Neural Graph Matching Improves Retrieval Augmented Generation in Molecular Machine Learning

• URL: http://arxiv.org/abs/2502.17874v2
• Date: Thu, 03 Jul 2025 03:15:08 GMT
• Title: Neural Graph Matching Improves Retrieval Augmented Generation in Molecular Machine Learning
• Authors: Runzhong Wang, Rui-Xi Wang, Mrunali Manjrekar, Connor W. Coley,
• Abstract summary: We introduce a novel model that incorporates neural graph matching to enhance a fragmentation-based neural network.<n>MarASON achieves 28% top-1 accuracy, a substantial improvement over the non-retrieval state-of-the-art accuracy of 19%.
• Score: 20.911425911621865
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Molecular machine learning has gained popularity with the advancements of geometric deep learning. In parallel, retrieval-augmented generation has become a principled approach commonly used with language models. However, the optimal integration of retrieval augmentation into molecular machine learning remains unclear. Graph neural networks stand to benefit from clever matching to understand the structural alignment of retrieved molecules to a query molecule. Neural graph matching offers a compelling solution by explicitly modeling node and edge affinities between two structural graphs while employing a noise-robust, end-to-end neural network to learn affinity metrics. We apply this approach to mass spectrum simulation and introduce MARASON, a novel model that incorporates neural graph matching to enhance a fragmentation-based neural network. Experimental results highlight the effectiveness of our design, with MARASON achieving 28% top-1 accuracy, a substantial improvement over the non-retrieval state-of-the-art accuracy of 19%. Moreover, MARASON outperforms both naive retrieval-augmented generation methods and traditional graph matching approaches. Code is publicly available at https://github.com/coleygroup/ms-pred

Related papers

• Transductive Spiking Graph Neural Networks for Loihi [0.8684584813982095]
  We present a fully neuromorphic implementation of spiking graph neural networks designed for Loihi 2. We showcase the performance benefits of combining neuromorphic Bayesian optimization with our approach for citation graph classification using fixed-precision spiking neurons.
  arXiv  Detail & Related papers  (2024-04-25T21:15:15Z)
• Graph Neural Networks for Learning Equivariant Representations of Neural Networks [55.04145324152541]
  We propose to represent neural networks as computational graphs of parameters. Our approach enables a single model to encode neural computational graphs with diverse architectures. We showcase the effectiveness of our method on a wide range of tasks, including classification and editing of implicit neural representations.
  arXiv  Detail & Related papers  (2024-03-18T18:01:01Z)
• Efficient Heterogeneous Graph Learning via Random Projection [58.4138636866903]
  Heterogeneous Graph Neural Networks (HGNNs) are powerful tools for deep learning on heterogeneous graphs. Recent pre-computation-based HGNNs use one-time message passing to transform a heterogeneous graph into regular-shaped tensors. We propose a hybrid pre-computation-based HGNN, named Random Projection Heterogeneous Graph Neural Network (RpHGNN)
  arXiv  Detail & Related papers  (2023-10-23T01:25:44Z)
• Extreme Acceleration of Graph Neural Network-based Prediction Models for Quantum Chemistry [7.592530794455257]
  We present a novel hardware-software co-design approach to scale up the training of graph neural networks for molecular property prediction. We introduce an algorithm to coalesce the batches of molecular graphs into fixed size packs to eliminate redundant computation and memory. We demonstrate that such a co-design approach can reduce the training time of such molecular property prediction models from days to less than two hours.
  arXiv  Detail & Related papers  (2022-11-25T01:30:18Z)
• Relation Embedding based Graph Neural Networks for Handling Heterogeneous Graph [58.99478502486377]
  We propose a simple yet efficient framework to make the homogeneous GNNs have adequate ability to handle heterogeneous graphs. Specifically, we propose Relation Embedding based Graph Neural Networks (RE-GNNs), which employ only one parameter per relation to embed the importance of edge type relations and self-loop connections.
  arXiv  Detail & Related papers  (2022-09-23T05:24:18Z)
• Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning [102.9138736545956]
  Heterogeneous graph neural network (HGNN) is a very popular technique for the modeling and analysis of heterogeneous graphs. We develop for the first time a novel and robust heterogeneous graph contrastive learning approach, namely HGCL, which introduces two views on respective guidance of node attributes and graph topologies. In this new approach, we adopt distinct but most suitable attribute and topology fusion mechanisms in the two views, which are conducive to mining relevant information in attributes and topologies separately.
  arXiv  Detail & Related papers  (2022-04-30T12:57:02Z)
• Making Graph Neural Networks Worth It for Low-Data Molecular Machine Learning [15.251466525698627]
  We investigate whether graph neural networks are competitive in small data settings compared to the parametrically 'cheaper' alternative of fingerprint methods. We find that MAML and FO-MAML do enable the graph neural network to outperform models based on fingerprints. In contrast to previous work, we find ANIL performs worse that other meta-learning approaches in this molecule setting.
  arXiv  Detail & Related papers  (2020-11-24T16:52:04Z)
• Neuralizing Efficient Higher-order Belief Propagation [19.436520792345064]
  We propose to combine approaches to learn better node and graph representations. We derive an efficient approximate sum-product loopy belief propagation inference algorithm for higher-order PGMs. Our model indeed captures higher-order information, substantially outperforming state-of-the-art $k$-order graph neural networks in molecular datasets.
  arXiv  Detail & Related papers  (2020-10-19T07:51:31Z)
• Meta-path Free Semi-supervised Learning for Heterogeneous Networks [16.641434334366227]
  Graph neural networks (GNNs) have been widely used in representation learning on graphs and achieved superior performance in tasks such as node classification. In this paper, we propose simple and effective graph neural networks for heterogeneous graph, excluding the use of meta-paths.
  arXiv  Detail & Related papers  (2020-10-18T06:01:58Z)
• Towards Deeper Graph Neural Networks [63.46470695525957]
  Graph convolutions perform neighborhood aggregation and represent one of the most important graph operations. Several recent studies attribute this performance deterioration to the over-smoothing issue. We propose Deep Adaptive Graph Neural Network (DAGNN) to adaptively incorporate information from large receptive fields.
  arXiv  Detail & Related papers  (2020-07-18T01:11:14Z)
• Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning [56.83172249278467]
  We introduce Evolutionary Graph Reinforcement Learning (EGRL), a method designed for large search spaces. We train and validate our approach directly on the Intel NNP-I chip for inference. We additionally achieve 28-78% speed-up compared to the native NNP-I compiler on all three workloads.
  arXiv  Detail & Related papers  (2020-07-14T18:50:12Z)
• Hcore-Init: Neural Network Initialization based on Graph Degeneracy [22.923756039561194]
  We propose an adapted version of the k-core structure for the complete weighted multipartite graph extracted from a deep learning architecture. As a multipartite graph is a combination of bipartite graphs, that are in turn the incidence graphs of hypergraphs, we design k-hypercore decomposition.
  arXiv  Detail & Related papers  (2020-04-16T12:57:14Z)
• Geometrically Principled Connections in Graph Neural Networks [66.51286736506658]
  We argue geometry should remain the primary driving force behind innovation in the emerging field of geometric deep learning. We relate graph neural networks to widely successful computer graphics and data approximation models: radial basis functions (RBFs) We introduce affine skip connections, a novel building block formed by combining a fully connected layer with any graph convolution operator.
  arXiv  Detail & Related papers  (2020-04-06T13:25:46Z)

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.