Two-Stream Spatial Graphormer Networks for Skeleton-Based Action Recognition

Li, Xiaolei; Zhang, Junyou; Wang, Shufeng; Zhou, Qian

doi:10.1109/access.2022.3206044

Cited by 5 publications

(7 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Graphormer was chosen as our model architecture to address the known limitation of the MPNN architecture and because of its recent success across a wide variety of domains. ,− A complete depiction of our model architecture is present in Figure . Transformers are a type of encoder that are successful because they learn contextual relationships between input embeddings which are aggregated to generate a learned description of the input.…”

Section: Methodsmentioning

confidence: 99%

Graphormer-IR: Graph Transformers Predict Experimental IR Spectra Using Highly Specialized Attention

Stienstra,

Hebert,

Thomas

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Infrared (IR) spectroscopy is an important analytical tool in various chemical and forensic domains and a great deal of effort has gone into developing in silico methods for predicting experimental spectra. A key challenge in this regard is generating highly accurate spectra quickly to enable real-time feedback between computation and experiment. Here, we employ Graphormer, a graph neural network (GNN) transformer, to predict IR spectra using only simplified molecular-input line-entry system (SMILES) strings. Our data set includes 53,528 high-quality spectra, measured in five different experimental media (i.e., phases), for molecules containing the elements H, C, N, O, F, Si, S, P, Cl, Br, and I. When using only atomic numbers for node encodings, Graphormer-IR achieved a mean test spectral information similarity (SIS μ ) value of 0.8449 ± 0.0012 (n = 5), which surpasses that the current state-of-the-art model Chemprop-IR (SIS μ = 0.8409 ± 0.0014, n = 5) with only 36% of the encoded information. Augmenting node embeddings with additional node-level descriptors in learned embeddings generated through a multilayer perceptron improves scores to SIS μ = 0.8523 ± 0.0006, a total improvement of 19.7σ (t = 19). These improved scores show how Graphormer-IR excels in capturing long-range interactions like hydrogen bonding, anharmonic peak positions in experimental spectra, and stretching frequencies of uncommon functional groups. Scaling our architecture to 210 attention heads demonstrates specialist-like behavior for distinct IR frequencies that improves model performance. Our model utilizes novel architectures, including a global node for phase encoding, learned node feature embeddings, and a one-dimensional (1D) smoothing convolutional neural network (CNN). Graphormer-IR's innovations underscore its value over traditional message-passing neural networks (MPNNs) due to its expressive embeddings and ability to capture long-range intramolecular relationships.

show abstract

Section: Methodsmentioning

confidence: 99%

Graphormer-IR: Graph Transformers Predict Experimental IR Spectra Using Highly Specialized Attention

Stienstra,

Hebert,

Thomas

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…Graphormer was chosen as our model architecture to address the known limitation of the MPNN architecture and because of its recent success across a wide variety of do-mains. 46,[56][57][58][59] .A complete depiction of our model architecture is present in Figure 1. Transformers are a type of encoder that are successful because they learn contextual relationships between input embeddings which are aggregated to a learned description of the input.…”

Section: Transformersmentioning

confidence: 99%

Graphormer-IR: Graph Transformers Predict Experimental IR Spectra Using Highly Specialized Attention

Stienstra,

Hebert,

Thomas

et al. 2024

Preprint

View full text Add to dashboard Cite

Given that Infrared (IR) spectroscopy is a crucial tool in various chemical and forensic domains, improved in silico methods for predicting experimental spectra are needed due to the time and accuracy limitations of ab initio methods. We employ Graphormer, a graph neural network (GNN) transformer, to predict IR spectra using only Simplified Molecular-Input Line-Entry System (SMILES) strings. Our dataset includes 53,528 high-quality spectra with elements H, C, N, O, F, Si, S, P, Cl, Br, and I in five phases. When using only atomic numbers for node encodings, Graphormer-IR achieved mean test Spectral Information Similarity (SIS_μ) of 0.8449±0.0012 (n=5), surpassing the state-of-the-art Chemprop-IR (SIS_μ = 0.8409 ± 0.0014, n=5), with only 36% of the encoded information. Augmenting node embeddings with additional node-level descriptors in learned embeddings generated through a multi-layer perceptron improves scores to SIS_μ = 0.8523±0.0006, a total improvement of 19.7σ. These improved scores show how Graphormer-IR excels in capturing long-range interactions like hydrogen bonding, anharmonic peak positions in experimental spectra, and stretching frequencies of uncommon functional groups. Scaling our architecture to 210 attention heads demonstrates specialist-like behavior for distinct IR frequencies that improves model performance. Our model utilizes novel architectures, including a global node for phase encoding, learned node feature embeddings, and a 1D smoothing CNN. Graphormer-IR’s innovations underscore its value over traditional message-passing neural networks (MPNNs) due to its expressive embeddings and ability to capture long-range intra-molecular relationships.

show abstract

“…Graphormer was chosen as our model architecture to address the known limitation of the MPNN architecture and because of its recent success across a wide variety of domains. 46,[56][57][58][59] Transformers are type of encoder that are successful because they learn contextual relationships between input embeddings which are aggregated to a learned description of the input. This is achieved using a self-attention mechanism, where the model assigns varying degrees of importance to between different items in the input sequence.…”

Section: Data Processingmentioning

confidence: 99%

Graphormer-IR: Graph Transformers Can Predict Experimental IR Spectra Using Highly Specialized Attention

Stienstra,

Hebert,

Thomas

et al. 2023

Preprint

View full text Add to dashboard Cite

Infrared (IR) spectroscopy is crucial in various chemical and forensic domains, but faster in silico methods for predicting experimental spectra are needed due to the time and accuracy limitations of ab initio methods. We employ Graphormer, a graph neural network (GNN) transformer, to predict IR spectra using only Simplified Molecular-Input Line-Entry System (SMILES) strings. Our dataset includes 53,528 high-quality spectra with elements H, C, N, O, F, Si, S, P, Cl, Br, and I in five solvent phases. When using only atomic numbers for node encodings, Graphormer-IR achieved SIS_μ test scores of 0.8449±0.0012 (n=5), surpassing the state-of-the-art Chemprop-IR (SIS_μ = 0.8409 ± 0.0014, n=5), with only 36% of the encoded information. Augmenting node embeddings with additional node-level descriptors in learned embeddings generated through a multi-layer perceptron improves scores to SIS_μ = 0.8523±0.0006, a total improvement of 19.7σ. These improved scores show how Graphormer-IR excels in capturing long-range interactions like hydrogen bonding, anharmonic peak positions in experimental spectra, and stretching frequencies of uncommon functional groups. Scaling our architecture to 210 attention heads demonstrates specialist-like behavior for distinct IR frequencies that improves model performance. Our model utilizes novel architectures, including a global node for solvent phase encoding, learned node feature embeddings, and a 1D smoothing CNN. Graphormer-IR’s innovations underscore its potency over traditional message-passing neural networks (MPNNs) due to its expressive embeddings and ability to capture long-range intra-molecular relationships.

show abstract

Two-Stream Spatial Graphormer Networks for Skeleton-Based Action Recognition

Cited by 5 publications

References 36 publications

Graphormer-IR: Graph Transformers Predict Experimental IR Spectra Using Highly Specialized Attention

Graphormer-IR: Graph Transformers Predict Experimental IR Spectra Using Highly Specialized Attention

Graphormer-IR: Graph Transformers Predict Experimental IR Spectra Using Highly Specialized Attention

Graphormer-IR: Graph Transformers Can Predict Experimental IR Spectra Using Highly Specialized Attention

Contact Info

Product

Resources

About