline, with the correlation-based estimator performing markedly worse. We formalise this gap as a statement about approximation error that the edge-accuracy condition cannot control, and we provide a lightweight transferability test (Jaccard similarity against a partially-observed target-task graph) that separates successful from failed transfer in all four domain/structure pairs we evaluate, using under an hour of computation and 15-20% of target-domain data; we present this as a heuristic calibrated on few cases, not a validated general threshold.

Momentum

Related topics

Latest papers 20