SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 52 references that are in the map. First posted on arXiv 21 May 2025.
Builds on
22 of 52 references.
References · 22
- 2020Supervised Contrastive Learningcited by 2,829
- 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
- 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
- 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
- 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 530
- 2016Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Predictioncited by 333
- 2021Spatial-Temporal Graph ODE Networks for Traffic Flow Forecastingcited by 210
- 2020Spatial-Temporal Transformer Networks for Traffic Flow Forecastingcited by 180
- 2023LargeST: A Benchmark Dataset for Large-Scale Traffic Forecastingcited by 118
- 2022Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning Systemcited by 112
- 2024TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignmentcited by 103
- 2024UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Predictioncited by 87
10 more
- 2024Spatial-Temporal Large Language Model for Traffic Predictioncited by 83
- 2023Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatmentcited by 47
- 2022CoSCL: Cooperation of Small Continual Learners is Stronger than a Big Onecited by 43
- 2023Incorporating Neuro-Inspired Adaptability for Continual Learning in Artificial Intelligencecited by 43
- 2021TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learningcited by 42
- 2020RiskOracle: A Minute-level Citywide Traffic Accident Forecasting Frameworkcited by 33
- 2023Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalizationcited by 26
- 2025Efficient Multivariate Time Series Forecasting via Calibrated Language Models with Privileged Knowledge Distillationcited by 20
- 2024Spatio-Temporal Field Neural Networks for Air Quality Inferencecited by 12
- 2024Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Frameworkcited by 9
Built on by
Citing papers per year: 2026: 1.
1 paper.