Author name cluster

Chuan He

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

1 author row

EAAI Journal 2026 Journal Article

Deep active sequential learning of stress evolution in early-age concrete informed by thermo-chemo-mechanical modelling

Minfei Liang
Yong Fang
Wenqi Guo
Chuan He
Erik Schlangen
Branko Šavija
Sonia Contera

This study presents an integrated finite-element–machine-learning framework for predicting early-age stress evolution in concrete materials/structures by combining an enhanced thermo-chemo-mechanical (TCM) model, deep sequential learning (DSL), and active learning (AL). The proposed TCM model incorporates experimentally informed viscoelasticity, a stable exponential creep–relaxation conversion, and an efficient exponential algorithm for the Maxwell-chain formulation in finite element analysis, which is further validated by a temperature stress testing machine. This model generates high-fidelity stress–time data across diverse mixtures, temperatures, and structural configurations. These simulations are used to train a Gated Recurrent Unit with Monte Carlo Dropout (GRU-MCD) model, whose predictive performance surpasses conventional point-wise approaches such as Light Gradient Boosting Machine and Gaussian Process Regression, yielding higher accuracy with reduced overfitting. The AL strategy further enhances efficiency by enabling the GRU-MCD model to achieve the accuracy of ∼900 Latin Hypercube samples using only ∼200 samples selected by active learning. Although demonstrated on a wall–base structure, the proposed framework is general and applicable to other cementitious material or structural systems, providing an effective tool for cracking-risk evaluation, reliability analysis, and the design of low-carbon concrete structures.

Details DOI

AAAI Conference 2026 Conference Paper

M²VAE: Multi-Modal Multi-View Variational Autoencoder for Cold-start Item Recommendation

Chuan He
Yongchao Liu
Qiang Li
Chuntao Hong
Wenliang Zhong
Xin-Wei Yao

Cold-start item recommendation is a significant challenge in recommendation systems, particularly when new items are introduced without any historical interaction data. While existing methods leverage multi-modal content to alleviate the cold-start issue, they often neglect the inherent multi-view structure of modalities, namely the distinction between shared and modality-specific features. In this paper, we propose Multi-Modal Multi-View Variational AutoEncoder (M²VAE), a generative model that addresses the challenges of modeling common and unique views in attribute and multi-modal features, as well as user preferences over single-typed item features. Specifically, we generate type-specific latent variables for item IDs, categorical attributes, and image features, and use Product-of-Experts (PoE) to derive a common representation. A disentangled contrastive loss decouples the common view from unique views while preserving feature informativeness. To model user inclinations, we employ a user-aware hierarchical Mixture-of-Experts (MoE) to adaptively fuse representations. We further incorporate co-occurrence signals via contrastive learning, eliminating the need for pretraining. Extensive experiments on real-world datasets validate the effectiveness of our approach.

PDF Details DOI

EAAI Journal 2026 Journal Article

Predicting the dynamic hydrogeological response of mountain tunnels to extreme climate: an integrated physics and artificial intelligence framework

Kaiyue Wang
Chuan He
Ziquan Chen
Zuodong Xie

To mitigate safety risks posed by climate extremes to mountain tunnels, this study had developed an integrated physics–artificial intelligence framework to predict the hydrological–mechanical cascade from rainfall forcing to hydraulic head and lining stress. A three-dimensional groundwater flow model had been built using the modular finite-difference groundwater flow model software (MODFLOW) to generate transient hydraulic head fields under rainfall and drought scenarios. A local-scale tunnel mechanical model had been established using the finite element analysis software ABAQUS to produce lining stress samples. Two cascaded surrogate models had then been trained: a long short-term memory network coupled with a multilayer perceptron had been used to forecast heads from rainfall time series, and a categorical boosting regressor (CatBoost) had been used to estimate lining stresses from the predicted heads and key geological descriptors. MODFLOW had reproduced observed heads at five monitoring points with a root mean square error of 19. 87 m and a relative error of 1. 59%. Scenario analyses had shown rapid, spatially heterogeneous head rises in high-permeability zones during extreme rainfall and sustained head declines under drought. The long short-term memory network coupled with a multilayer perceptron had achieved a coefficient of determination of 0. 90 for head prediction. CatBoost had predicted maximum and minimum principal lining stresses with coefficients of determination of 0. 95 and 0. 98, respectively, and had identified high-stress segments along the tunnel alignment. Overall, the cascade surrogate strategy had enabled near-real-time rainfall-to-risk mapping with reduced computational cost, supporting operational risk assessment and drainage-oriented decision support.

Details DOI

YNIMG Journal 2025 Journal Article

Precuneus-to-hippocampus connectivity links LTP-like plasticity to cognitive function in subjective cognitive decline and mild cognitive impairment

Jie Song
Qian Lu
Shuai Zhang
Chuan He
Tianjiao Zhang
Hailang Yan
Han Yang
Huanping Wang

BACKGROUND: Disruptions in synaptic plasticity and alterations in effective connectivity (EC) involving the hippocampus and amygdala are hallmarks of early Alzheimer's disease (AD). However, the interplay between these neurophysiological changes and their relationships with cognitive functions in subjective cognitive decline (SCD) and mild cognitive impairment (MCI) remains poorly understood. METHODS: Transcranial magnetic stimulation (TMS) and resting-state functional magnetic resonance imaging (rs-fMRI) were used to assess long-term potentiation (LTP)-like plasticity and EC involving the amygdala and hippocampus in 34 individuals with SCD, 27 with MCI, and 35 healthy controls (HC). Between-group differences in cognitive performance, EC alterations, and LTP-like plasticity were examined and their relationships were assessed via correlation and mediation analyses. RESULTS: Both SCD and MCI groups exhibited disrupted EC between the amygdala/hippocampus and the inferior occipital gyrus (IOG), inferior parietal lobule (IPL), medial frontal lobe (MFL), and precuneus. Also, both LTP-5min and LTP-10min were significantly reduced in MCI group compared to SCD and HC groups. Importantly, EC from the left hippocampus to the IPL and from the IPL, MFL, and precuneus to the hippocampus was correlated with memory and executive functions. Moreover, precuneus-to-hippocampus EC was positively correlated with LTP-10min and mediated the relationship between LTP-like plasticity and cognitive performance. CONCLUSIONS: This study provides novel evidence that precuneus-to-hippocampus EC mediates the link between synaptic plasticity and cognitive function in SCD and MCI, suggesting the precuneus-hippocampus pathway as a promising target for early diagnosis and intervention.

Details DOI

JMLR Journal 2025 Journal Article

Stochastic Interior-Point Methods for Smooth Conic Optimization with Applications

Chuan He
Zhanwang Deng

Conic optimization plays a crucial role in many machine learning (ML) problems. However, practical algorithms for conic constrained ML problems with large datasets are often limited to specific use cases, as stochastic algorithms for general conic optimization remain underdeveloped. To fill this gap, we introduce a stochastic interior-point method (SIPM) framework for general conic optimization, along with four novel SIPM variants leveraging distinct stochastic gradient estimators. Under mild assumptions, we establish the iteration complexity of our proposed SIPMs, which, up to a polylogarithmic factor, matches the best-known results in stochastic unconstrained optimization. Finally, our numerical experiments on robust linear regression, multi-task relationship learning, and clustering data streams demonstrate the effectiveness and efficiency of our approach. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2025. ( edit, beta )

PDF Details

TMLR Journal 2024 Journal Article

Federated Learning with Convex Global and Local Constraints

Chuan He
Le Peng
Ju Sun

In practice, many machine learning (ML) problems come with constraints, and their applied domains involve distributed sensitive data that cannot be shared with others, e.g., in healthcare. Collaborative learning in such practical scenarios entails federated learning (FL) for ML problems with constraints, or FL with constraints for short. Despite the extensive developments of FL techniques in recent years, these techniques only deal with unconstrained FL problems or FL problems with simple constraints that are amenable to easy projections. There is little work dealing with FL problems with general constraints. To fill this gap, we take the first step toward building an algorithmic framework for solving FL problems with general constraints. In particular, we propose a new FL algorithm for constrained ML problems based on the proximal augmented Lagrangian (AL) method. %The subproblems of our proposed algorithm are solved by an inexact alternating direction method of multipliers (ADMM). Assuming convex objective and convex constraints plus other mild conditions, we establish the worst-case complexity of the proposed algorithm. Our numerical experiments show the effectiveness of our algorithm in performing Neyman-Pearson classification and fairness-aware learning with nonconvex constraints, in an FL setting.

PDF Details

JMLR Journal 2023 Journal Article

A Parameter-Free Conditional Gradient Method for Composite Minimization under Hölder Condition

Masaru Ito
Zhaosong Lu
Chuan He

In this paper we consider a composite optimization problem that minimizes the sum of a weakly smooth function and a convex function with either a bounded domain or a uniformly convex structure. In particular, we first present a parameter-dependent conditional gradient method for this problem, whose step sizes require prior knowledge of the parameters associated with the Hölder continuity of the gradient of the weakly smooth function, and establish its rate of convergence. Given that these parameters could be unknown or known but possibly conservative, such a method may suffer from implementation issue or slow convergence. We therefore propose a parameter-free conditional gradient method whose step size is determined by using a constructive local quadratic upper approximation and an adaptive line search scheme, without using any problem parameter. We show that this method achieves the same rate of convergence as the parameter-dependent conditional gradient method. Preliminary experiments are also conducted and illustrate the superior performance of the parameter-free conditional gradient method over the methods with some other step size rules. [abs] [ pdf ][ bib ] &copy JMLR 2023. ( edit, beta )

PDF Details