Hu, J., Liu, X., Fan, Z., Yin, Y., Xiang, S., Ramasamy, S., & Zimmermann, R. (2024). Prompt-Based Spatio-Temporal Graph Transfer Learning. In (Editor), Proceedings of the 33rd ACM International Conference on Information and Knowledge Management. https://doi.org/10.1145/3627673.3679554
Abstract:
Spatio-temporal graph neural networks have proven efficacy in capturing complex dependencies for urban computing tasks such as forecasting and kriging. Yet, their performance is constrained by the reliance on extensive data for training on a specific task, thereby limiting their adaptability to new urban domains with varied task demands. Although transfer learning has been proposed to remedy this problem by leveraging knowledge across domains, the cross-task generalization still remains under-explored in spatio-temporal graph transfer learning due to the lack of a unified framework. To bridge the gap, we propose Spatio-Temporal Graph Prompting (STGP), a prompt-based framework capable of adapting to multi-diverse tasks in a data-scarce domain. Specifically, we first unify different tasks into a single template and introduce a task-agnostic network architecture that aligns with this template. This approach enables capturing dependencies shared across tasks. Furthermore, we employ learnable prompts to achieve domain and task transfer in a two-stage prompting pipeline, facilitating the prompts to effectively capture domain knowledge and task-specific properties. Our extensive experiments demonstrate that STGP outperforms state-of-the-art baselines in three tasks-forecasting, kriging, and extrapolation-achieving an improvement of up to 10.7%.
License type:
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Funding Info:
This research / project is supported by the National Research Foundation - DesCARTES, Campus for Research Excellence and Technological Enterprise (CREATE) programme
Grant Reference no. : DesCARTES
This research / project is supported by the Ministry of Education - Academic Research Fund Tier 2
Grant Reference no. : T2EP20221-002