Metraipolis › archive › dc_408eeb81d80c

MM-DyGraph: A Dataset, Benchmark, and Model for Multimodal Dynamic Graphs — arXiv:2611.09240

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09240
License (as archived)
CC0-1.0
Archived
2026-11-09T22:33:57.014Z
SHA-256 of the archived text
b3377a9ded70a3dceac579a45bac707c41f49d0da1b305b80817fab09ad665b4
Stable URL of this page
https://metraipolis.com/documento/dc_408eeb81d80c

How to cite

MM-DyGraph: A Dataset, Benchmark, and Model for Multimodal Dynamic Graphs — arXiv:2611.09240 — arXiv (en), https://arxiv.org/abs/2611.09240 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_408eeb81d80c (Metraipolis archive dc_408eeb81d80c, sha256 b3377a9ded70a3dceac579a45bac707c41f49d0da1b305b80817fab09ad665b4)
BibTeX
@misc{dc408eeb81d80c,
  title = {MM-DyGraph: A Dataset, Benchmark, and Model for Multimodal Dynamic Graphs — arXiv:2611.09240},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09240},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_408eeb81d80c; sha256 b3377a9ded70a3dceac579a45bac707c41f49d0da1b305b80817fab09ad665b4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09240. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal dynamic graphs are pervasive in real-world applications, where nodes and edges are accompanied by multimodal signals, including text and images. Despite their practical importance, benchmarks and methods that explicitly study multimodal learning in dynamic graphs remain scarce, hindering the full understanding and effective utilization of multimodal information for downstream tasks. To address this gap, we introduce MM-DyGraph, to the best of our knowledge, the first benchmark for multimodal dynamic graph learning, consisting of diverse real-world datasets with fine-grained temporal graph evolution and rich multimodal attributes. MM-DyGraph provides three evaluation tasks to comprehensively assess model performance in dynamic settings. We benchmark representative state-of-the-art dynamic graph methods and reveal that naive feature concatenation yields target-level inconsistencies: multimodal inputs benefit certain prediction targets while harming others. This observation indicates that the modality informativeness depends on the specific prediction target over time. Building on these observations, we propose a Target-aware Spatial-Temporal Multimodal Fusion (TST-MF) framework, which jointly conditions multimodal fusion on the prediction target and spatial-temporal relations, enabling context-adaptive cross-modal interplay for target-specific representations. Extensive experiments over diverse datasets and tasks show that TST-MF delivers robust and competitive performance, achieving clear gains in multimodal settings.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.09240 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-09T22:30:47.269Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).