Shuang Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Shuang Wang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Hakan Ferhatosmanoglu
University of Warwick
2 shared publications - Aparajita Haldar
University of Warwick, Coventry, UK
1 shared publication - Bahaeddin Eravci
Department of Artificial Intelligence Engineering, TOBB University of Economics and Technology, Ankara, Türkiye
1 shared publication - Gunduz Vehbi Demirci
Imagination Technologies, Coventry, UK
1 shared publication - Haijun Zhang
Harbin Institute of Technology
1 shared publication - Heng Yue
Singapore Management University - School of Accountancy
1 shared publication
Latest Publications
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 2626-2636
Low-bit Quantization for Deep Graph Neural Networks with Smoothness-aware Message Propagation
Graph Neural Network (GNN) training and inference involve significant challenges of scalability with respect to both model sizes and number of layers, resulting in degradation of efficiency and accuracy for large and deep GNNs. We present an end-to-end solution that aims to address these challenges for efficient GNNs in resource constrained environments while avoiding the oversmoothing problem in deep GNNs. We introduce a quantization based approach for all stages of GNNs, from message passing in training to node classification, compressing the model and enabling efficient processing. The proposed GNN quantizer learns quantization ranges and reduces the model size with comparable accuracy even under low-bit quantization. To scale with the number of layers, we devise a message propagation mechanism in training that controls layer-wise changes of similarities between neighboring nodes. This objective is incorporated into a Lagrangian function with constraints and a differential multiplier method is utilized to iteratively find optimal embeddings. This mitigates oversmoothing and suppresses the quantization error to a bound. Significant improvements are demonstrated over state-of-the-art quantization methods and deep GNN approaches in both full-precision and quantized models. The proposed quantizer demonstrates superior performance in INT2 configurations across all stages of GNN, achieving a notable level of accuracy. In contrast, existing quantization approaches fail to generate satisfactory accuracy levels. Finally, the inference with INT2 and INT4 representations exhibits a speedup of 5.11 × and 4.70 × compared to full precision counterparts, respectively.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 2626-2636
Open AccessLow-bit Quantization for Deep Graph Neural Networks with Smoothness-aware Message Propagation
Graph Neural Network (GNN) training and inference involve significant challenges of scalability with respect to both model sizes and number of layers, resulting in degradation of efficiency and accuracy for large and deep GNNs. We present an end-to-end solution that aims to address these challenges for efficient GNNs in resource constrained environments while avoiding the oversmoothing problem in deep GNNs. We introduce a quantization based approach for all stages of GNNs, from message passing in training to node classification, compressing the model and enabling efficient processing. The proposed GNN quantizer learns quantization ranges and reduces the model size with comparable accuracy even under low-bit quantization. To scale with the number of layers, we devise a message propagation mechanism in training that controls layer-wise changes of similarities between neighboring nodes. This objective is incorporated into a Lagrangian function with constraints and a differential multiplier method is utilized to iteratively find optimal embeddings. This mitigates oversmoothing and suppresses the quantization error to a bound. Significant improvements are demonstrated over state-of-the-art quantization methods and deep GNN approaches in both full-precision and quantized models. The proposed quantizer demonstrates superior performance in INT2 configurations across all stages of GNN, achieving a notable level of accuracy. In contrast, existing quantization approaches fail to generate satisfactory accuracy levels. Finally, the inference with INT2 and INT4 representations exhibits a speedup of 5.11 × and 4.70 × compared to full precision counterparts, respectively.
- Open Access
- 12 April 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Spatial Algorithms and Systems
- Vol. 9 (2) , 1-30
Temporal Cascade Model for Analyzing Spread in Evolving Networks
Current approaches for modeling propagation in networks (e.g., of diseases, computer viruses, rumors) cannot adequately capture temporal properties such as order/duration of evolving connections or dynamic likelihoods of propagation along connections. Temporal models on evolving networks are crucial in applications that need to analyze dynamic spread. For example, a disease spreading virus has varying transmissibility based on interactions between individuals occurring with different frequency, proximity, and venue population density. Similarly, propagation of information having a limited active period, such as rumors, depends on the temporal dynamics of social interactions. To capture such behaviors, we first develop the Temporal Independent Cascade (T-IC) model with a spread function that efficiently utilizes a hypergraph-based sampling strategy and dynamic propagation probabilities. We prove this function to be submodular, with guarantees of approximation quality. This enables scalable analysis on highly granular temporal networks where other models struggle, such as when the spread across connections exhibits arbitrary temporally evolving patterns. We then introduce the notion of “reverse spread” using the proposed T-IC processes, and develop novel solutions to identify both sentinel/detector nodes and highly susceptible nodes. Extensive analysis on real-world datasets shows that the proposed approach significantly outperforms the alternatives in modeling both if and how spread occurs, by considering evolving network topology alongside granular contact/interaction information. Our approach has numerous applications, such as virus/rumor/influence tracking. Utilizing T-IC, we explore vital challenges of monitoring the impact of various intervention strategies over real spatio-temporal contact networks where we show our approach to be highly effective.
- 12 April 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Spatial Algorithms and Systems
- Vol. 9 (2) , 1-30
Open AccessTemporal Cascade Model for Analyzing Spread in Evolving Networks
Current approaches for modeling propagation in networks (e.g., of diseases, computer viruses, rumors) cannot adequately capture temporal properties such as order/duration of evolving connections or dynamic likelihoods of propagation along connections. Temporal models on evolving networks are crucial in applications that need to analyze dynamic spread. For example, a disease spreading virus has varying transmissibility based on interactions between individuals occurring with different frequency, proximity, and venue population density. Similarly, propagation of information having a limited active period, such as rumors, depends on the temporal dynamics of social interactions. To capture such behaviors, we first develop the Temporal Independent Cascade (T-IC) model with a spread function that efficiently utilizes a hypergraph-based sampling strategy and dynamic propagation probabilities. We prove this function to be submodular, with guarantees of approximation quality. This enables scalable analysis on highly granular temporal networks where other models struggle, such as when the spread across connections exhibits arbitrary temporally evolving patterns. We then introduce the notion of “reverse spread” using the proposed T-IC processes, and develop novel solutions to identify both sentinel/detector nodes and highly susceptible nodes. Extensive analysis on real-world datasets shows that the proposed approach significantly outperforms the alternatives in modeling both if and how spread occurs, by considering evolving network topology alongside granular contact/interaction information. Our approach has numerous applications, such as virus/rumor/influence tracking. Utilizing T-IC, we explore vital challenges of monitoring the impact of various intervention strategies over real spatio-temporal contact networks where we show our approach to be highly effective.
- 3 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5006-5013
Learning to link human objects in videos and advertisements with clothes retrieval
In this paper, we present a new method for human object-level video advertising. A framework that aims to embed content-relevant ads within a video stream is investigated in this context. In particular, to support content-relevant advertising, we employ the discriminatively trained part based model to detect human objects in a video and then select the ads that are related to the detected human objects. For human clothing advertising, we design a deep Convolutional Neural Network (CNN) using face features to recognize human genders in a video stream. Human parts alignment is then implemented to extract human part features that are used for clothes retrieval. Our novel framework is examined in various types of videos. Experimental results demonstrate the effectiveness of the proposed method for human object-level video advertising.
- 3 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5006-5013
Learning to link human objects in videos and advertisements with clothes retrieval
In this paper, we present a new method for human object-level video advertising. A framework that aims to embed content-relevant ads within a video stream is investigated in this context. In particular, to support content-relevant advertising, we employ the discriminatively trained part based model to detect human objects in a video and then select the ads that are related to the detected human objects. For human clothing advertising, we design a deep Convolutional Neural Network (CNN) using face features to recognize human genders in a video stream. Human parts alignment is then implemented to extract human part features that are used for clothes retrieval. Our novel framework is examined in various types of videos. Experimental results demonstrate the effectiveness of the proposed method for human object-level video advertising.