GeoRecon: Graph-Level Representation Learning for 3D Molecules via Reconstruction-Based Pretraining

• URL: http://arxiv.org/abs/2506.13174v2
• Date: Mon, 20 Oct 2025 00:21:40 GMT
• Title: GeoRecon: Graph-Level Representation Learning for 3D Molecules via Reconstruction-Based Pretraining
• Abstract summary: We introduce GeoRecon, a graph-level pretraining framework that shifts the focus from individual atoms to the molecule as an integrated whole.<n>GeoRecon formulates a graph-level reconstruction task that guides geometry reconstruction while inducing smoother and more transferable latent spaces.<n>Without relying on external supervision, GeoRecon generally improves over backbone baselines on multiple molecular benchmarks.
• Score: 34.23512730854597
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The pretraining-finetuning paradigm has powered major advances in domains such as natural language processing and computer vision, with representative examples including masked language modeling and next-token prediction. In molecular representation learning, however, pretraining tasks remain largely restricted to node-level denoising, which effectively captures local atomic environments but is often insufficient for encoding the global molecular structure critical to graph-level property prediction tasks such as energy estimation and molecular regression. To address this gap, we introduce GeoRecon, a graph-level pretraining framework that shifts the focus from individual atoms to the molecule as an integrated whole. GeoRecon formulates a graph-level reconstruction task: during pretraining, the model is trained to produce an informative graph representation that guides geometry reconstruction while inducing smoother and more transferable latent spaces. This encourages the learning of coherent, global structural features beyond isolated atomic details. Without relying on external supervision, GeoRecon generally improves over backbone baselines on multiple molecular benchmarks including QM9, MD17, MD22, and 3BPA, demonstrating the effectiveness of graph-level reconstruction for holistic and geometry-aware molecular embeddings.

Related papers

• Multi-level Self-supervised Pretraining on Compositional Hierarchical Graph for Molecular Property Prediction [0.5097809301149341]
  MolCHG is a multi-level self-supervised pretraining framework built upon a novel Compositional Hierarchical Graph.<n>Our architecture elevates bond-level information to independently evolving node representations.<n>Experiments on nine MoleculeNet benchmarks demonstrate that MolCHG achieves the best performance on seven datasets.
  arXiv  Detail & Related papers  (2026-05-15T15:47:11Z)
• Riemannian Geometry Speaks Louder Than Words: From Graph Foundation Model to Next-Generation Graph Intelligence [51.30336200738606]
  There is strong agreement that Graph Foundation Models (GFMs) are essential for advancing graph learning.<n> considerable disagreement persists on how to build a powerful, general-purpose GFM analogous to Large Language Models (LLMs)
  arXiv  Detail & Related papers  (2026-03-23T05:49:19Z)
• GeoGNN: Quantifying and Mitigating Semantic Drift in Text-Attributed Graphs [59.61242815508687]
  Graph neural networks (GNNs) on text--attributed graphs (TAGs) encode node texts using pretrained language models (PLMs) and propagate these embeddings through linear neighborhood aggregation.<n>This work introduces a local PCA-based metric that measures the degree of semantic drift and provides the first quantitative framework to analyze how different aggregation mechanisms affect manifold structure.
  arXiv  Detail & Related papers  (2025-11-12T06:48:43Z)
• GeoGraph: Geometric and Graph-based Ensemble Descriptors for Intrinsically Disordered Proteins [0.43981305860983716]
  We introduce GeoGraph, a simulation-informed surrogate trained to predict ensemble-averaged statistics of residue-residue contact-map topology directly from sequence.<n>By featurizing coarse-grained molecular dynamics simulations into residue- and sequence-level graph descriptors, we create a robust and information-rich learning target.
  arXiv  Detail & Related papers  (2025-10-01T11:13:53Z)
• Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining [21.71848826907517]
  We introduce C-FREE (Contrast-Free Representation learning on Ego-nets), a simple framework that integrates 2D graphs with ensembles of 3D conformers.<n>C-FREE learns molecular representations by predicting subgraph embeddings from their complementary neighborhoods in the latent space.<n>C-FREE state-of-the-art results on MoleculeNet, surpassing contrastive, generative, and other multimodal self-supervised methods.
  arXiv  Detail & Related papers  (2025-09-26T15:16:20Z)
• A Remedy for Over-Squashing in Graph Learning via Forman-Ricci Curvature based Graph-to-Hypergraph Structural Lifting [0.0]
  We propose a structural lifting strategy using Forman-Ricci curvature, which defines an edge-based network characteristic.<n>Curvature reveals local and global properties of a graph, such as a network's backbones.<n>Our approach provides a remedy to the problem of information distortion in message passing across long distances and graph bottlenecks.
  arXiv  Detail & Related papers  (2025-08-15T10:46:27Z)
• Pre-trained Molecular Language Models with Random Functional Group Masking [54.900360309677794]
  We propose a SMILES-based underlineem Molecular underlineem Language underlineem Model, which randomly masking SMILES subsequences corresponding to specific molecular atoms. This technique aims to compel the model to better infer molecular structures and properties, thus enhancing its predictive capabilities.
  arXiv  Detail & Related papers  (2024-11-03T01:56:15Z)
• Pushing the Limits of All-Atom Geometric Graph Neural Networks: Pre-Training, Scaling and Zero-Shot Transfer [15.302727191576784]
  Geometric graph neural networks (Geom-GNNs) with all-atom information have transformed atomistic simulations. We study the scaling behaviors of Geom-GNNs under self-supervised pre-training, supervised and unsupervised learning setups. We show how all-atom graph embedding can be organically combined with other neural architectures to enhance the expressive power.
  arXiv  Detail & Related papers  (2024-10-29T03:07:33Z)
• Using pretrained graph neural networks with token mixers as geometric featurizers for conformational dynamics [0.0]
  We introduce geom2vec, in which pretrained graph neural networks (GNNs) are used as universal geometric featurizers.<n>We show how the learned GNN representations can capture interpretable relationships between structural units (tokens) by combining them with expressive token mixers.
  arXiv  Detail & Related papers  (2024-09-30T00:36:06Z)
• Hi-GMAE: Hierarchical Graph Masked Autoencoders [90.30572554544385]
  Hierarchical Graph Masked AutoEncoders (Hi-GMAE) Hi-GMAE is a novel multi-scale GMAE framework designed to handle the hierarchical structures within graphs. Our experiments on 15 graph datasets consistently demonstrate that Hi-GMAE outperforms 17 state-of-the-art self-supervised competitors.
  arXiv  Detail & Related papers  (2024-05-17T09:08:37Z)
• CTAGE: Curvature-Based Topology-Aware Graph Embedding for Learning Molecular Representations [11.12640831521393]
  We propose an embedding approach CTAGE, utilizing $k$-hop discrete Ricci curvature to extract structural insights from molecular graph data. Results indicate that introducing node curvature significantly improves the performance of current graph neural network frameworks.
  arXiv  Detail & Related papers  (2023-07-25T06:13:01Z)
• Bi-level Contrastive Learning for Knowledge-Enhanced Molecule Representations [68.32093648671496]
  We introduce GODE, which accounts for the dual-level structure inherent in molecules.<n> Molecules possess an intrinsic graph structure and simultaneously function as nodes within a broader molecular knowledge graph.<n>By pre-training two GNNs on different graph structures, GODE effectively fuses molecular structures with their corresponding knowledge graph substructures.
  arXiv  Detail & Related papers  (2023-06-02T15:49:45Z)
• Molecular Graph Generation via Geometric Scattering [7.796917261490019]
  Graph neural networks (GNNs) have been used extensively for addressing problems in drug design and discovery. We propose a representation-first approach to molecular graph generation. We show that our architecture learns meaningful representations of drug datasets and provides a platform for goal-directed drug synthesis.
  arXiv  Detail & Related papers  (2021-10-12T18:00:23Z)
• GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction [47.70253904390288]
  We propose a novel graph contrastive learning method utilizing the geometry of a molecule across 2D and 3D views. Specifically, we first devise a dual-view geometric message passing network (GeomMPNN) to adaptively leverage the rich information of both 2D and 3D graphs of a molecule.
  arXiv  Detail & Related papers  (2021-09-24T03:55:27Z)
• GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles [60.12186997181117]
  Prediction of a molecule's 3D conformer ensemble from the molecular graph holds a key role in areas of cheminformatics and drug discovery. Existing generative models have several drawbacks including lack of modeling important molecular geometry elements. We propose GeoMol, an end-to-end, non-autoregressive and SE(3)-invariant machine learning approach to generate 3D conformers.
  arXiv  Detail & Related papers  (2021-06-08T14:17:59Z)
• Self-supervised Graph-level Representation Learning with Local and Global Structure [71.45196938842608]
  We propose a unified framework called Local-instance and Global-semantic Learning (GraphLoG) for self-supervised whole-graph representation learning. Besides preserving the local similarities, GraphLoG introduces the hierarchical prototypes to capture the global semantic clusters. An efficient online expectation-maximization (EM) algorithm is further developed for learning the model.
  arXiv  Detail & Related papers  (2021-06-08T05:25:38Z)
• Uncovering the Folding Landscape of RNA Secondary Structure with Deep Graph Embeddings [71.20283285671461]
  We propose a geometric scattering autoencoder (GSAE) network for learning such graph embeddings. Our embedding network first extracts rich graph features using the recently proposed geometric scattering transform. We show that GSAE organizes RNA graphs both by structure and energy, accurately reflecting bistable RNA structures.
  arXiv  Detail & Related papers  (2020-06-12T00:17:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.