UniBrain: A Unified Model for Cross-Subject Brain Decoding

2024-12-27

AI Summary

Existing cross-subject fMRI decoding methods suffer from limited generalizability due to substantial inter-subject variability, hindering the extraction of population-shared neural representations. To address this, we propose the first subject-agnostic unified decoding framework, explicitly modeling and disentangling subject-specific variability via three core components: a group-level signal extractor, a cross-subject mutual embedding module, and a dual-level (cross-subject and cross-modal) feature alignment mechanism. Our lightweight, parameter-efficient architecture achieves performance on par with state-of-the-art subject-specific models on standard benchmarks while reducing parameter count significantly. Furthermore, we introduce the first dedicated evaluation benchmark for cross-subject generalization. This work breaks the reliance on subject-specific customization, advancing universal brain decoding from “individualized modeling” toward “population-level commonality learning.”

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Brain decoding aims to reconstruct original stimuli from fMRI signals, providing insights into interpreting mental content. Current approaches rely heavily on subject-specific models due to the complex brain processing mechanisms and the variations in fMRI signals across individuals. Therefore, these methods greatly limit the generalization of models and fail to capture cross-subject commonalities. To address this, we present UniBrain, a unified brain decoding model that requires no subject-specific parameters. Our approach includes a group-based extractor to handle variable fMRI signal lengths, a mutual assistance embedder to capture cross-subject commonalities, and a bilevel feature alignment scheme for extracting subject-invariant features. We validate our UniBrain on the brain decoding benchmark, achieving comparable performance to current state-of-the-art subject-specific models with extremely fewer parameters. We also propose a generalization benchmark to encourage the community to emphasize cross-subject commonalities for more general brain decoding. Our code is available at https://github.com/xiaoyao3302/UniBrain.

Problem

• Brain Decoding
• Inter-subject Variability
• Common Feature Extraction

Innovation

• UniBrain
• Cross-disciplinary Brain Activity
• Two-step Feature Matching