Task Transferability Estimation

Follow this topic Ask about this topic

Task transferability estimation asks whether knowledge from a source model, dataset, task, or skill will improve performance on a target, helping choose what to reuse before expensive training or deployment. Methods compare frozen representations using embedding distances, CKA, or topological features; measure gradient or Fisher alignment; or learn rankers from task metadata and small transfer probes. Applications span vision and medical segmentation, cross-lingual NLP, and reinforcement learning, where estimates can route among models or skills, compose prior policies, or gate transfer against target-only baselines. Results show useful predictive signals, but rankings can change with target samples, metrics, architecture, and task type, while similarity may miss negative or directional transfer; reliable calibration and validation remain open challenges.

Latest papers

38 papers11 papers in the last four weeks, up 83% on the four weeks before. 0.1% of all new papers.

DISC: Domain-Integrated Similarity Cost for Time-Series Dataset
Oct 22, 2026Yen-Ku Liu, Hongjie Chen, Franck Dernoncourt +1Task Transferability Estimation Cross-Dataset Generalization
National Yang Ming Chiao Tung University · Dolby Laboratories · Adobe Research
Which Differences Matter? Controlled Tests of Rule Transfer, Joint Reliability, and Information Use in Decision Models
Oct 21, 2026Tianyou Lai, Wentao Yue, Zhiwei Zuo +1Rule-Based Classification Task Transferability Estimation
Carnegie Mellon University · Shenzhen University · Central China Normal University
Learning When to Transfer: Reinforcement Learning for Carbon-Footprint Modeling in New Manufacturing Domains
Oct 13, 2026Muhammad Umar Farooq, Daniel R. CooperTransfer Learning Cross-Domain Transfer Learning
Mechanical Engineering Department, University of Michigan, 2350 Hayward Street, Ann Arbor, 48109, MI, United States
Benchmarking Self-Supervised 3D Medical Vision Foundation Models and Transferability Estimation
Oct 13, 2026Jiaqi Tang, Yu Wang, Yang Liu +7Medical Imaging Foundation Models Medical Image Benchmarks
National Institution 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. +5
EvoCowork: A Benchmark for Real-World Office Tasks
Oct 10, 2026Zhou Liu, Xingyan Chen, ZhaoYang Han +6Computer-Use Agent Benchmarks AI Agent Benchmarks
Peking University · Sun Yat-sen University · Shanghai Jiao Tong University +3
From Transfer Probes to Expert Grouping: Evidence from LoRA Post-Training
Oct 10, 2026Xueyang WuLanguage Model Post-Training Mixture-of-Experts Models
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
How to Find and Reuse Policies for Continuous Adaptation in Lifelong Reinforcement Learning
Oct 2, 2026Saptarshi Nath, Inish M. D'Souza, Antonio Carta +2Continual RL Lifelong Learning Agents
Department of Computer Science Loughborough University · Department of Computer Science University of Pisa · Department of Computer Science
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
Language Distances are Practical for Equitable Cross-Lingual Transfer
Sep 26, 2026York Hay Ng, Razan Ahsan Rifandi, Aditya Khan +1Cross-Lingual Transfer Low-Resource Language Processing
University of Toronto, Canada · Ontario Tech University, Canada
When Does a Skill Add Value? Task-Conditional Gain Prediction for Selective Skill Use
Sep 26, 2026Anjie Xu, Zhiyu Zhang, Ruiqing Ding +2Task Transferability Estimation Conditional Average Treatment Effect Estimation
Key Lab of High Confidence Software Technologies (Peking University), Ministry of Education, China · School of Computer Science, Peking University, Beijing, China · Zhongguancun Academy, Beijing, China +4
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
A Shared Encoder Is Not a Shared Task: Conditional Comparison for Deep Expert Pools
Aug 21, 2026Kentaro OdaTask Transferability Estimation Mixture-of-Experts Models
Center for Management of Information Technologies, Kagoshima University
When do machine-learned exchange-correlation improvements inherit into density-functional tight binding?
Aug 14, 2026Can Polat, Mustafa Kurban, Erchin Serpedin +1Density Functional Theory Computational Materials Science
Department of Computer and Electrical Engineering, Texas A&M University, College Station, TX, USA · Department of Electrical and Computer Engineering, Texas A&M University at Qatar, Doha, Qatar · Department of Prosthetics and Orthotics, Ankara University, Ankara, Turkey +1
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 of Topological Invariants of Learned Representations
May 30, 2026Luciano MelodiaNeural Representation Geometry Task Transferability Estimation
Chair for Theoretical Computer Science Friedrich-Alexander Universität Erlangen-Nürnberg Martensstraße 3, 91058 Erlangen, Germany
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

Oct 22, 2026J/K move · Enter open · S save

DISC: Domain-Integrated Similarity Cost for Time-Series Dataset

Yen-Ku Liu, Hongjie Chen, Franck Dernoncourt, Ryan Rossi

National Yang Ming Chiao Tung University · Dolby Laboratories · Adobe Research

Task Transferability Estimation Cross-Dataset Generalization

Open paper AskPDF arXiv

The growth of time-series datasets and foundation models has made dataset comparison a central part of time-series workflows. Assessing source-target transfer before model adaptation requires similarity estimates that can summarize transfer-related dataset relationships without exhaustive source-target evaluation over every candidate pair. Many metrics have been proposed for measuring similarity between time-series datasets, but they capture different dataset relationships and vary in how well they align with downstream utility across tasks. We evaluate this gap by measuring the correlation between source-target similarity scores and downstream forecasting errors in out-of-distribution and transfer-learning settings. We propose Domain-Integrated Similarity Cost (DISC), a learnable aggregation framework that uses calibration transfer observations to select, weight, and combine similarity metrics for different downstream tasks. By integrating complementary metric values, DISC better distinguishes source-target dataset differences that matter for downstream behavior. After calibration, DISC scores source-target pairs using only their similarity-metric values and yields higher alignment than single-metric references on the reported split. These results show that time-series dataset similarity is task-dependent, and that learned metric integration provides a stronger proxy for downstream transfer behavior than manually selecting one similarity metric.