EUVIMEDEUVIMED entdecken
Crossref

MMPG: MoE-based Adaptive Multi-Perspective Graph Fusion for Protein Representation Learning

Yusong Wang, Jialun Shen, Zhihao Wu, Yicheng Xu, Shiyin Tan, Mingkun Xu, Changshuo Wang, Zixing Song, Prayag Tiwari

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (2) · 1240-1248

DOI: 10.1609/aaai.v40i2.37096 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yusong Wang und 8 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph Neural Networks (GNNs) have been widely adopted for Protein Representation Learning (PRL), as residue interaction networks can be naturally represented as graphs. Current GNN-based PRL methods typically rely on single-perspective graph construction strategies, which capture partial properties of residue interactions, resulting in incomplete protein representations. To address this limitation, we propose MMPG, a framework that constructs protein graphs from multiple perspectives and adaptively fuses them via Mixture of Experts (MoE) for PRL. MMPG constructs graphs from physical, chemical, and geometric perspectives to characterize different properties of residue interactions. To capture both perspective-specific features and their synergies, we develop an MoE module, which dynamically routes perspectives to specialized experts, where experts learn intrinsic features and cross-perspective interactions. We quantitatively verify that MoE automatically specializes experts in modeling distinct levels of interaction—from individual representations, to pairwise inter-perspective synergies, and ultimately to a global consensus across all perspectives. Through integrating this multi-level information, MMPG produces superior protein representations and achieves advanced performance on four different downstream protein tasks.

Zitieren

APA

Wang, Y., Shen, J., Wu, Z., Xu, Y., Tan, S., Xu, M., Wang, C., Song, Z., & Tiwari, P. (2026). MMPG: MoE-based Adaptive Multi-Perspective Graph Fusion for Protein Representation Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(2), 1240-1248. https://doi.org/10.1609/aaai.v40i2.37096

Vancouver

Wang Y, Shen J, Wu Z, Xu Y, Tan S, Xu M, et al. MMPG: MoE-based Adaptive Multi-Perspective Graph Fusion for Protein Representation Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(2):1240-1248. doi:10.1609/aaai.v40i2.37096

BibTeX
@article{Wang2026,
  author = {Wang, Yusong and Shen, Jialun and Wu, Zhihao and Xu, Yicheng and Tan, Shiyin and Xu, Mingkun and Wang, Changshuo and Song, Zixing and Tiwari, Prayag},
  title = {MMPG: MoE-based Adaptive Multi-Perspective Graph Fusion for Protein Representation Learning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {2},
  pages = {1240--1248},
  doi = {10.1609/aaai.v40i2.37096}
}
Kostenlos starten →