Todyformer: Towards Holistic Dynamic Graph Transformers with Structure-Aware Tokenization

Mahdi Biparva, Raika Karimi, Faezeh Faez, Yingxue Zhang

Keywords: graph representation learning, graph transformers

TL;DR: Towards Holistic Dynamic Graph Transformers with Structure-Aware Tokenization

Abstract: Temporal Graph Neural Networks have garnered substantial attention for their capacity to model evolving structural and temporal patterns while exhibiting impressive performance. However, it is known that these architectures are encumbered by issues that constrain their performance, such as over-squashing and over-smoothing. Meanwhile, Transformers have demonstrated exceptional computational capacity to effectively address challenges related to long-range dependencies. Consequently, we introduce Todyformer—a novel Transformer-based neural network tailored for dynamic graphs. It unifies the local encoding capacity of Message-Passing Neural Networks (MPNNs) with the global encoding of Transformers through i) a novel patchifying paradigm for dynamic graphs to improve over-squashing, ii) a structure-aware parametric tokenization strategy leveraging MPNNs, iii) a Transformer with temporal positional-encoding to capture long-range dependencies, and iv) an encoding architecture that alternates between local and global contextualization, mitigating over-smoothing in MPNNs. Experimental evaluations on public benchmark datasets demonstrate that Todyformer consistently outperforms the state-of-the-art methods for the downstream tasks. Furthermore, we illustrate the underlying aspects of the proposed model in effectively capturing extensive temporal dependencies in dynamic graph.

Format: Long paper, up to 8 pages. If the reviewers recommend it to be changed to a short paper, I would prefer to withdraw my submission.

Submission Number: 46