Learning Hierarchical and Geometry-Aware Graph ... - OpenReview
Jan 26, 2026 · We address this gap by learning an intermediate representation: a hierarchical and geometry-aware graph. The graph represents an assembly-based decomposition, with multi-level …
RiemannGFM: Learning a Graph Foundation Model from Structural …
Jan 29, 2025 · Track: Graph algorithms and modeling for the Web Keywords: Graph Neural Network, Foundation Model, Riemannian Geometry TL;DR: This work opens a new opportunity to build graph …
Pre-training Molecular Graph Representation with 3D Geometry
Jan 28, 2022 · Molecular graph representation learning is a fundamental problem in modern drug and material discovery. Molecular graphs are typically modeled by their 2D topological structures, but it …
Graph Geometry-Preserving Autoencoders - OpenReview
May 1, 2024 · Through extensive experiments, we show that our method outperforms existing state-of-the-art geometry-preserving and graph-based autoencoders with respect to learning accurate latent …
Geometry-Aware Generative Modeling for Graph Clustering via ...
Sep 20, 2025 · Unsupervised graph clustering is fundamental for uncovering latent structures in graph-structured data, particularly in scenarios where labeled data is limited or unavailable. However, …
TetraGT: Tetrahedral Geometry-Driven Explicit Token Interactions...
Jan 26, 2026 · Keywords: Molecular Representation Learning, Graph Transformer, Molecular Geometry Pretraining TL;DR: The Tetrahedral Graph Transformer (TetraGT) directly models molecular …
Fractal Graph Contrastive Learning - OpenReview
Sep 18, 2025 · Keywords: Graph Representation Learning, Graph Contrastive Learning, Fractal Geometry, Graph Classification, Network Science TL;DR: We were among the first to bring fractal …
Underwater Visual Geometry Estimation with Self-supervised...
Sep 15, 2025 · Underwater Visual Geometry Estimation with Self-supervised Prototype-Graph Modulation Linqing Zhao, Wenzhao Zheng, Zelan Zhu, Haibin Yan, Jiwen Lu 15 Sept 2025 …
Bridging the Space Gap: Unifying Geometry Knowledge Graph …
Jan 23, 2024 · Knowledge Graph Embedding (KGE) is a critical field aiming to transform the elements of knowledge graphs into continuous spaces, offering great potential for structured data representation. …
Contrastive Graph Autoencoder for Shape-based Polygon Retrieval...
Jun 3, 2024 · By leveraging graph message-passing layers, graph feature augmentation and contrastive learning, the proposed CGAE embeds highly discriminative latent embeddings by reconstructing …