Recurrent Distance-Encoding Neural Networks for Graph Representation Learning
Primary Area: learning on graphs and other geometries & topologies
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Recurrent Neural Networks, Graph Neural Networks
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
Abstract: Graph neural networks based on iterative one-hop message-passing have been shown to struggle in harnessing information from distant nodes effectively. Conversely, graph transformers allow each node to attend to all other nodes directly, but suffer from high computational complexity and have to rely on ad-hoc positional encodings to bake in the graph inductive bias. In this paper, we propose a new architecture to reconcile these challenges. Our approach stems from the recent breakthroughs in long-range modeling provided by deep state-space models on sequential data: for a given target node, our model aggregates nodes at different distances and uses a parallelizable linear recurrent network over the chain of distances to provide a natural encoding of its neighborhood structure. With no need for positional encoding, we empirically show that the performance of our model is competitive compared with that of state-of-the-art graph transformers on various benchmarks, at a drastically reduced computational complexity. In addition, we show that our model is theoretically more expressive than one-hop message-passing neural networks.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 9385
Loading