MultiDiffNet: A Multi-Objective Diffusion Framework for Generalizable Brain Decoding

Meng-Chun Zhang, Kateryna Shapovalenko, Yucheng Shao, Eddie Guo, Parusha Pradhan
Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026, PMLR 308:155-162, 2026.

Abstract

Neural decoding from electroencephalography (EEG) remains fundamentally limited by poor generalization to unseen subjects, driven by high inter-subject variability and the lack of large-scale datasets to model it effectively. Existing methods often rely on synthetic subject generation or simplistic data augmentation, but these strategies fail to scale or generalize reliably. We introduce MultiDiffNet, a diffusion-based framework that bypasses generative augmentation entirely by learning a compact latent space optimized for multiple objectives. We decode directly from this space and achieve state-of-the-art generalization across various neural decoding tasks using subject and session disjoint evaluation. We also curate and release a unified benchmark suite spanning four EEG decoding tasks of increasing complexity (SSVEP, Motor Imagery, P300, and Imagined Speech) and an evaluation protocol that addresses inconsistent split practices in prior EEG research. Finally, we develop a statistical reporting framework tailored for low-trial EEG settings. Our work provides a reproducible and open-source foundation for subject-agnostic EEG decoding in real-world BCI systems.

Cite this Paper

BibTeX
@InProceedings{pmlr-v308-zhang26a, title = {MultiDiffNet: A Multi-Objective Diffusion Framework for Generalizable Brain Decoding}, author = {Zhang, Meng-Chun and Shapovalenko, Kateryna and Shao, Yucheng and Guo, Eddie and Pradhan, Parusha}, booktitle = {Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026}, pages = {155--162}, year = {2026}, editor = {Abbasi-Asl, Reza and Iqbal, Asim and Ito, Shinya and Arkhipov, Anton and Sanborn, Sophia}, volume = {308}, series = {Proceedings of Machine Learning Research}, month = {27 Jan}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v308/main/assets/zhang26a/zhang26a.pdf}, url = {https://proceedings.mlr.press/v308/zhang26a.html}, abstract = {Neural decoding from electroencephalography (EEG) remains fundamentally limited by poor generalization to unseen subjects, driven by high inter-subject variability and the lack of large-scale datasets to model it effectively. Existing methods often rely on synthetic subject generation or simplistic data augmentation, but these strategies fail to scale or generalize reliably. We introduce MultiDiffNet, a diffusion-based framework that bypasses generative augmentation entirely by learning a compact latent space optimized for multiple objectives. We decode directly from this space and achieve state-of-the-art generalization across various neural decoding tasks using subject and session disjoint evaluation. We also curate and release a unified benchmark suite spanning four EEG decoding tasks of increasing complexity (SSVEP, Motor Imagery, P300, and Imagined Speech) and an evaluation protocol that addresses inconsistent split practices in prior EEG research. Finally, we develop a statistical reporting framework tailored for low-trial EEG settings. Our work provides a reproducible and open-source foundation for subject-agnostic EEG decoding in real-world BCI systems.} }
Endnote
%0 Conference Paper %T MultiDiffNet: A Multi-Objective Diffusion Framework for Generalizable Brain Decoding %A Meng-Chun Zhang %A Kateryna Shapovalenko %A Yucheng Shao %A Eddie Guo %A Parusha Pradhan %B Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026 %C Proceedings of Machine Learning Research %D 2026 %E Reza Abbasi-Asl %E Asim Iqbal %E Shinya Ito %E Anton Arkhipov %E Sophia Sanborn %F pmlr-v308-zhang26a %I PMLR %P 155--162 %U https://proceedings.mlr.press/v308/zhang26a.html %V 308 %X Neural decoding from electroencephalography (EEG) remains fundamentally limited by poor generalization to unseen subjects, driven by high inter-subject variability and the lack of large-scale datasets to model it effectively. Existing methods often rely on synthetic subject generation or simplistic data augmentation, but these strategies fail to scale or generalize reliably. We introduce MultiDiffNet, a diffusion-based framework that bypasses generative augmentation entirely by learning a compact latent space optimized for multiple objectives. We decode directly from this space and achieve state-of-the-art generalization across various neural decoding tasks using subject and session disjoint evaluation. We also curate and release a unified benchmark suite spanning four EEG decoding tasks of increasing complexity (SSVEP, Motor Imagery, P300, and Imagined Speech) and an evaluation protocol that addresses inconsistent split practices in prior EEG research. Finally, we develop a statistical reporting framework tailored for low-trial EEG settings. Our work provides a reproducible and open-source foundation for subject-agnostic EEG decoding in real-world BCI systems.
APA
Zhang, M., Shapovalenko, K., Shao, Y., Guo, E. & Pradhan, P.. (2026). MultiDiffNet: A Multi-Objective Diffusion Framework for Generalizable Brain Decoding. Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026, in Proceedings of Machine Learning Research 308:155-162 Available from https://proceedings.mlr.press/v308/zhang26a.html.

Related Material