Reproduce “MM-DyGraph: A Dataset, Benchmark, and Model for Multimodal Dynamic Graphs” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Zongyuan Wu, Pengjie Wang, Lingshan Chen, Tianhang Wan, Yuan Meng, Xin Wang, Ling Feng, Wenwu Zhu
The authors introduce MM-DyGraph, a benchmark for evolving graphs with text and image features, and TST-MF, a fusion method that uses a prediction target’s interaction history and neighbors to guide modality combination. In transductive Yelp node retrieval with Text+Image features, TST-MF reaches 79.11 ± 0.49 Hits@10 versus 67.54 ± 14.55 for same-backbone DyGFormer concatenation, under sampled negatives.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.