Multimodal Attributed Graphs: Benchmarking and Rethinking

Jing Zhu, Yuhang Zhou, Shengyi Qian, Zhongmou He, Tong Zhao, Neil Shah, Danai Koutra

Keywords: Multimodal Learning, Representation Learning

Abstract: Associating unstructured data with structured information is crucial for real-world tasks that require relevance search. However, existing graph learning benchmarks often overlook the rich semantic information associated with each node, ignoring other available modalities such as the corresponding images. To bridge this gap, we introduce the Multimodal Graph Benchmark (MM-GRAPH), the first comprehensive multi-modal graph benchmark that incorporates both textual and visual information, going beyond the prior focus on just text-attributed graphs. MM-GRAPH consists of seven graph learning datasets of various scales that are appropriate for different learning tasks, and enable a comprehensive evaluation of graph learning algorithms in real-world scenarios thanks to their multimodal node features. To facilitate research on multimodal graph learning, we further provide an extensive study on the performance of various graph learning frameworks in the presence of features from various modalities. MM-GRAPH aims to foster research on multimodal attributed graphs and drive the development of more advanced and robust multimodal attributed graph learning algorithms. By providing a diverse set of datasets and benchmarks, MM-GRAPH enables researchers to evaluate and compare their models in realistic settings, ultimately leading to improved performance on real-world applications that rely on multimodal attributed graphs.

Primary Area: datasets and benchmarks

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.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

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: 11937