Author name cluster

Wenhuan Lu

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.

5 papers

1 author row

AAAI Conference 2026 Conference Paper

DuoKD: Dual Knowledge Distillation from Large Language Models for Robust Graph Neural Networks

Cuiying Huo
Xiaotong Huang
Dongxiao He
Yixuan Du
Wenhuan Lu
Di Jin

Graph neural networks (GNNs) have become a dominant modeling paradigm for graph-structured data, and the emergence of large language models (LLMs) has spurred growing interest in integrating external semantic knowledge into GNNs. Current LLM-based GNNs are devoted to extracting semantically similar information from LLMs to enhance representation learning. However, they generally overlook key signals that are semantically dissimilar but exhibit stronger inter-class discriminative ability. Especially when the original graph data contains noise or semantic ambiguity, a single similarity-based semantic augmentation strategy not only fails to provide effective enhancement, but may also amplify misleading signals generated by the LLM in response to low-quality inputs or its own hallucinations, further degrading the discriminative power and robustness of GNNs. To this end, we propose a dual positive-negative knowledge extraction strategy based on LLMs, and integrate it with a knowledge distillation mechanism to dynamically transfer multi-dimensional enhanced signals to GNNs, thereby achieving fine-grained and robust graph representation learning. Specifically, we design personalized prompts to guide LLMs in generating semantically similar positive signals and semantically dissimilar negative signals, which help the model capture intra-class consistency and inter-class distinction. Then, we further generate structural and semantic reasoning as supplementary knowledge to support the rationality and guidance of supervision signals. To identify high-confidence transferred knowledge, we introduce a language-based evaluation mechanism to filter low-confidence or hallucinated outputs. Finally, under a unified distillation framework, our method uses both positive and negative knowledge to guide GNN training, achieving adaptive and robust representation learning. Extensive experiments on benchmark datasets verify the superior performance of our approach across various tasks.

PDF Details DOI

AAAI Conference 2026 Conference Paper

EA-VAE: Learning to Reconstruct Dysarthric Speech via Variational Autoencoder with Encoding Alignment

Daipeng Zhang
Wenhuan Lu
Xianghu Yue
Hongcheng Zhang
Jianguo Wei

Dysarthric speech reconstruction (DSR) aims to enhance the intelligibility of dysarthric speech. Compared with normal speech, the dysarthric speech is characterized by its pathological features, including discontinuous pronunciation, slow speech, hoarseness, and improper pauses. Significant disparities in the feature space between normal and dysarthric speech may result in suboptimal speech reconstruction, thereby degrading speech intelligibility. To enhance the reconstruction ability of speech feature spaces, this paper proposes a DSR model named the Encoding-Aligned Variational Autoencoder (EA-VAE). By incorporating alignment modules of frame-level embedding features, prior distributions, and duration into the encoder of the VAE, the model explicitly aligns the dysarthric speech encoding with a representation of the parallel normal speech. A shared decoder is then used to generate speech with improved intelligibility. Experimental results on the UASpeech benchmark confirm that EA-VAE achieves state-of-the-art performance, with a 31.7% relative word error rate reduction and the highest subjective MOS score (4.48), thoroughly validating the effectiveness and advancements of the proposed method in dysarthric speech reconstruction.

PDF Details DOI

EAAI Journal 2025 Journal Article

Efficient dehazing network based on mix structure for single image with uneven haze distribution

Kangle Yuan
Jianguo Wei
Wenhuan Lu

Although the defogging algorithm based on convolutional neural networks has made significant progress on synthetic uniform foggy datasets, it still exhibits subpar performance on real non-uniform foggy images. In recent years, the transformer network has been applied in the field of image dehazing and has achieved good results in removing haze from non-uniform hazy images. However, two main issues remain: The neglect of the multi-scale characteristics of the image; And the lack of effective strategies to better combine the convolutional structure with the transformer. In this paper, we propose an efficient image dehazing network framework based on a novel hybrid structure. Specifically, the mixed structure block consists of a convolutional component utilizing a parallel attention mechanism and a Transformer architecture. This design effectively captures extensive areas of blur while simultaneously restoring texture details. Additionally, it takes into account the uneven distribution of haze, thereby addressing the challenges associated with removing uneven fog in single images more effectively. Meanwhile, we propose a fusion structure that comprises a skip branch and a main branch, enabling dynamic adjustment of the receptive field size and selection of the appropriate convolution kernel. The experimental results demonstrate that the dehazing algorithm proposed by us outperforms existing methods in terms of dehazing performance.

Details DOI

JBHI Journal 2022 Journal Article

A Progressive Generative Adversarial Method for Structurally Inadequate Medical Image Data Augmentation

ruixuan zhang
Wenhuan Lu
Xi Wei
Jialin Zhu
Han Jiang
Zhiqiang Liu
Jie Gao
Xuewei Li

The generation-based data augmentation method can overcome the challenge caused by the imbalance of medical image data to a certain extent. However, most of the current research focus on images with unified structure which are easy to learn. What is different is that ultrasound images are structurally inadequate, making it difficult for the structure to be captured by the generative network, resulting in the generated image lacks structural legitimacy. Therefore, a Progressive Generative Adversarial Method for Structurally Inadequate Medical Image Data Augmentation is proposed in this paper, including a network and a strategy. Our Progressive Texture Generative Adversarial Network alleviates the adverse effect of completely truncating the reconstruction of structure and texture during the generation process and enhances the implicit association between structure and texture. The Image Data Augmentation Strategy based on Mask-Reconstruction overcomes data imbalance from a novel perspective, maintains the legitimacy of the structure in the generated data, as well as increases the diversity of disease data interpretably. The experiments prove the effectiveness of our method on data augmentation and image reconstruction on Structurally Inadequate Medical Image both qualitatively and quantitatively. Finally, the weakly supervised segmentation of the lesion is the additional contribution of our method.

Details DOI

AAMAS Conference 2018 Conference Paper

Efficient Convention Emergence through Decoupled Reinforcement Social Learning with Teacher-Student Mechanism

Yixi Wang
Wenhuan Lu
Jianye Hao
Jianguo Wei
Ho-fung Leung

In this paper, we design reinforcement learning based (RLbased) strategies to promote convention emergence in multiagent systems (MASs) with large convention space. We apply our approaches to a language coordination problem in which agents need to coordinate on a dominant lexicon for efficient communication. By modeling each lexicon which maps each concept to a single word as a Markov strategy representation, the original single-state convention learning problem can be transformed into a multi-state multiagent coordination problem. The dynamics of lexicon evolutions during an interaction episode can be modeled as a Markov game, which allows agents to improve the action values of each concept separately and incrementally. Specifically we propose two learning strategies, multiple-Q and multiple-R, and also propose incorporating teacher-student mechanism on top of the learning strategies to accelerate lexicon convergence speed. Extensive experiments verify that our approaches outperform the state-of-the-art approaches in terms of convergence efficiency, convention quality and scalability.

PDF