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

TL;DR

SynEVO is a neuro-inspired framework that enhances cross-domain adaptation of spatiotemporal models by enabling collective learning and model evolution, significantly improving generalization across diverse sources.

Contribution

It introduces SynEVO, a novel neuro-inspired spatiotemporal network that facilitates knowledge sharing and model evolution across domains, inspired by neuroscience theories.

Findings

Improves cross-domain generalization by up to 42%.

Enables shared knowledge aggregation across diverse sources.

Provides a new paradigm for NeuroAI in transfer and adaptation.

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.