papers

Publications (27)

quant-ph2025

Exploring the Nexus of Many-Body Theories through Neural Network Techniques: the Tangent Model

Senwei Liang, Karol Kowalski, Chao Yang +1

In this paper, we present a physically informed neural network representation of the effective interactions associated with coupled-cluster downfolding models to describe chemical…

physics.chem-ph2023

Probing reaction channels via reinforcement learning

Senwei Liang, Aditya N. Singh, Yuanran Zhu +2

We propose a reinforcement learning based method to identify important configurations that connect reactant and product states along chemical reaction paths. By shooting multiple t…

cs.CV2024

A Generic Shared Attention Mechanism for Various Backbone Neural Networks

Zhongzhan Huang, Senwei Liang, Mingfu Liang +1

The self-attention mechanism has emerged as a critical component for improving the performance of various backbone neural networks. However, current mainstream approaches individua…

cs.LG2020

Drop-Activation: Implicit Parameter Reduction and Harmonic Regularization

Senwei Liang, Yuehaw Khoo, Haizhao Yang

Overfitting frequently occurs in deep learning. In this paper, we propose a novel regularization method called Drop-Activation to reduce overfitting and improve generalization. The…

math.NA2021

Stationary Density Estimation of Itô Diffusions Using Deep Learning

Yiqi Gu, John Harlim, Senwei Liang +1

In this paper, we consider the density estimation problem associated with the stationary measure of ergodic Itô diffusions from a discrete-time series that approximate the solutio…

cs.CV2021

Blending Pruning Criteria for Convolutional Neural Networks

Wei He, Zhongzhan Huang, Mingfu Liang +2

The advancement of convolutional neural networks (CNNs) on various vision applications has attracted lots of attention. Yet the majority of CNNs are unable to satisfy the strict re…

cs.LG2019

Instance Enhancement Batch Normalization: an Adaptive Regulator of Batch Noise

Senwei Liang, Zhongzhan Huang, Mingfu Liang +1

Batch Normalization (BN)(Ioffe and Szegedy 2015) normalizes the features of an input image via statistics of a batch of images and hence BN will bring the noise to the gradient of…

quant-ph2024

Effective Many-body Interactions in Reduced-Dimensionality Spaces Through Neural Network Models

Senwei Liang, Karol Kowalski, Chao Yang +1

Accurately describing properties of challenging problems in physical sciences often requires complex mathematical models that are unmanageable to tackle head-on. Therefore, develop…

cs.CE2023

On Fast Simulation of Dynamical System with Neural Vector Enhanced Numerical Solver

Zhongzhan Huang, Senwei Liang, Hong Zhang +2

The large-scale simulation of dynamical systems is critical in numerous scientific and engineering disciplines. However, traditional numerical solvers are limited by the choice of…

physics.soc-ph2021

Quantifying Spatial Homogeneity of Urban Road Networks via Graph Neural Networks

Jiawei Xue, Nan Jiang, Senwei Liang +4

Quantifying the topological similarities of different parts of urban road networks (URNs) enables us to understand the urban growth patterns. While conventional statistics provide…

cs.LG2021

AlterSGD: Finding Flat Minima for Continual Learning by Alternative Training

Zhongzhan Huang, Mingfu Liang, Senwei Liang +1

Deep neural networks suffer from catastrophic forgetting when learning multiple knowledge sequentially, and a growing number of approaches have been proposed to mitigate this probl…

cs.LG2021

Reproducing Activation Function for Deep Learning

Senwei Liang, Liyao Lyu, Chunmei Wang +1

We propose reproducing activation functions (RAFs) to improve deep learning accuracy for various applications ranging from computer vision to scientific computing. The idea is to e…

math.NA2025

Finite Expression Method for Solving High-Dimensional Partial Differential Equations

Senwei Liang, Haizhao Yang

Designing efficient and accurate numerical solvers for high-dimensional partial differential equations (PDEs) remains a challenging and important topic in computational science and…

cs.CV2025

Robust Multimodal Learning for Ophthalmic Disease Grading via Disentangled Representation

Xinkun Wang, Yifang Wang, Senwei Liang +7

This paper discusses how ophthalmologists often rely on multimodal data to improve diagnostic accuracy. However, complete multimodal data is rare in real-world applications due to…

cs.LG2025

H-FEX: A Symbolic Learning Method for Hamiltonian Systems

Jasen Lai, Senwei Liang, Chunmei Wang

Hamiltonian systems describe a broad class of dynamical systems governed by Hamiltonian functions, which encode the total energy and dictate the evolution of the system. Data-drive…

cs.LG2025

Identifying Unknown Stochastic Dynamics via Finite expression methods

Senwei Liang, Chunmei Wang, Xingjian Xu

Modeling stochastic differential equations (SDEs) is crucial for understanding complex dynamical systems in various scientific fields. Recent methods often employ neural network-ba…

cs.CV2021

Efficient Attention Network: Accelerate Attention by Searching Where to Plug

Zhongzhan Huang, Senwei Liang, Mingfu Liang +2

Recently, many plug-and-play self-attention modules are proposed to enhance the model generalization by exploiting the internal information of deep convolutional neural networks (C…

math.NA2025

Solving High-Dimensional Partial Integral Differential Equations: The Finite Expression Method

Gareth Hardwick, Senwei Liang, Haizhao Yang

In this paper, we introduce a new finite expression method (FEX) to solve high-dimensional partial integro-differential equations (PIDEs). This approach builds upon the original FE…

quant-ph2024

Optimizing Shot Assignment in Variational Quantum Eigensolver Measurement

Linghua Zhu, Senwei Liang, Chao Yang +1

The rapid progress in quantum computing has opened up new possibilities for tackling complex scientific problems. Variational quantum eigensolver (VQE) holds the potential to solve…

cs.CV2022

The Lottery Ticket Hypothesis for Self-attention in Convolutional Neural Network

Zhongzhan Huang, Senwei Liang, Mingfu Liang +3

Recently many plug-and-play self-attention modules (SAMs) are proposed to enhance the model generalization by exploiting the internal information of deep convolutional neural netwo…

quant-ph2024

Artificial-Intelligence-Driven Shot Reduction in Quantum Measurement

Senwei Liang, Linghua Zhu, Xiaolin Liu +2

Variational Quantum Eigensolver (VQE) provides a powerful solution for approximating molecular ground state energies by combining quantum circuits and classical computers. However,…

math.NA2020

Machine Learning for Prediction with Missing Dynamics

John Harlim, Shixiao W. Jiang, Senwei Liang +1

This article presents a general framework for recovering missing dynamical systems using available data and machine learning techniques. The proposed framework reformulates the pre…

quant-ph2025

QuGStep: Refining Step Size Selection in Gradient Estimation for Variational Quantum Algorithms

Senwei Liang, Linghua Zhu, Xiaosong Li +1

Variational quantum algorithms (VQAs) offer a promising approach to solving computationally demanding problems by combining parameterized quantum circuits with classical optimizati…

cs.LG2024

Learning Epidemiological Dynamics via the Finite Expression Method

Jianda Du, Senwei Liang, Chunmei Wang

Modeling and forecasting the spread of infectious diseases is essential for effective public health decision-making. Traditional epidemiological models rely on expert-defined frame…

cs.LG2023

Learning nonlinear integral operators via Recurrent Neural Networks and its application in solving Integro-Differential Equations

Hardeep Bassi, Yuanran Zhu, Senwei Liang +4

In this paper, we propose using LSTM-RNNs (Long Short-Term Memory-Recurrent Neural Networks) to learn and represent nonlinear integral operators that appear in nonlinear integro-di…

math.NA2024

Solving PDEs on Unknown Manifolds with Machine Learning

Senwei Liang, Shixiao W. Jiang, John Harlim +1

This paper proposes a mesh-free computational framework and machine learning theory for solving elliptic PDEs on unknown manifolds, identified with point clouds, based on diffusion…

cs.CV2019

DIANet: Dense-and-Implicit Attention Network

Zhongzhan Huang, Senwei Liang, Mingfu Liang +1

Attention networks have successfully boosted the performance in various vision problems. Previous works lay emphasis on designing a new attention module and individually plug them…