Do We Really Need Message Passing in Brain Network Modeling?

Liang Yang, Yuwei Liu, Jiaming Zhuo, Di Jin, Chuan Wang, Zhen Wang, Xiaochun Cao
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70873-70887, 2025.

Abstract

Brain network analysis plays a critical role in brain disease prediction and diagnosis. Graph mining tools have made remarkable progress. Graph neural networks (GNNs) and Transformers, which rely on the message-passing scheme, recently dominated this field due to their powerful expressive ability on graph data. Unfortunately, by considering brain network construction using pairwise Pearson’s coefficients between any pairs of ROIs, model analysis and experimental verification reveal that the message-passing under both GNNs and Transformers can NOT be fully explored and exploited. Surprisingly, this paper observes the significant performance and efficiency enhancements of the Hadamard product compared to the matrix product, which is the matrix form of message passing, in processing the brain network. Inspired by this finding, a novel Brain Quadratic Network (BQN) is proposed by incorporating quadratic networks, which possess better universal approximation properties. Moreover, theoretical analysis demonstrates that BQN implicitly performs community detection along with representation learning. Extensive evaluations verify the superiority of the proposed BQN compared to the message-passing-based brain network modeling. Source code is available at https://github.com/LYWJUN/BQN-demo.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-yang25r, title = {Do We Really Need Message Passing in Brain Network Modeling?}, author = {Yang, Liang and Liu, Yuwei and Zhuo, Jiaming and Jin, Di and Wang, Chuan and Wang, Zhen and Cao, Xiaochun}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {70873--70887}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/yang25r/yang25r.pdf}, url = {https://proceedings.mlr.press/v267/yang25r.html}, abstract = {Brain network analysis plays a critical role in brain disease prediction and diagnosis. Graph mining tools have made remarkable progress. Graph neural networks (GNNs) and Transformers, which rely on the message-passing scheme, recently dominated this field due to their powerful expressive ability on graph data. Unfortunately, by considering brain network construction using pairwise Pearson’s coefficients between any pairs of ROIs, model analysis and experimental verification reveal that the message-passing under both GNNs and Transformers can NOT be fully explored and exploited. Surprisingly, this paper observes the significant performance and efficiency enhancements of the Hadamard product compared to the matrix product, which is the matrix form of message passing, in processing the brain network. Inspired by this finding, a novel Brain Quadratic Network (BQN) is proposed by incorporating quadratic networks, which possess better universal approximation properties. Moreover, theoretical analysis demonstrates that BQN implicitly performs community detection along with representation learning. Extensive evaluations verify the superiority of the proposed BQN compared to the message-passing-based brain network modeling. Source code is available at https://github.com/LYWJUN/BQN-demo.} }
Endnote
%0 Conference Paper %T Do We Really Need Message Passing in Brain Network Modeling? %A Liang Yang %A Yuwei Liu %A Jiaming Zhuo %A Di Jin %A Chuan Wang %A Zhen Wang %A Xiaochun Cao %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-yang25r %I PMLR %P 70873--70887 %U https://proceedings.mlr.press/v267/yang25r.html %V 267 %X Brain network analysis plays a critical role in brain disease prediction and diagnosis. Graph mining tools have made remarkable progress. Graph neural networks (GNNs) and Transformers, which rely on the message-passing scheme, recently dominated this field due to their powerful expressive ability on graph data. Unfortunately, by considering brain network construction using pairwise Pearson’s coefficients between any pairs of ROIs, model analysis and experimental verification reveal that the message-passing under both GNNs and Transformers can NOT be fully explored and exploited. Surprisingly, this paper observes the significant performance and efficiency enhancements of the Hadamard product compared to the matrix product, which is the matrix form of message passing, in processing the brain network. Inspired by this finding, a novel Brain Quadratic Network (BQN) is proposed by incorporating quadratic networks, which possess better universal approximation properties. Moreover, theoretical analysis demonstrates that BQN implicitly performs community detection along with representation learning. Extensive evaluations verify the superiority of the proposed BQN compared to the message-passing-based brain network modeling. Source code is available at https://github.com/LYWJUN/BQN-demo.
APA
Yang, L., Liu, Y., Zhuo, J., Jin, D., Wang, C., Wang, Z. & Cao, X.. (2025). Do We Really Need Message Passing in Brain Network Modeling?. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:70873-70887 Available from https://proceedings.mlr.press/v267/yang25r.html.

Related Material