Hydra: Towards Transferable Multi-Task Learning on Temporal Graphs

Kiarash Shamsi, Farimah Poursafaei, Tran Gia Bao Ngo, Reihaneh Rabbany, Baris Coskunuzer, Guillaume Rabusseau, Shenyang Huang, Cuneyt Gurcan Akcora

Keywords: Temporal graph learning, Transfer learning, Multi-Task Learning, Graph neural networks, Temporal multi-network learning

TL;DR: We present Hydra, the first multi-task temporal graph model that integrates spatial and spectral learning to transfer across unseen networks without fine-tuning. Hydra outperforms task-specific baselines in both classification and regression.

Abstract: Real-world evolving networks are naturally modeled as temporal graphs (TGs), where capturing temporal dynamics is essential for predicting future graph properties that support downstream decision-making. Existing temporal graph methods have been developed primarily for single-task prediction, and little is known about their generalization across tasks or transfer to unseen networks. This leaves the challenge of multi-task graph property prediction in TGs largely open. We address this challenge by introducing Hydra, a novel architecture that integrates local connectivity features from temporal GNNs with a spectral learning module that captures global connectivity patterns. This design enables joint learning of local and global information under a multi-task objective. In multi-task classification, Hydra achieves an 8.9\% relative gain in AUC over the strongest competitor. In multi-task regression, Hydra achieves competitive results in all three tasks, while obtaining the best results in two tasks with a 8.2\% relative gain in MAE compared to the strongest baseline. Moreover, Hydra delivers these gains with a 22× reduction in training time compared to temporal transfer models. These results provide the first systematic evidence that multi-task transferable learning on temporal graphs is effective. By delivering consistent top-ranked performance, Hydra highlights multi-task training on temporal graphs as a promising direction toward adaptable foundation models for temporal graphs.

Primary Area: learning on graphs and other geometries & topologies

Submission Number: 11525