Author name cluster

Shan Wu

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

2 author rows

ICML Conference 2025 Conference Paper

SBGD: Improving Graph Diffusion Generative Model via Stochastic Block Diffusion

Junwei Su
Shan Wu

Graph diffusion generative models (GDGMs) have emerged as powerful tools for generating high-quality graphs. However, their broader adoption faces challenges in scalability and size generalization. GDGMs struggle to scale to large graphs due to their high memory requirements, as they typically operate in the full graph space, requiring the entire graph to be stored in memory during training and inference. This constraint limits their feasibility for large-scale real-world graphs. GDGMs also exhibit poor size generalization, with limited ability to generate graphs of sizes different from those in the training data, restricting their adaptability across diverse applications. To address these challenges, we propose the stochastic block graph diffusion (SBGD) model, which refines graph representations into a block graph space. This space incorporates structural priors based on real-world graph patterns, significantly reducing memory complexity and enabling scalability to large graphs. The block representation also improves size generalization by capturing fundamental graph structures. Empirical results show that SBGD achieves significant memory improvements (up to 6$\times$) while maintaining comparable or even superior graph generation performance relative to state-of-the-art methods. Furthermore, experiments demonstrate that SBGD better generalizes to unseen graph sizes. The significance of SBGD extends beyond being a scalable and effective GDGM; it also exemplifies the principle of modularization in generative modelling, offering a new avenue for exploring generative models by decomposing complex tasks into more manageable components.

Details

AAAI Conference 2025 Conference Paper

Temporal-Aware Evaluation and Learning for Temporal Graph Neural Networks

Junwei Su
Shan Wu

Temporal Graph Neural Networks (TGNNs) are a family of graph neural networks designed to model and learn dynamic information from temporal graphs. Given their substantial empirical success, there is an escalating interest in TGNNs within the research community. However, the majority of these efforts have been channelled towards algorithm and system design, with the evaluation metrics receiving comparatively less attention. Effective evaluation metrics are crucial for providing detailed performance insights, particularly in the temporal domain. This paper investigates the commonly used evaluation metrics for TGNNs and illustrates the failure mechanisms of these metrics in capturing essential temporal structures in the predictive behaviour of TGNNs. We provide a mathematical formulation of existing performance metrics and utilize an instance-based study to underscore their inadequacies in identifying volatility clustering (the occurrence of emerging errors within a brief interval). This phenomenon has profound implications for both algorithm and system design in the temporal domain. To address this deficiency, we introduce a new volatility-aware evaluation metric (termed volatility cluster statistics), designed for a more refined analysis of model temporal performance. Additionally, we demonstrate how this metric can serve as a temporal-volatility-aware training objective to alleviate the clustering of temporal errors. Through comprehensive experiments on various TGNN models, we validate our analysis and the proposed approach. The empirical results offer revealing insights: 1) existing TGNNs are prone to making errors with volatility clustering, and 2) TGNNs with different mechanisms to capture temporal information exhibit distinct volatility clustering patterns. Moreover, our empirical findings demonstrate that our proposed training objective effectively reduces volatility clusters in error.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Dialogue Rewriting via Skeleton-Guided Generation

Chunlei Xin
Hongyu Lin
Shan Wu
Xianpei Han
Bo Chen
Wen Dai
Shuai Chen
Bin Wang

Dialogue rewriting aims to transform multi-turn, context-dependent dialogues into well-formed, context-independent text for most NLP systems. Previous dialogue rewriting benchmarks and systems assume a fluent and informative utterance to rewrite. Unfortunately, dialogue utterances from real-world systems are frequently noisy and with various kinds of errors that can make them almost uninformative. In this paper, we first present Real-world Dialogue Rewriting Corpus (RealDia), a new benchmark to evaluate how well current dialogue rewriting systems can deal with real-world noisy and uninformative dialogue utterances. RealDia contains annotated multi-turn dialogues from real scenes with ASR errors, spelling errors, redundancies and other noises that are ignored by previous dialogue rewriting benchmarks. We show that previous dialogue rewriting approaches are neither effective nor data-efficient to resolve RealDia. Then this paper presents Skeleton-Guided Rewriter (SGR), which can resolve the task of dialogue rewriting via a skeleton-guided generation paradigm. Experiments show that RealDia is a much more challenging benchmark for real-world dialogue rewriting, and SGR can effectively resolve the task and outperform previous approaches by a large margin.

PDF Details DOI

JBHI Journal 2020 Journal Article

Detection and Monitoring of Thermal Lesions Induced by Microwave Ablation Using Ultrasound Imaging and Convolutional Neural Networks

Siyuan Zhang
Shan Wu
Shaoqiang Shang
Xuewei Qin
Xin Jia
Dapeng Li
Zhiwei Cui
Tianqi Xu

Microwave ablation (MWA) for cancer treatment is frequently monitored by ultrasound (US) B-mode imaging in the clinic, which often fails due to the low intrinsic contrast between the thermal lesion and normal tissue. Deep learning, especially convolutional neural network (CNN), has shown significant improvements in medical image analysis. Here, we propose and evaluate an US imaging based on a CNN architecture for the detection and monitoring of thermal lesions induced by MWA in porcine livers. Unlike dealing with images in many visual object recognition tasks, US radiofrequency (RF) data backscattered from the ablated region were utilized to capture features related to the thermal lesion. The dataset comprised of 1640 US RF envelope data matrices and their corresponding gross-pathology images, and were utilized for training and testing. After envelope detection, US B-mode, segmentation results based on CNN (SI CNN ), and modified CNN (SI m-CNN ) for US data were simultaneously reconstructed to reveal the suitability for monitoring of MWA. The SI CNN and SI m-CNN outperformed B-mode images for the detection and monitoring of MWA-induced thermal lesions. The values of the area under the receiver operating characteristic curve were 0. 8728 and 0. 8948 for the SI CNN and Si m-CNN, respectively, which were both higher than the value of 0. 6904 for B-mode images. Ablated regions that were assessed using SI m-CNN showed a good correlation (J 0. 8845, r 0. 8739, and E 0. 410) to gross-pathology images. This study was the first to illustrate that SI m-CNN has the potential to detect and monitor thermal lesions, and may be utilized as an alternative modality for image-guided MWA treatments.

Details DOI

AAAI Conference 2018 Conference Paper

Variational Recurrent Neural Machine Translation

Jinsong Su
Shan Wu
Deyi Xiong
Yaojie Lu
Xianpei Han
Biao Zhang

Partially inspired by successful applications of variational recurrent neural networks, we propose a novel variational recurrent neural machine translation (VRNMT) model in this paper. Different from the variational NMT, VRNMT introduces a series of latent random variables to model the translation procedure of a sentence in a generative way, instead of a single latent variable. Specifically, the latent random variables are included into the hidden states of the NMT decoder with elements from the variational autoencoder. In this way, these variables are recurrently generated, which enables them to further capture strong and complex dependencies among the output translations at different timesteps. In order to deal with the challenges in performing efficient posterior inference and large-scale training during the incorporation of latent variables, we build a neural posterior approximator, and equip it with a reparameterization technique to estimate the variational lower bound. Experiments on Chinese-English and English-German translation tasks demonstrate that the proposed model achieves significant improvements over both the conventional and variational NMT models.

PDF Details

AAAI Conference 2017 Conference Paper

Capturing Dependencies among Labels and Features for Multiple Emotion Tagging of Multimedia Data

Shan Wu
Shangfei Wang
Qiang Ji

In this paper, we tackle the problem of emotion tagging of multimedia data by modeling the dependencies among multiple emotions in both the feature and label spaces. These dependencies, which carry crucial top-down and bottom-up evidence for improving multimedia affective content analysis, have not been thoroughly exploited yet. To this end, we propose two hierarchical models that independently and dependently learn the shared features and global semantic relationships among emotion labels to jointly tag multiple emotion labels of multimedia data. Efﬁcient learning and inference algorithms of the proposed models are also developed. Experiments on three benchmark emotion databases demonstrate the superior performance of our methods to existing methods.

PDF Details