aiqbench analysis
This paper introduces FoSTA, a novel framework for label-supervised manifold alignment that constructs task-aware intra-domain affinities to improve cross-domain correspondence in multimodal datasets. By leveraging shared class-semantic structures within supervised forest geometries, the method effectively addresses limitations in existing approaches regarding partial labeling and batch correction. The results demonstrate robust performance on both synthetic benchmarks and real-world applications like single-cell data integration, advancing the state of representation learning.
Forest-Guided Semantic Transport for Label-Supervised Manifold Alignment
arXiv:2602.00974v2 Announce Type: replace Abstract: Label-supervised manifold alignment bridges the gap between unsupervised and correspondence-based paradigms by leveraging shared label information to align multimodal datasets. However, existing methods either rely on label-independent intra-domain geometry or incorporate supervision primarily through the alignment objective, rather than directly constructing task-aware intra-domain affinities. To address this limitation, we introduce FoSTA (Forest-guided Semantic Transport Alignment), which learns supervised forest geometries independently within each domain and uses their shared class-semantic structure to infer cross-domain correspondences without predefined anchors. FoSTA extends RF-GAP affinities to partially labeled data and aligns the resulting semantic representations through scalable hierarchical transport. Extensive comparisons with established baselines demonstrate strong correspondence recovery and semantic structure preservation on synthetic and real-world benchmarks, including multimodal data integration and single-cell batch correction.
Abstract:Label-supervised manifold alignment bridges the gap between unsupervised and correspondence-based paradigms by leveraging shared label information to align multimodal datasets. However, existing methods either rely on label-independent intra-domain geometry or incorporate supervision primarily through the alignment objective, rather than directly constructing task-aware intra-domain affinities. To address this limitation, we introduce FoSTA (Forest-guided Semantic Transport Alignment), which learns supervised forest geometries independently within each domain and uses their shared class-semantic structure to infer cross-domain correspondences without predefined anchors. FoSTA extends RF-GAP affinities to partially labeled data and aligns the resulting semantic representations through scalable hierarchical transport. Extensive comparisons with established baselines demonstrate strong correspondence recovery and semantic structure preservation on synthetic and real-world benchmarks, including multimodal data integration and single-cell batch correction.
Machine Learning (cs.LG)
arXiv:2602.00974 [cs.LG]
(or arXiv:2602.00974v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2602.00974 Focus to learn more arXiv-issued DOI via DataCite
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.
Full text under the publisher's open licence · 213 words
Related coverage
J++ Lens: Jacobian Filtering Enables More Faithful Workspace Lenses
LessWrong · Oct 8, 2026
A Source Domain is All You Need: Source-Only Cross-OS Transfer Learning for APT Anomaly Detection via Semantic Alignment and Optimal Transport
arXiv · Jun 10, 2026
CMA-OT: Hierarchical Expert Supervision for Dance-to-Music Generation
arXiv · Sep 14, 2026
Momentum-Guided Semantic Forecasting (MoFore) for Self-Supervised Video Representation Learning
arXiv · Jun 16, 2026