paper-with-me

Papers

Transformers are efficient hierarchical chemical graph learners

2023-10-02 · Zihan Pengmei, Zimu Li, Chih-chan Tien, Risi Kondor, Aaron R. Dinner

Transformers, adapted from natural language processing, are emerging as a leading approach for graph representation learning. Contemporary graph transformers often treat nodes or edges as separate tokens. This approach leads to computational challenges for even moderately-sized graphs due to the quadratic scaling of self-attention complexity with token count. In this paper, we introduce SubFormer, a graph transformer that operates on subgraphs that aggregate information by a message-passing mechanism. This approach reduces the number of tokens and enhances learning long-range interactions. We demonstrate SubFormer on benchmarks for predicting molecular properties from chemical structures and show that it is competitive with state-of-the-art graph transformers at a fraction of the computational cost, with training times on the order of minutes on a consumer-grade graphics card. We interpret the attention weights in terms of chemical structures. We show that SubFormer exhibits limited over-smoothing and avoids over-squashing, which is prevalent in traditional graph neural networks.

📄 PDF Abstract BibTeX arXiv:2310.01704

Code (1)

zpengmei/SubFormer-Spec 공식 구현 pytorch

Tasks

Graph Representation LearningRepresentation Learning

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Multiresolution Graph Transformers and Wavelet Positional Encoding for Learning Hierarchical Structures

2023-02-17 · Nhat Khang Ngo, Truong Son Hy, Risi Kondor

Contemporary graph learning algorithms are not well-defined for large molecules since they do not consider the hierarchical interactions among the atoms, which are essential to determine the molecular properties of macro…

Graph ClassificationGraph LearningGraph Regression

Enhancing Graph Transformers with Hierarchical Distance Structural Encoding

2023-08-22 · Yuankai Luo, Hongkang Li, Lei Shi, Xiao-Ming Wu

Graph transformers need strong inductive biases to derive meaningful attention scores. Yet, current methods often fall short in capturing longer ranges, hierarchical structures, or community structures, which are common …

Graph ClassificationGraph RegressionNode Classification

MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights

2024-12-21 · Jingjing Hu, Dan Guo, Zhan Si, Deguang Liu 외

Molecular representation learning plays a crucial role in various downstream tasks, such as molecular property prediction and drug design. To accurately represent molecules, Graph Neural Networks (GNNs) and Graph Transfo…

Drug DesignMambaMolecular Property Predictionmolecular representation+2

BiScale-GTR: Fragment-Aware Graph Transformers for Multi-Scale Molecular Representation Learning

2026-04-07 · Yi Yang, Ovidiu Daescu arxiv

Graph Transformers have recently attracted attention for molecular property prediction by combining the inductive biases of graph neural networks (GNNs) with the global receptive field of Transformers. However, many exis…

Molecular Property PredictionRepresentation Learning

Learning Hierarchical Interaction for Accurate Molecular Property Prediction

2025-04-28 · Huiyang Hong, Xinkai Wu, Hongyu Sun, Chaoyang Xie 외

Discovering molecules with desirable molecular properties, including ADMET profiles, is of great importance in drug discovery. Existing approaches typically employ deep learning models, such as Graph Neural Networks (GNN…

Drug DiscoveryMolecular Property PredictionPredictionProperty Prediction+1