SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation

Jiayue Liu, Zhongchao Yi, Zhengyang Zhou, Qihe Huang, Kuo Yang, Xu Wang, Yang Wang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40069-40084, 2025.

Abstract

Discovering regularities from spatiotemporal systems can benefit various scientific and social planning. Current spatiotemporal learners usually train an independent model from a specific source data that leads to limited transferability among sources, where even correlated tasks requires new design and training. The key towards increasing cross-domain knowledge is to enable collective intelligence and model evolution. In this paper, inspired by neuroscience theories, we theoretically derive the increased information boundary via learning cross-domain collective intelligence and propose a Synaptic EVOlutional spatiotemporal network, SynEVO, where SynEVO breaks the model independence and enables cross-domain knowledge to be shared and aggregated. Specifically, we first re-order the sample groups to imitate the human curriculum learning, and devise two complementary learners, elastic common container and task-independent extractor to allow model growth and task-wise commonality and personality disentanglement. Then an adaptive dynamic coupler with a new difference metric determines whether the new sample group should be incorporated into common container to achieve model evolution under various domains. Experiments show that SynEVO improves the generalization capacity by at most 42% under cross-domain scenarios and SynEVO provides a paradigm of NeuroAI for knowledge transfer and adaptation. Code available at https://github.com/Rodger-Lau/SynEVO.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-liu25co, title = {{S}yn{EVO}: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation}, author = {Liu, Jiayue and Yi, Zhongchao and Zhou, Zhengyang and Huang, Qihe and Yang, Kuo and Wang, Xu and Wang, Yang}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {40069--40084}, 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/liu25co/liu25co.pdf}, url = {https://proceedings.mlr.press/v267/liu25co.html}, abstract = {Discovering regularities from spatiotemporal systems can benefit various scientific and social planning. Current spatiotemporal learners usually train an independent model from a specific source data that leads to limited transferability among sources, where even correlated tasks requires new design and training. The key towards increasing cross-domain knowledge is to enable collective intelligence and model evolution. In this paper, inspired by neuroscience theories, we theoretically derive the increased information boundary via learning cross-domain collective intelligence and propose a Synaptic EVOlutional spatiotemporal network, SynEVO, where SynEVO breaks the model independence and enables cross-domain knowledge to be shared and aggregated. Specifically, we first re-order the sample groups to imitate the human curriculum learning, and devise two complementary learners, elastic common container and task-independent extractor to allow model growth and task-wise commonality and personality disentanglement. Then an adaptive dynamic coupler with a new difference metric determines whether the new sample group should be incorporated into common container to achieve model evolution under various domains. Experiments show that SynEVO improves the generalization capacity by at most 42% under cross-domain scenarios and SynEVO provides a paradigm of NeuroAI for knowledge transfer and adaptation. Code available at https://github.com/Rodger-Lau/SynEVO.} }
Endnote
%0 Conference Paper %T SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation %A Jiayue Liu %A Zhongchao Yi %A Zhengyang Zhou %A Qihe Huang %A Kuo Yang %A Xu Wang %A Yang Wang %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-liu25co %I PMLR %P 40069--40084 %U https://proceedings.mlr.press/v267/liu25co.html %V 267 %X Discovering regularities from spatiotemporal systems can benefit various scientific and social planning. Current spatiotemporal learners usually train an independent model from a specific source data that leads to limited transferability among sources, where even correlated tasks requires new design and training. The key towards increasing cross-domain knowledge is to enable collective intelligence and model evolution. In this paper, inspired by neuroscience theories, we theoretically derive the increased information boundary via learning cross-domain collective intelligence and propose a Synaptic EVOlutional spatiotemporal network, SynEVO, where SynEVO breaks the model independence and enables cross-domain knowledge to be shared and aggregated. Specifically, we first re-order the sample groups to imitate the human curriculum learning, and devise two complementary learners, elastic common container and task-independent extractor to allow model growth and task-wise commonality and personality disentanglement. Then an adaptive dynamic coupler with a new difference metric determines whether the new sample group should be incorporated into common container to achieve model evolution under various domains. Experiments show that SynEVO improves the generalization capacity by at most 42% under cross-domain scenarios and SynEVO provides a paradigm of NeuroAI for knowledge transfer and adaptation. Code available at https://github.com/Rodger-Lau/SynEVO.
APA
Liu, J., Yi, Z., Zhou, Z., Huang, Q., Yang, K., Wang, X. & Wang, Y.. (2025). SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:40069-40084 Available from https://proceedings.mlr.press/v267/liu25co.html.

Related Material