Skip to content
AI News HubLIVE
Original source2 min read

GRASP: Gradient-Aligned Sequential Parameter Transfer for Memory-Efficient Multi-Source Learning

Summary

GRASP is a novel multi-source transfer learning method that achieves superior knowledge integration with constant O(1) memory through sequential processing, parameter-wise gradient alignment, and iterative fine-tuning, outperforming ensemble methods on continual learning benchmarks.

SourcearXiv Machine LearningAuthor: Mary Isabelle Wisell, Nicholas Jacobs, Aayush Manandhar, Salimeh Yasaei Sekeh
GRASP: Gradient-Aligned Sequential Parameter Transfer for Memory-Efficient Multi-Source Learning
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[2606.14900] GRASP: Gradient-Aligned Sequential Parameter Transfer for Memory-Efficient Multi-Source Learning

[Submitted on 12 Jun 2026]

Title:GRASP: Gradient-Aligned Sequential Parameter Transfer for Memory-Efficient Multi-Source Learning

View a PDF of the paper titled GRASP: Gradient-Aligned Sequential Parameter Transfer for Memory-Efficient Multi-Source Learning, by Mary Isabelle Wisell and 3 other authors

View PDF HTML (experimental)

Abstract:Multi-source transfer learning faces a fundamental scalability bottleneck: existing approaches require either loading all K source models into memory simultaneously during parameter fusion, requiring O(K) memory, or deploying all models at inference time, making production deployment infeasible. We propose GRASP (Gradient-Aligned Sequential Parameter Transfer), which achieves superior knowledge integration while maintaining O(1) memory consumption through three key innovations: (1) sequential processing that merges one source at a time into an evolving target model, (2) parameter-wise gradient alignment that selectively transfers only parameters whose optimization directions align with the target domain, avoiding negative transfer, and (3) iterative fine-tuning that adapts transferred knowledge before integrating the next source. Extensive experiments across three continual learning benchmarks (Yearbook, CLEAR-10, CLEAR-100) spanning 10 to 108-year temporal distribution shifts and four architectures (1.3M to 25.6M parameters) demonstrate that GRASP achieves 93.5% mean accuracy over all datasets and architectures compared to ensemble method's 71.7% accuracy while requiring only constant memory versus K models for standard multi-source fusion. Critically, GRASP's sequential previously merged models and scales to arbitrarily many sources without memory growth, making it uniquely suitable for resource-constrained deployment and continually evolving source domains.

Subjects:

Machine Learning (cs.LG)

Cite as: arXiv:2606.14900 [cs.LG]

(or arXiv:2606.14900v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2606.14900

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Mary Isabelle Wisell [view email] [v1] Fri, 12 Jun 2026 19:10:45 UTC (964 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled GRASP: Gradient-Aligned Sequential Parameter Transfer for Memory-Efficient Multi-Source Learning, by Mary Isabelle Wisell and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-06

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • GRASP processes one source model at a time, requiring constant memory and scaling to arbitrary numbers of sources.
  • Parameter-wise gradient alignment avoids negative transfer by transferring only parameters aligned with the target domain.
  • On three continual learning benchmarks, GRASP achieves 93.5% mean accuracy vs 71.7% for ensemble methods.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Models