scholarly journals Uncertainty-aware prediction of chemical reaction yields with graph neural networks

2022 ◽  
Vol 14 (1) ◽  
Author(s):  
Youngchun Kwon ◽  
Dongseon Lee ◽  
Youn-Suk Choi ◽  
Seokho Kang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Uncertainty Quantification ◽  
Chemical Reaction ◽  
Predictive Distribution ◽  
Data Driven ◽  
Permutation Invariance ◽  
Molecular Graphs ◽  
Benchmark Datasets ◽  
Graph Neural Networks

AbstractIn this paper, we present a data-driven method for the uncertainty-aware prediction of chemical reaction yields. The reactants and products in a chemical reaction are represented as a set of molecular graphs. The predictive distribution of the yield is modeled as a graph neural network that directly processes a set of graphs with permutation invariance. Uncertainty-aware learning and inference are applied to the model to make accurate predictions and to evaluate their uncertainty. We demonstrate the effectiveness of the proposed method on benchmark datasets with various settings. Compared to the existing methods, the proposed method improves the prediction and uncertainty quantification performance in most settings.

scholarly journals SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks

2021 ◽  
Vol 40 (3) ◽  
pp. 1-13
Author(s):  
Lumin Yang ◽  
Jiajie Zhuang ◽  
Hongbo Fu ◽  
Xiangzhi Wei ◽  
Kun Zhou ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Large Scale ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Structure Information ◽  
Graph Neural Networks ◽  
Node Labels ◽  
Point Level

We introduce SketchGNN , a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches. We treat an input stroke-based sketch as a graph with nodes representing the sampled points along input strokes and edges encoding the stroke structure information. To predict the per-node labels, our SketchGNN uses graph convolution and a static-dynamic branching network architecture to extract the features at three levels, i.e., point-level, stroke-level, and sketch-level. SketchGNN significantly improves the accuracy of the state-of-the-art methods for semantic sketch segmentation (by 11.2% in the pixel-based metric and 18.2% in the component-based metric over a large-scale challenging SPG dataset) and has magnitudes fewer parameters than both image-based and sequence-based methods.

scholarly journals An efficient pruning scheme of deep neural networks for Internet of Things applications

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Chen Qi ◽  
Shibo Shen ◽  
Rongpeng Li ◽  
Zhifeng Zhao ◽  
Qing Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Internet Of Things ◽  
Deep Neural Networks ◽  
Computational Cost ◽  
Superior Performance ◽  
Compact Structure ◽  
Resource Limited ◽  
Benchmark Datasets ◽  
Iot Devices

AbstractNowadays, deep neural networks (DNNs) have been rapidly deployed to realize a number of functionalities like sensing, imaging, classification, recognition, etc. However, the computational-intensive requirement of DNNs makes it difficult to be applicable for resource-limited Internet of Things (IoT) devices. In this paper, we propose a novel pruning-based paradigm that aims to reduce the computational cost of DNNs, by uncovering a more compact structure and learning the effective weights therein, on the basis of not compromising the expressive capability of DNNs. In particular, our algorithm can achieve efficient end-to-end training that transfers a redundant neural network to a compact one with a specifically targeted compression rate directly. We comprehensively evaluate our approach on various representative benchmark datasets and compared with typical advanced convolutional neural network (CNN) architectures. The experimental results verify the superior performance and robust effectiveness of our scheme. For example, when pruning VGG on CIFAR-10, our proposed scheme is able to significantly reduce its FLOPs (floating-point operations) and number of parameters with a proportion of 76.2% and 94.1%, respectively, while still maintaining a satisfactory accuracy. To sum up, our scheme could facilitate the integration of DNNs into the common machine-learning-based IoT framework and establish distributed training of neural networks in both cloud and edge.

scholarly journals k-Nearest Neighbor Learning with Graph Neural Networks

Mathematics ◽  
2021 ◽  
Vol 9 (8) ◽  
pp. 830
Author(s):  
Seokho Kang
Keyword(s):  
Neural Network ◽  
Nearest Neighbor ◽  
Learning Algorithm ◽  
Weighting Function ◽  
High Sensitivity ◽  
Training Data ◽  
K Nearest Neighbor ◽  
Main Challenge ◽  
Benchmark Datasets ◽  
Graph Neural Networks

k-nearest neighbor (kNN) is a widely used learning algorithm for supervised learning tasks. In practice, the main challenge when using kNN is its high sensitivity to its hyperparameter setting, including the number of nearest neighbors k, the distance function, and the weighting function. To improve the robustness to hyperparameters, this study presents a novel kNN learning method based on a graph neural network, named kNNGNN. Given training data, the method learns a task-specific kNN rule in an end-to-end fashion by means of a graph neural network that takes the kNN graph of an instance to predict the label of the instance. The distance and weighting functions are implicitly embedded within the graph neural network. For a query instance, the prediction is obtained by performing a kNN search from the training data to create a kNN graph and passing it through the graph neural network. The effectiveness of the proposed method is demonstrated using various benchmark datasets for classification and regression tasks.

scholarly journals Inverse design of glass structure with deep graph neural networks

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Qi Wang ◽  
Longfei Zhang
Keyword(s):  
Neural Networks ◽  
Monte Carlo ◽  
Configuration Space ◽  
Glass Structure ◽  
Stable State ◽  
Specific Property ◽  
Inverse Design ◽  
Data Driven ◽  
Common Belief ◽  
Graph Neural Networks

AbstractDirectly manipulating the atomic structure to achieve a specific property is a long pursuit in the field of materials. However, hindered by the disordered, non-prototypical glass structure and the complex interplay between structure and property, such inverse design is dauntingly hard for glasses. Here, combining two cutting-edge techniques, graph neural networks and swap Monte Carlo, we develop a data-driven, property-oriented inverse design route that managed to improve the plastic resistance of Cu-Zr metallic glasses in a controllable way. Swap Monte Carlo, as a sampler, effectively explores the glass landscape, and graph neural networks, with high regression accuracy in predicting the plastic resistance, serves as a decider to guide the search in configuration space. Via an unconventional strengthening mechanism, a geometrically ultra-stable yet energetically meta-stable state is unraveled, contrary to the common belief that the higher the energy, the lower the plastic resistance. This demonstrates a vast configuration space that can be easily overlooked by conventional atomistic simulations. The data-driven techniques, structural search methods and optimization algorithms consolidate to form a toolbox, paving a new way to the design of glassy materials.

scholarly journals Identification of Granule Growth Regimes in High Shear Wet Granulation Processes Using a Physics-Constrained Neural Network

Processes ◽  
2021 ◽  
Vol 9 (5) ◽  
pp. 737
Author(s):  
Chaitanya Sampat ◽  
Rohit Ramachandran
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Real Time ◽  
Data Driven ◽  
Wet Granulation ◽  
Manufacturing Processes ◽  
High Shear ◽  
Process Data ◽  
Physical Constraints ◽  
Granule Growth

The digitization of manufacturing processes has led to an increase in the availability of process data, which has enabled the use of data-driven models to predict the outcomes of these manufacturing processes. Data-driven models are instantaneous in simulate and can provide real-time predictions but lack any governing physics within their framework. When process data deviates from original conditions, the predictions from these models may not agree with physical boundaries. In such cases, the use of first-principle-based models to predict process outcomes have proven to be effective but computationally inefficient and cannot be solved in real time. Thus, there remains a need to develop efficient data-driven models with a physical understanding about the process. In this work, we have demonstrate the addition of physics-based boundary conditions constraints to a neural network to improve its predictability for granule density and granule size distribution (GSD) for a high shear granulation process. The physics-constrained neural network (PCNN) was better at predicting granule growth regimes when compared to other neural networks with no physical constraints. When input data that violated physics-based boundaries was provided, the PCNN identified these points more accurately compared to other non-physics constrained neural networks, with an error of <1%. A sensitivity analysis of the PCNN to the input variables was also performed to understand individual effects on the final outputs.

Estimation of Site Amplification from Geotechnical Array Data Using Neural Networks

2021 ◽  
Author(s):  
Daniel Roten ◽  
Kim B. Olsen
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Site Response ◽  
Site Amplification ◽  
Data Driven ◽  
Vertical Array ◽  
The Neural Network ◽  
Simplifying Assumptions ◽  
The Mean ◽  
Fully Connected

ABSTRACT We use deep learning to predict surface-to-borehole Fourier amplification functions (AFs) from discretized shear-wave velocity profiles. Specifically, we train a fully connected neural network and a convolutional neural network using mean AFs observed at ∼600 KiK-net vertical array sites. Compared with predictions based on theoretical SH 1D amplifications, the neural network (NN) results in up to 50% reduction of the mean squared log error between predictions and observations at sites not used for training. In the future, NNs may lead to a purely data-driven prediction of site response that is independent of proxies or simplifying assumptions.

scholarly journals Towards Heterogeneous Multi-Agent Reinforcement Learning with Graph Neural Networks

2020 ◽  
Author(s):  
Douglas Meneghetti ◽  
Reinaldo Bianchi
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Communication Channels ◽  
Neural Network Architecture ◽  
Graph Representations ◽  
Labeled Graph ◽  
Multiple Agent ◽  
Multi Agent ◽  
Graph Neural Networks

This work proposes a neural network architecture that learns policies for multiple agent classes in a heterogeneous multi-agent reinforcement setting. The proposed network uses directed labeled graph representations for states, encodes feature vectors of different sizes for different entity classes, uses relational graph convolution layers to model different communication channels between entity types and learns distinct policies for different agent classes, sharing parameters wherever possible. Results have shown that specializing the communication channels between entity classes is a promising step to achieve higher performance in environments composed of heterogeneous entities.

Data-Driven Time Series Forecasting for Social Studies Using Spatio-Temporal Graph Neural Networks

2021 ◽  
Author(s):  
Yi-Fan Li ◽  
Bo Dong ◽  
Latifur Khan ◽  
Bhavani Thuraisingham ◽  
Patrick T. Brandt ◽  
...  
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Social Studies ◽  
Time Series Forecasting ◽  
Data Driven ◽  
Temporal Graph ◽  
Spatio Temporal ◽  
Graph Neural Networks

scholarly journals Fast and Deep Graph Neural Networks

2020 ◽  
Vol 34 (04) ◽  
pp. 3898-3905 ◽  
Author(s):  
Claudio Gallicchio ◽  
Alessio Micheli
Keyword(s):  
Neural Network ◽  
Dynamical System ◽  
Neural Networks ◽  
State Of The Art ◽  
Input Graph ◽  
Sparse Networks ◽  
Set Up ◽  
The Stability ◽  
Graph Neural Networks ◽  
Architectural Organization

We address the efficiency issue for the construction of a deep graph neural network (GNN). The approach exploits the idea of representing each input graph as a fixed point of a dynamical system (implemented through a recurrent neural network), and leverages a deep architectural organization of the recurrent units. Efficiency is gained by many aspects, including the use of small and very sparse networks, where the weights of the recurrent units are left untrained under the stability condition introduced in this work. This can be viewed as a way to study the intrinsic power of the architecture of a deep GNN, and also to provide insights for the set-up of more complex fully-trained models. Through experimental results, we show that even without training of the recurrent connections, the architecture of small deep GNN is surprisingly able to achieve or improve the state-of-the-art performance on a significant set of tasks in the field of graphs classification.

scholarly journals Enhancing protein backbone angle prediction by using simpler models of deep neural networks

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Fereshteh Mataeimoghadam ◽  
M. A. Hakim Newton ◽  
Abdollah Dehzangi ◽  
Abdul Karim ◽  
B. Jayaram ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Structure Prediction ◽  
Protein Structures ◽  
Absolute Error ◽  
Grand Challenge ◽  
Protein Backbone ◽  
The Neural Network ◽  
Benchmark Datasets ◽  
The Neural Networks

Abstract Protein structure prediction is a grand challenge. Prediction of protein structures via the representations using backbone dihedral angles has recently achieved significant progress along with the on-going surge of deep neural network (DNN) research in general. However, we observe that in the protein backbone angle prediction research, there is an overall trend to employ more and more complex neural networks and then to throw more and more features to the neural networks. While more features might add more predictive power to the neural network, we argue that redundant features could rather clutter the scenario and more complex neural networks then just could counterbalance the noise. From artificial intelligence and machine learning perspectives, problem representations and solution approaches do mutually interact and thus affect performance. We also argue that comparatively simpler predictors can more easily be reconstructed than the more complex ones. With these arguments in mind, we present a deep learning method named Simpler Angle Predictor (SAP) to train simpler DNN models that enhance protein backbone angle prediction. We then empirically show that SAP can significantly outperform existing state-of-the-art methods on well-known benchmark datasets: for some types of angles, the differences are 6–8 in terms of mean absolute error (MAE). The SAP program along with its data is available from the website https://gitlab.com/mahnewton/sap.

Sign in / Sign up

Export Citation Format

Share Document