Author name cluster

Jianguo Wei

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.

10 papers

1 author row

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

IJCAI Conference 2025 Conference Paper

Attribute Association Driven Multi-Task Learning for Session-based Recommendation

Xinyao Wang
Zhizhi Yu
Dongxiao He
Liang Yang
Jianguo Wei
Di Jin

Session-based Recommendation (SBR) aims to predict users’ next interaction based on their current session without relying on long-term profiles. Despite its effectiveness in privacy-preserving and real-time scenarios, SBR remains challenging due to limited behavioral signals. Prior methods often overfit co-occurrence patterns, neglecting semantic priors like item attributes. Recent studies have attempted to incorporate item attributes (e. g. , category) by assigning fixed embeddings shared across all sessions. However, such approaches suffer from two key limitations: 1) Static attribute encoding fails to reflect semantic shifts under different session contexts. 2) Semantic misalignment between attribute and item ID embeddings. To address these issues, we propose attribute association driven multi-task learning for SBR, dubbed A²D-MTL. It explicitly models item categories using cross-session context to capture user potential interests and designs an adaptive sparse attention mechanism to suppress noise. Experimental results on three public datasets demonstrate the superiority of our method in recommendation accuracy (P@20) and ranking quality (MRR@20), validating the model’s effectiveness.

PDF Details DOI

JBHI Journal 2025 Journal Article

BFGTP: A BERT-Guided Two-Stage Molecular Representation Learning Framework for Toxicity Prediction

Kaimiao Hu
Yuan He
Jianguo Wei
Changming Sun
Jie Geng
Leyi Wei
Ran Su

Accurate prediction of molecular toxicity is vital for drug development. Most mainstream methods rely on fingerprints or graph-based feature extraction, the emergence of large language models (LLMs) offers new prospects for molecular representation learning in toxicity prediction. Although several studies attempt to leverage LLMs to integrate molecular sequence data for pretraining molecular representations, certain limitations remain. Current LLM-based approaches usually utilize solely on class embedding features, overlooking the rich information in sequence embedding. Moreover, integrating pre-trained molecular representations with multi-modal molecular data may further enhance performance in toxicity prediction. To address these challenges, we propose BFGTP, a BERT-guided two-stage molecular representation learning framework for toxicity prediction. Firstly, we design independent encoders for molecular descriptions of three modalities, where the fingerprint encoder with dual level attention mechanisms effectively integrates multi-category fingerprints. Then, the two-stage guide strategy is introduced to fully utilize the prior knowledge of LLMs, employing contrastive learning to align and fuse the tri-modal representations and knowledge distillation to align predicted value distributions. BFGTP ultimately combines fingerprint and graph representations to predict molecular toxicity. Experiments on seven toxicity datasets show that BFGTP outperforms baselines, achieving the highest AUC on five datasets and the best average performance across five evaluation metrics. Ablation studies, t-SNE visualization and case study confirm the effectiveness of BFGTP's components and its ability to capture meaningful molecular representations.

Details DOI

AAAI Conference 2025 Conference Paper

Dynamic Neighborhood Modeling via Node-Subgraph Contrastive Learning for Graph-Based Fraud Detection

Zhizhi Yu
Chundong Liang
Xinglong Chang
Dongxiao He
Di Jin
Jianguo Wei

Fraud detection that aims to discern frauds from the majority of benigns has become an increasingly prominent research field. Recently, Graph Neural Networks (GNNs) have been widely applied in graph-based fraud detection due to their outstanding data analysis and mining capabilities. However, owing to the inherent homophily-heterophily mixture and class imbalance of fraud graphs, most GNNs with homophily assumption inevitably suffer from local abnormal signal loss during information propagation, posing significant challenges in situations where frauds are rare and valuable. To address the aforementioned issues, we present a novel dynamic neighborhood modeling via node-subgraph contrastive learning for graph-based fraud detection, dubbed DCL-GFD. Specifically, we first design a node abnormality estimation module from the perspective of feature, which analyses the likelihood of a node belonging to fraud or benign by comparing the feature similarity between the target node and its corresponding subgraph. We then present a dynamic neighborhood modeling mechanism guided by the abnormal probability of a node to adaptively group and aggregate neighborhood information. By this means, the target node can effectively aggregate the neighbor information from the perspective of fraud or benign, thereby preserving as much fraud characteristics that occupy minority population as possible. Extensive experiments across four real-world fraud detection datasets demonstrate the superiority and effectiveness of our proposed DCL-GFD over state-of-the-art baselines.

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

IJCAI Conference 2024 Conference Paper

Generalized Taxonomy-Guided Graph Neural Networks

Yu Zhou
Di Jin
Jianguo Wei
Dongxiao He
Zhizhi Yu
Weixiong Zhang

Graph neural networks have been demonstrated to be effective analytic apparatus for mining network data. Most real-world networks are inherently hierarchical, offering unique opportunities to acquire latent, intrinsic network organizational properties by utilizing network taxonomies. The existing approaches for learning implicit hierarchical network structures focus on introducing taxonomy to graph neural networks but often run short of exploiting the rich network semantics and structural properties in the taxonomy, resulting in poor generalizability and reusability. To address these issues, we propose generalized Taxonomy-Guided Graph Neural Networks (TG-GNN) to integrate taxonomy into network representation learning. We first construct a taxonomy representation learning module that introduces the concept of ego network to propagate and aggregate rich semantic and structural information in the taxonomy. We then design a taxonomy-guided Markov mechanism, which encapsulates taxonomy knowledge in pairwise potential functions, to refine network embeddings. Extensive experiments on various real-world networks illustrate the effectiveness of TG-GNN over the state-of-the-art methods on scenarios involving incomplete taxonomies and inductive settings.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Synergistic Dual Spatial-aware Generation of Image-to-text and Text-to-image

Yu Zhao
Hao Fei
Xiangtai Li
Libo Qin
Jiayi Ji
Hongyuan Zhu
Meishan Zhang
Min Zhang

In the visual spatial understanding (VSU) field, spatial image-to-text (SI2T) and spatial text-to-image (ST2I) are two fundamental tasks that appear in dual form. Existing methods for standalone SI2T or ST2I perform imperfectly in spatial understanding, due to the difficulty of 3D-wise spatial feature modeling. In this work, we consider modeling the SI2T and ST2I together under a dual learning framework. During the dual framework, we then propose to represent the 3D spatial scene features with a novel 3D scene graph (3DSG) representation that can be shared and beneficial to both tasks. Further, inspired by the intuition that the easier 3D$\to$image and 3D$\to$text processes also exist symmetrically in the ST2I and SI2T, respectively, we propose the Spatial Dual Discrete Diffusion (SD$^3$) framework, which utilizes the intermediate features of the 3D$\to$X processes to guide the hard X$\to$3D processes, such that the overall ST2I and SI2T will benefit each other. On the visual spatial understanding dataset VSD, our system outperforms the mainstream T2I and I2T methods significantly. Further in-depth analysis reveals how our dual learning strategy advances.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Local-Global Defense against Unsupervised Adversarial Attacks on Graphs

Di Jin
Bingdao Feng
Siqi Guo
Xiaobao Wang
Jianguo Wei
Zhen Wang

Unsupervised pre-training algorithms for graph representation learning are vulnerable to adversarial attacks, such as first-order perturbations on graphs, which will have an impact on particular downstream applications. Designing an effective representation learning strategy against white-box attacks remains a crucial open topic. Prior research attempts to improve representation robustness by maximizing mutual information between the representation and the perturbed graph, which is sub-optimal because it does not adapt its defense techniques to the severity of the attack. To address this issue, we propose an unsupervised defense method that combines local and global defense to improve the robustness of representation. Note that we put forward the Perturbed Edges Harmfulness (PEH) metric to determine the riskiness of the attack. Thus, when the edges are attacked, the model can automatically identify the risk of attack. We present a method of attention-based protection against high-risk attacks that penalizes attention coefficients of perturbed edges to encoders. Extensive experiments demonstrate that our strategies can enhance the robustness of representation against various adversarial attacks on three benchmark graphs.

PDF Details DOI

IJCAI Conference 2020 Conference Paper

Visual Encoding and Decoding of the Human Brain Based on Shared Features

Chao Li
Baolin Liu
Jianguo Wei

Using a convolutional neural network to build visual encoding and decoding models of the human brain is a good starting point for the study on relationship between deep learning and human visual cognitive mechanism. However, related studies have not fully considered their differences. In this paper, we assume that only a portion of neural network features is directly related to human brain signals, which we call shared features. In the encoding process, we extract shared features from the lower and higher layers of the neural network, and then build a non-negative sparse map to predict brain activities. In the decoding process, we use back-propagation to reconstruct visual stimuli, and use dictionary learning and a deep image prior to improve the robustness and accuracy of the algorithm. Experiments on a public fMRI dataset confirm the rationality of the encoding models, and comparing with a recently proposed method, our reconstruction results obtain significantly higher accuracy.

PDF 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