With massive amounts of atomic simulation data available, there is a huge opportunity to develop fast and accurate machine learning models to approximate expensive physics-based calculations. The key quantity to estimate is atomic forces, where the state-of-the-art Graph Neural Networks (GNNs) explicitly enforce basic physical constraints such as rotation-covariance. However, to strictly satisfy the physical constraints, existing models have to make tradeoffs between computational efficiency and model expressiveness. Here we explore an alternative approach. By not imposing explicit physical constraints, we can flexibly design expressive models while maintaining their computational efficiency. Physical constraints are implicitly imposed by training the models using physics-based data augmentation. To evaluate the approach, we carefully design a scalable and expressive GNN model, ForceNet, and apply it to OC20 (Chanussot et al., 2020), an unprecedentedly-large dataset of quantum physics calculations. Our proposed ForceNet is able to predict atomic forces more accurately than state-of-the-art physics-based GNNs while being faster both in training and inference. Overall, our promising and counter-intuitive results open up an exciting avenue for future research.
Efficient Extreme Operating Condition Search for Online Relay Setting Calculation in Renewable Power Systems Based on Parallel Graph Neural Network
State Key Laboratory of Advanced Electromagnetic Technology and the School of Electrical and Electronic Engineering, Huazhong University of Science and Technology（先进电磁技术国家重点实验室和华中科技大学电子与信息学院）；State Grid Hubei Electric Power Co., Ltd.（国网湖北省电力有限公司）
Graph neural networks have become a powerful framework for learning complex structure-property relationships and fast screening of chemical compounds. Recently proposed methods have demonstrated that using 3D geometry information of the molecule along with the bonding structure can lead to more accurate prediction on a wide range of properties. A common practice is to use 3D geometries computed through density functional theory (DFT) for both training and testing of models. However, the computational time needed for DFT calculations can be prohibitively large. Moreover, many of the properties …
GQD-AdsNet: Graph Neural Networks Unlock Rapid Exploration of Transition Metal Adsorption on Graphene Quantum Dots
Instituto de Química Aplicada del Litoral IQAL (UNL-CONICET)（应用化学海岸研究所（UNL-CONICET））；Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional sinc(i) (UNL-CONICET)（信号、系统和计算智能研究所（UNL-CONICET））；General Chemistry (ALGC) - Materials Modelling Group, Vrije Universiteit Brussel (VUB)（化学与材料建模组，布鲁塞尔自由大学）
This paper proposes fractional order graph neural networks (FGNNs), optimized by the approximation strategy to address the challenges of local optimum of classic and fractional graph neural networks which are specialised at aggregating information from the feature and adjacent matrices of connected nodes and their neighbours to solve learning tasks on non-Euclidean data such as graphs. Meanwhile the approximate calculation of fractional order gradients also overcomes the high computational complexity of fractional order derivations. We further prove that such an approximation is feasible and t…
Pacific Northwest National Laboratory（太平洋西北国家实验室）；University of California San Diego（加州大学圣迭戈分校）；Rutgers University - New Brunswick（罗格斯大学新布朗斯维克分校）
We introduce torchNTK, a python library to calculate the empirical neural tangent kernel (NTK) of neural network models in the PyTorch framework. We provide an efficient method to calculate the NTK of multilayer perceptrons. We compare the explicit differentiation implementation against autodifferentiation implementations, which have the benefit of extending the utility of the library to any architecture supported by PyTorch, such as convolutional networks. A feature of the library is that we expose the user to layerwise NTK components, and show that in some regimes a layerwise calculation is …
Fast Searching of Extreme Operating Conditions for Relay Protection Setting Calculation Based on Graph Neural Network and Reinforcement Learning
State Key Laboratory of Advanced Electromagnetic Technology（强电磁工程与新技术国家重点实验室）；School of Electrical and Electronic Engineering, Huazhong University of Science and Technology（华中科技大学电气与电子工程学院）；Northwest Branch of State Grid Corporation of China（国家电网有限公司西北分部）；College of Electrical and Information Engineering, Hunan University（湖南大学电气与信息工程学院）
This paper presents a pure neural solver for arithmetic expression calculation (AEC) problem. Previous work utilizes the powerful capabilities of deep neural networks and attempts to build an end-to-end model to solve this problem. However, most of these methods can only deal with the additive operations. It is still a challenging problem to solve the complex expression calculation problem, which includes the adding, subtracting, multiplying, dividing and bracketing operations. In this work, we regard the arithmetic expression calculation as a hierarchical reinforcement learning problem. An ar…
State University of New York at Buffalo（纽约州立大学布法罗分校）；University of Tehran（德黑兰大学）
Gradient descent optimizations and backpropagation are the most common methods for training neural networks, but they are computationally expensive for real time applications, need high memory resources, and are difficult to converge for many networks and large datasets. [Pseudo]inverse models for training neural network have emerged as powerful tools to overcome these issues. In order to effectively implement these methods, structured pruning maybe be applied to produce sparse neural networks. Although sparse neural networks are efficient in memory usage, most of their algorithms use the same…
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；China University of Geosciences（中国地质大学）
Phase equilibrium calculation, also known as flash calculation, has been extensively applied in petroleum engineering, not only as a standalone application for separation process but also an integral component of compositional reservoir simulation. It is of vital importance to accelerate flash calculation without much compromise in accuracy and reliability, turning it into an active research topic in the last two decades. In this study, we establish a deep neural network model to approximate the iterative NVT-flash calculation. A dynamic model designed for NVT flash problems is iteratively sol…
Imperial College London（伦敦帝国理工学院）；DeepMind（深度思维）；Lancaster University（兰卡斯特大学）；University of Oxford（牛津大学）
Deep neural networks have been extremely successful as highly accurate wave function ansätze for variational Monte Carlo calculations of molecular ground states. We present an extension of one such ansatz, FermiNet, to calculations of the ground states of periodic Hamiltonians, and study the homogeneous electron gas. FermiNet calculations of the ground-state energies of small electron gas systems are in excellent agreement with previous initiator full configuration interaction quantum Monte Carlo and diffusion Monte Carlo calculations. We investigate the spin-polarized homogeneous electron gas…
East China University of Science and Technology（华东理工大学）
Artificial neural networks learn various rules and algorithms to form different ways of processing information, and have been widely used in various chemical processes. Among them, with the development of rectification technology, its production scale continues to expand, and its calculation requirements are also more stringent, because the artificial neural network has the advantages of self-learning, associative storage and high-speed search for optimized solutions, it can make high-precision simulation predictions for rectification operations, so it is widely used in the chemical field of r…
Neural Thermodynamic Integration: Free Energies from Energy-based Diffusion Models
Institute for Theoretical Physics, Heidelberg University（海德堡大学理论物理研究所）；Department of Computer Science, University of Geneva（日内瓦大学计算机系）；Department of Physics, University of Geneva（日内瓦大学物理系）
Aplicaciones en Informática Avanzada (AIA)（高级信息应用公司）；University of Geneva（日内瓦大学）
The generation of accurate neutrino-nucleus cross-section models needed for neutrino oscillation experiments require simultaneously the description of many degrees of freedom and precise calculations to model nuclear responses. The detailed calculation of complete models makes the Monte Carlo generators slow and impractical. We present Exhaustive Neural Importance Sampling (ENIS), a method based on normalizing flows to find a suitable proposal density for rejection sampling automatically and efficiently, and discuss how this technique solves common issues of the rejection algorithm.
Binary neural networks have attracted tremendous attention due to the efficiency for deploying them on mobile devices. Since the weak expression ability of binary weights and features, their accuracy is usually much lower than that of full-precision (i.e. 32-bit) models. Here we present a new frame work for automatically searching for compact but accurate binary neural networks. In practice, number of channels in each layer will be encoded into the search space and optimized using the evolutionary algorithm. Experiments conducted on benchmark datasets and neural architectures demonstrate that …
United Kingdom Atomic Energy Authority（英国原子能管理局）；The University of Hong Kong（香港大学）
We devise a new type of feedforward neural network. It is equivariant with respect to the unitary group $U(n)$. The input and output can be vectors in $\mathbb{C}^n$ with arbitrary dimension $n$. No convolution layer is required in our implementation. We avoid errors due to truncated higher order terms in Fourier-like transformation. The implementation of each layer can be done efficiently using simple calculations. As a proof of concept, we have given empirical results on the prediction of the dynamics of atomic motion to demonstrate the practicality of our approach.
In view of the large amount of calculation and long calculation time of convolutional neural network (CNN), this paper proposes a convolutional neural network hardware accelerator based on field programmable logic gate array (FPGA). First, through in-depth analysis of the forward operation principle of the convolutional layer and exploration of the parallelism of the convolutional layer operation, a hardware architecture of input channel parallelism, output channel parallelism and convolution window deep pipeline is designed. Then in the above architecture, a fully parallel multiplication-addi…
University of Chicago（芝加哥大学）；University of Texas Austin（德克萨斯大学奥斯汀分校）；Peking University（北京大学）
In this paper, we develop a novel regularization method for deep neural networks by penalizing the trace of Hessian. This regularizer is motivated by a recent guarantee bound of the generalization error. We explain its benefits in finding flat minima and avoiding Lyapunov stability in dynamical systems. We adopt the Hutchinson method as a classical unbiased estimator for the trace of a matrix and further accelerate its calculation using a dropout scheme. Experiments demonstrate that our method outperforms existing regularizers and data augmentation methods, such as Jacobian, Confidence Penalty…
SLAC National Accelerator Laboratory（SLAC国家加速器实验室）
Particle accelerators support a wide array of scientific, industrial, and medical applications. To meet the needs of these applications, accelerator physicists rely heavily on detailed simulations of the complicated particle beam dynamics through the accelerator. One of the most computationally expensive and difficult-to-model effects is the impact of Coherent Synchrotron Radiation (CSR). As a beam travels through a curved trajectory (e.g. due to a bending magnet), it emits radiation that in turn interacts with the rest of the beam. At each step through the trajectory, the electromagnetic fiel…
We have developed a neural network potential energy function for use in drug discovery, with chemical element support extended from 41% to 94% of druglike molecules based on ChEMBL. We expand on the work of Smith et al., with their highly accurate network for the elements H, C, N, O, creating a network for H, C, N, O, S, F, Cl, P. We focus particularly on the calculation of relative conformer energies, for which we show that our new potential energy function has an RMSE of 0.70 kcal/mol for prospective druglike molecule conformers, substantially better than the previous state of the art. The s…
School of Electronics Engineering and Computer Science, Peking University（北京大学电子工程与计算机科学学院）；MOE Key Laboratory of Computational Linguistics, Peking University（北京大学计算语言学教育部重点实验室）
As traditional neural network consumes a significant amount of computing resources during back propagation, \citet{Sun2017mePropSB} propose a simple yet effective technique to alleviate this problem. In this technique, only a small subset of the full gradients are computed to update the model parameters. In this paper we extend this technique into the Convolutional Neural Network(CNN) to reduce calculation in back propagation, and the surprising results verify its validity in CNN: only 5\% of the gradients are passed back but the model still achieves the same effect as the traditional CNN, or …
Deep neural networks (DNN) are powerful models for many pattern recognition tasks, yet their high computational complexity and memory requirement limit them to applications on high-performance computing platforms. In this paper, we propose a new method to evaluate DNNs trained with 32bit floating point (float32) accuracy using only low precision integer arithmetics in combination with binary shift and clipping operations. Because hardware implementation of these operations is much simpler than high precision floating point calculation, our method can be used for an efficient DNN inference on d…
University of California, Berkeley（加州大学伯克利分校）；Lawrence Livermore National Lab（劳伦斯利弗莫尔国家实验室）；International Computer Science Institute, Berkeley（伯克利国际计算机科学研究所）
We derive the calculation of two critical numbers predicting the behavior of perceptron networks. First, we derive the calculation of what we call the lossless memory (LM) dimension. The LM dimension is a generalization of the Vapnik--Chervonenkis (VC) dimension that avoids structured data and therefore provides an upper bound for perfectly fitting almost any training data. Second, we derive what we call the MacKay (MK) dimension. This limit indicates a 50% chance of not being able to train a given function. Our derivations are performed by embedding a neural network into Shannon's communicati…
In many mechanistic medical, biological, physical and engineered spatiotemporal dynamic models the numerical solution of partial differential equations (PDEs) can make simulations impractically slow. Biological models require the simultaneous calculation of the spatial variation of concentration of dozens of diffusing chemical species. Machine learning surrogates, neural networks trained to provide approximate solutions to such complicated numerical problems, can often provide speed-ups of several orders of magnitude compared to direct calculation. PDE surrogates enable use of larger models th…
Nihon University（日本大学）；Tokyo City University（东京都市大学）
Recently, many convolutional neural networks (CNNs) for classification by time domain data of multisignals have been developed. Although some signals are important for correct classification, others are not. When data that do not include important signals for classification are taken as the CNN input layer, the calculation, memory, and data collection costs increase. Therefore, identifying and eliminating nonimportant signals from the input layer are important. In this study, we proposed features gradient-based signals selection algorithm (FG-SSA), which can be used for finding and removing no…
Bayesian neural networks perform variational inference over the weights however calculation of the posterior distribution remains a challenge. Our work builds on variational inference techniques for bayesian neural networks using the original Evidence Lower Bound. In this paper, we present a stochastic bayesian neural network in which we maximize Evidence Lower Bound using a new objective function which we name as Stochastic Evidence Lower Bound. We evaluate our network on 5 publicly available UCI datasets using test RMSE and log likelihood as the evaluation metrics. We demonstrate that our wo…
We establish estimations for the parameters of the output distribution for the softmax activation function using the probit function. As an application, we develop a new efficient Bayesian learning algorithm for fully connected neural networks, where training and predictions are performed within the Bayesian inference framework in closed-form. This approach allows sequential learning and requires no computationally expensive gradient calculation and Monte Carlo sampling. Our work generalizes the Bayesian algorithm for a single perceptron for binary classification in \cite{H} to multi-layer per…
Neural Network Entropy (NNetEn): Entropy-Based EEG Signal and Chaotic Time Series Classification, Python Package for NNetEn Calculation
Institute of Physics and Technology, Petrozavodsk State University（彼得罗扎沃茨克国立大学物理与技术学院）；Kuwait College of Science and Technology（科威特科学技术学院）；Vels Institute of Sciences, Technology, and Advanced Studies（维尔斯科学技术与高等研究院）；Damghan University（达姆甘大学）
University of California, Santa Barbara（加州大学圣巴巴拉分校）
Tensor decomposition is an effective approach to compress over-parameterized neural networks and to enable their deployment on resource-constrained hardware platforms. However, directly applying tensor compression in the training process is a challenging task due to the difficulty of choosing a proper tensor rank. In order to achieve this goal, this paper proposes a Bayesian tensorized neural network. Our Bayesian method performs automatic model compression via an adaptive tensor rank determination. We also present approaches for posterior density calculation and maximum a posteriori (MAP) est…
Tsinghua University（清华大学）；Rutgers University（罗格斯大学）；Carnegie Mellon University（卡内基梅隆大学）；People’s Public Security University（人民公安大学）
This paper focuses on sentiment mining and sentiment correlation analysis of web events. Although neural network models have contributed a lot to mining text information, little attention is paid to analysis of the inter-sentiment correlations. This paper fills the gap between sentiment calculation and inter-sentiment correlations. In this paper, the social emotion is divided into six categories: love, joy, anger, sadness, fear, and surprise. Two deep neural network models are presented for sentiment calculation. Three datasets - the titles, the bodies, the comments of news articles - are coll…
Identifying the influence of training data for data cleansing can improve the accuracy of deep learning. An approach with stochastic gradient descent (SGD) called SGD-influence to calculate the influence scores was proposed, but, the calculation costs are expensive. It is necessary to temporally store the parameters of the model during training phase for inference phase to calculate influence sores. In close connection with the previous method, we propose a method to reduce cache files to store the parameters in training phase for calculating inference score. We only adopt the final parameters…
AIT Austrian Institute of Technology GmbH（AIT奥地利技术研究院）；Washington University（华盛顿大学）
We introduce a class of neural networks derived from probabilistic models in the form of Bayesian networks. By imposing additional assumptions about the nature of the probabilistic models represented in the networks, we derive neural networks with standard dynamics that require no training to determine the synaptic weights, that perform accurate calculation of the mean values of the random variables, that can pool multiple sources of evidence, and that deal cleanly and consistently with inconsistent or contradictory evidence. The presented neural networks capture many properties of Bayesian ne…
InstaDeep（英斯塔迪普）；University of Oxford（牛津大学）；Russian Quantum Center（俄罗斯量子中心）
In recent years, neural network quantum states (NNQS) have emerged as powerful tools for the study of quantum many-body systems. Electronic structure calculations are one such canonical many-body problem that have attracted significant research efforts spanning multiple decades, whilst only recently being attempted with NNQS. However, the complex non-local interactions and high sample complexity are significant challenges that call for bespoke solutions. Here, we parameterise the electronic wavefunction with a novel autoregressive neural network (ARN) that permits highly efficient and scalable…
When a Convolutional Neural Network is used for on-the-fly evaluation of continuously updating time-sequences, many redundant convolution operations are performed. We propose the method of Deep Shifting, which remembers previously calculated results of convolution operations in order to minimize the number of calculations. The reduction in complexity is at least a constant and in the best case quadratic. We demonstrate that this method does indeed save significant computation time in a practical implementation, especially when the networks receives a large number of time-frames.
Edmond and Lilly Safra Center for Brain Sciences（埃德蒙与莉莉·萨夫拉脑科学中心）；The Hebrew University of Jerusalem（耶路撒冷希伯来大学）；Google Research（谷歌研究院）
In this preliminary work, we study the generalization properties of infinite ensembles of infinitely-wide neural networks. Amazingly, this model family admits tractable calculations for many information-theoretic quantities. We report analytical and empirical investigations in the search for signals that correlate with generalization.
Quantum many-body problems are some of the most challenging problems in science and are central to demystifying some exotic quantum phenomena, e.g., high-temperature superconductors. The combination of neural networks (NN) for representing quantum states, coupled with the Variational Monte Carlo (VMC) algorithm, has been shown to be a promising method for solving such problems. However, the run-time of this approach scales quadratically with the number of simulated particles, constraining the practically usable NN to - in machine learning terms - minuscule sizes (<10M parameters). Considering …
Physics-informed neural networks have been widely applied to learn general parametric solutions of differential equations. Here, we propose a neural network to discover parametric eigenvalue and eigenfunction surfaces of quantum systems. We apply our method to solve the hydrogen molecular ion. This is an ab-initio deep learning method that solves the Schrodinger equation with the Coulomb potential yielding realistic wavefunctions that include a cusp at the ion positions. The neural solutions are continuous and differentiable functions of the interatomic distance and their derivatives are analy…
This document, as the title stated, is meant to provide a vectorized implementation of adjoint dynamics calculation for Graph Convolutional Neural Ordinary Differential Equations (GCDE). The adjoint sensitivity method is the gradient approximation method for neural ODEs that replaces the back propagation. When implemented on libraries such as PyTorch or Tensorflow, the adjoint can be calculated by autograd functions without the need for a hand-derived formula. In applications such as edge computing and in memristor crossbars, however, autograds are not available, and therefore we need a vector…
Modern deep neural network training is typically based on mini-batch stochastic gradient optimization. While the use of large mini-batches increases the available computational parallelism, small batch training has been shown to provide improved generalization performance and allows a significantly smaller memory footprint, which might also be exploited to improve machine throughput. In this paper, we review common assumptions on learning rate scaling and training duration, as a basis for an experimental comparison of test performance for different mini-batch sizes. We adopt a learning rate th…
University of Notre Dame（圣母大学）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）
Simulations of high-energy density physics often need non-local thermodynamic equilibrium (NLTE) opacity data. This data, however, is expensive to produce at relatively low-fidelity. It is even more so at high-fidelity such that the opacity calculations can contribute ninety-five percent of the total computation time. This proportion can even reach large proportions. Neural networks can be used to replace the standard calculations of low-fidelity data, and the neural networks can be trained to reproduce artificial, high-fidelity opacity spectra. In this work, it is demonstrated that a novel ne…
