Author name cluster

Qihe Liu

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.

6 papers

1 author row

AAAI Conference 2026 Conference Paper

Learning Adaptive and Expandable Mixture Model for Continual Learning

Fei Ye
Yongcheng Zhong
Qihe Liu
Adrian G. Bors
Jingling sun
Jinyu Guo
shijie zhou

Continuous learning constitutes a fundamental capability of artificial intelligence systems, enabling them to incrementally assimilate novel information without succumbing to catastrophic forgetting. Recent research has leveraged Pre-Trained Models (PTMs) to enhance continual learning efficacy. Nevertheless, prevailing methodologies typically depend on a singular pre-trained backbone and freeze all pre-trained parameters to mitigate network forgetting, thereby constraining adaptability to emerging tasks. In this study, we introduce an innovative PTM-based framework featuring a Dual-Representation Backbone Architecture (DRBA), which integrates both invariant and evolved representation networks to concurrently capture static and dynamic features. Building upon DRBA, we propose an Adaptive and Expandable Mixture Model (AEMM) that incrementally incorporates new expert modules with minimal parameter overhead to accommodate the learning of each novel task. To further augment adaptability, we develop a Dynamic Adaptive Representation Fusion Mechanism (DARFM) that processes outputs from both representation networks and autonomously generates data-driven adaptive weights, optimizing the contribution of each representation. This mechanism yields an adaptive, semantically enriched composite representation, thereby maximizing positive knowledge transfer. Additionally, we propose a Dynamic Knowledge Calibration Mechanism (DKCM), comprising prediction and representation calibration processes, to ensure consistency in both predictions and feature representations. This approach achieves a balance between stability and plasticity, even when learning complex datasets. Empirical evaluations substantiate that the proposed approach attains state-of-the-art performance.

PDF Details DOI

EAAI Journal 2025 Journal Article

A survey on closed-loop intelligent frameworks for parallel training of deep neural networks

Zhiyuan Ren
shijie zhou
Dong Liu
Qihe Liu

This paper proposes a novel closed-loop intelligent framework to overcome the critical challenges of computational inefficiency, memory limitations, and communication overhead in large-scale deep neural network training. Unlike conventional static or decoupled approaches, our methodology integrates environmental perception, policy decision-making, and execution optimization into a dynamic, cohesive system capable of self-adaptation. The core of our research involves a dynamic collaboration kernel for real-time hardware monitoring, a unified multi-objective cost model for Pareto-optimal resource allocation, and a generalized architecture for cross-domain deployment. Our major findings demonstrate that this framework reduces communication latency by 40% and improves training throughput by 1. 45 × in Generative Pre-trained Transformer 3 (GPT-3)-like models. It achieves a 58% reduction in end-to-end training time for 175-billion-parameter models and maintains robust performance under significant resource fluctuations, such as 30% bandwidth variations. Validation across diverse scenarios shows 81% weak scaling efficiency in computational fluid dynamics simulations and a 9. 3 × speedup for generalized linear model training on edge devices. We conclude that the framework establishes a new paradigm for scalable, adaptive, and efficient deep learning, effectively bridging the gap between system-level parallelism and algorithmic intelligence. Its generalizability offers significant potential for applications in scientific computing, edge intelligence, and next-generation model architectures.

Details DOI

NeurIPS Conference 2025 Conference Paper

Dynamic Siamese Expansion Framework for Improving Robustness in Online Continual Learning

Fei Ye
Yulong Zhao
Qihe Liu
Junlin Chen
Adrian G. Bors
Jingling sun
Rongyao Hu
shijie zhou

Continual learning requires the model to continually capture novel information without forgetting prior knowledge. Nonetheless, existing studies predominantly address the catastrophic forgetting, often neglecting enhancements in model robustness. Consequently, these methodologies fall short in real-time applications, such as autonomous driving, where data samples frequently exhibit noise due to environmental and lighting variations, thereby impairing model efficacy and causing safety issues. In this paper, we address robustness in continual learning systems by introducing an innovative approach, the Dynamic Siamese Expansion Framework (DSEF) that employs a Siamese backbone architecture, comprising static and dynamic components, to facilitate the learning of both global and local representations over time. Specifically, the proposed framework dynamically generates a lightweight expert for each novel task, leveraging the Siamese backbone to enable rapid adaptation. A novel Robust Dynamic Representation Optimization (RDRO) approach is proposed to incrementally update the dynamic backbone by maintaining all previously acquired representations and prediction patterns of historical experts, thereby fostering new task learning without inducing detrimental knowledge transfer. Additionally, we propose a novel Robust Feature Fusion (RFF) approach to incrementally amalgamate robust representations from all historical experts into the expert construction process. A novel mutual information-based technique is employed to derive adaptive weights for feature fusion by assessing the knowledge relevance between historical experts and the new task, thus maximizing positive knowledge transfer effects. A comprehensive experimental evaluation, benchmarking our approach against established baselines, demonstrates that our method achieves state-of-the-art performance even under adversarial attacks.

PDF Details

JAIR Journal 2025 Journal Article

EPINN: Enhanced Physics-Informed Neural Network for Solving Continuous Integral Equations

Zhiyuan Ren
shijie zhou
Dong Liu
Qihe Liu

Background: Integral equations play a crucial role in modeling complex systems across various scientific disciplines. However, traditional numerical methods and existing physics-informed neural networks (PINNs) face substantial challenges, including the curse of dimensionality, uncontrolled error propagation, and limited generalization capabilities. Objectives: This paper aims to overcome these limitations by developing a robust and scalable solver for high-dimensional and nonlinear integral equations. The primary goal is to achieve higher accuracy and efficiency compared to traditional methods and existing deep learning approaches. Methods: We present the enhanced physics-informed neural network (EPINN), a novel framework that incorporates three key innovations: 1) a variable-order operator decomposition theory that transforms integral equations into well-posed differential systems, thereby mitigating error accumulation, 2) a differentiable primal function projection layer that ensures physical consistency within the Sobolev spaces, and 3) a boundary-aware multi-objective training paradigm that improves generalization. Results: Experimental validation across five benchmark cases spanning two to four dimensions, including linear/nonlinear Volterra/Fredholm and hybrid Volterra-Fredholm integral equations, demonstrates the superior performance of EPINN. Compared with traditional methods, EPINN reduces relative errors by 1 to 2 orders of magnitude, while achieving over 92% accuracy with limited training data. When compared with existing deep learning solvers, EPINN provides significant improvements in computational efficiency (with a speedup factor of 3 to 6 times) and accuracy (error reduction of 23% to 85%). Conclusions: These advancements establish EPINN as a robust and scalable solver for high-dimensional and nonlinear integral equations, with wide-ranging applications in computational physics and engineering. The success of EPINN suggests that integrating physical principles with neural networks can lead to substantial improvements in solving complex mathematical problems.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Learning Multi-Source and Robust Representations for Continual Learning

Fei Ye
Yongcheng Zhong
Qihe Liu
Adrian G. Bors
Jingling sun
Rongyao Hu
shijie zhou

Plasticity and stability denote the ability to assimilate new tasks while preserving previously acquired knowledge, representing two important concepts in continual learning. Recent research addresses stability by leveraging pre-trained models to provide informative representations, yet the efficacy of these methods is highly reliant on the choice of the pre-trained backbone, which may not yield optimal plasticity. This paper addresses this limitation by introducing a streamlined and potent framework that orchestrates multiple different pre-trained backbones to derive semantically rich multi-source representations. We propose an innovative Multi-Scale Interaction and Dynamic Fusion (MSIDF) technique to process and selectively capture the most relevant parts of multi-source features through a series of learnable attention modules, thereby helping to learn better decision boundaries to boost performance. Furthermore, we introduce a novel Multi-Level Representation Optimization (MLRO) strategy to adaptively refine the representation networks, offering adaptive representations that enhance plasticity. To mitigate over-regularization issues, we propose a novel Adaptive Regularization Optimization (ARO) method to manage and optimize a switch vector that selectively governs the updating process of each representation layer, which promotes the new task learning. The proposed MLRO and ARO approaches are collectively optimized within a unified optimization framework to achieve an optimal trade-off between plasticity and stability. Our extensive experimental evaluations reveal that the proposed framework attains state-of-the-art performance. The source code of our algorithm is available at https: //github. com/CL-Coder236/LMSRR.

PDF Details

EAAI Journal 2015 Journal Article

Fast crowd density estimation with convolutional neural networks

Min Fu
Pei Xu
Xudong Li
Qihe Liu
Mao Ye
Ce Zhu

As an effective way for crowd control and management, crowd density estimation is an important research topic in artificial intelligence applications. Since the existing methods are hard to satisfy the accuracy and speed requirements of engineering applications, we propose to estimate crowd density by an optimized convolutional neural network (ConvNet). The contributions are twofold: first, convolutional neural network is first introduced for crowd density estimation. The estimation speed is significantly accelerated by removing some network connections according to the observation of the existence of similar feature maps. Second, a cascade of two ConvNet classifier has been designed, which improves both of the accuracy and speed. The method is tested on three data sets: PETS_2009, a Subway image sequence and a ground truth image sequence. Experiments confirm the good performance of the method on the same data sets compared with the state of the art works.

Details DOI