Long Range Graph Benchmark

Vijay Prakash Dwivedi, Ladislav Rampášek, Mikhail Galkin, Ali Parviz, Guy Wolf, Anh Tuan Luu, Dominique Beaini

Keywords: graph learning benchmark, long range dependencies, graph transformers, graph datasets, graph neural networks

TL;DR: We present the Long Range Graph Benchmark (LRGB) with 5 datasets that can be used for the development of models enabling long range dependencies in graphs, like Graph Transformers.

Abstract: Graph Neural Networks (GNNs) that are based on the message passing (MP) paradigm generally exchange information between 1-hop neighbors to build node representations at each layer. In principle, such networks are not able to capture long-range interactions (LRI) that may be desired or necessary for learning a given task on graphs. Recently, there has been an increasing interest in development of Transformer-based methods for graphs that can consider full node connectivity beyond the original sparse structure, thus enabling the modeling of LRI. However, MP-GNNs that simply rely on 1-hop message passing often fare better in several existing graph benchmarks when combined with positional feature representations, among other innovations, hence limiting the perceived utility and ranking of Transformer-like architectures. Here, we present the Long Range Graph Benchmark (LRGB) with 5 graph learning datasets: $\texttt{PascalVOC-SP}$, $\texttt{COCO-SP}$, $\texttt{PCQM-Contact}$, $\texttt{Peptides-func}$ and $\texttt{Peptides-struct}$ that arguably require LRI reasoning to achieve strong performance in a given task. We benchmark both baseline GNNs and Graph Transformer networks to verify that the models which capture long-range dependencies perform significantly better on these tasks. Therefore, these datasets are suitable for benchmarking and exploration of MP GNNs and Graph Transformer architectures that are intended to capture LRI.

Author Statement: Yes

URL: https://github.com/vijaydwivedi75/lrgb

Dataset Url: https://github.com/vijaydwivedi75/lrgb

License: The licenses of the datasets in the proposed benchmark are listed in the supplementary as well as the README of the code repository at https://github.com/vijaydwivedi75/lrgb.

Contribution Process Agreement: Yes

In Person Attendance: Yes

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2206.08164/code)