Zhuang Wang

AAAI Conference 2025 Conference Paper

STLC-KG:A Social Text Steganalysis Method Combining Large-Scale Language Models and Common-Sense Knowledge Graphs

• Zhuang Wang
• Linna Zhou
• Xuekai Chen
• Zhili Zhou
• Zhongliang Yang

Language steganography in social networks primarily focuses on embedding secret information into social media text efficiently to achieve covert communication. The misuse of such techniques could pose significant potential threats to public cyberspace, such as the spread of malicious code, commands, or viruses. Existing social text steganalysis techniques mainly focus on the analysis of individual social media texts. However, the information content in a single text is very limited, leading to poor detection performance in practical applications. To address this challenge, this paper proposes a social text steganalysis method that combines large-scale language models with common-sense knowledge graphs (STLC-KG). This method first uses knowledge graphs to expand the knowledge contained in the text under investigation, enriching its linguistic expression, and then utilizes large-scale language models to extract the linguistic features of the social text. The results of tests conducted on three mainstream social media platforms demonstrate that the proposed method significantly improves the performance of social text steganalysis.

JBHI Journal 2024 Journal Article

EEG Characteristic Comparison of Motor Imagery Between Supernumerary and Inherent Limb: Sixth-Finger MI Enhances the ERD Pattern and Classification Performance

• Zhuang Wang
• Yuan Liu
• Shuaifei Huang
• Shiyin Qiu
• Yujian Zhang
• Huimin Huang
• Xingwei An
• Dong Ming

Adding supernumerary robotic limbs (SRLs) to humans and controlling them directly through the brain are main goals for movement augmentation. However, it remains uncertain whether neural patterns different from the traditional inherent limbs motor imagery (MI) can be extracted, which is essential for high-dimensional control of external devices. In this work, we established a MI neo-framework consisting of novel supernumerary robotic sixth-finger MI (SRF-MI) and traditional right-hand MI (RH-MI) paradigms and validated the distinctness of EEG response patterns between two MI tasks for the first time. Twenty-four subjects were recruited for this experiment involving three mental tasks. Event-related spectral perturbation was adopted to supply details about event-related desynchronization (ERD). Activation region, intensity and response time (RT) of ERD were compared between SRF-MI and RH-MI tasks. Three classical classification algorithms were utilized to verify the separability between different mental tasks. And genetic algorithm aims to select optimal combination of channels for neo-framework. A bilateral sensorimotor and prefrontal modulation was found during the SRF-MI task, whereas in RH-MI only contralateral sensorimotor modulation was exhibited. The novel SRF-MI paradigm enhanced ERD intensity by a maximum of 117% in prefrontal area and 188% in the ipsilateral somatosensory-association cortex. And, a global decrease of RT was exhibited during SRF-MI tasks compared to RH-MI. Classification results indicate well separable performance among different mental tasks (88. 1% maximum for 2-class and 88. 2% maximum for 3-class). This work demonstrated the difference between the SRF-MI and RH-MI paradigms, widening the control bandwidth of the BCI system.

ICML Conference 2022 Conference Paper

DRAGONN: Distributed Randomized Approximate Gradients of Neural Networks

• Zhuang Wang
• Zhaozhuo Xu
• Xinyu Crystal Wu
• Anshumali Shrivastava
• T. S. Eugene Ng

Data-parallel distributed training (DDT) has become the de-facto standard for accelerating the training of most deep learning tasks on massively parallel hardware. In the DDT paradigm, the communication overhead of gradient synchronization is the major efficiency bottleneck. A widely adopted approach to tackle this issue is gradient sparsification (GS). However, the current GS methods introduce significant new overhead in compressing the gradients, outweighing the communication overhead and becoming the new efficiency bottleneck. In this paper, we propose DRAGONN, a randomized hashing algorithm for GS in DDT. DRAGONN can significantly reduce the compression time by up to 70% compared to state-of-the-art GS approaches, and achieve up to 3. 52x speedup in total training throughput.

ICML Conference 2020 Conference Paper

Growing Adaptive Multi-hyperplane Machines

• Nemanja Djuric
• Zhuang Wang
• Slobodan Vucetic

Adaptive Multi-hyperplane Machine (AMM) is an online algorithm for learning Multi-hyperplane Machine (MM), a classification model which allows multiple hyperplanes per class. AMM is based on Stochastic Gradient Descent (SGD), with training time comparable to linear Support Vector Machine (SVM) and significantly higher accuracy. On the other hand, empirical results indicate there is a large accuracy gap between AMM and non-linear SVMs. In this paper we show that this performance gap is not due to limited representability of the MM model, as it can represent arbitrary concepts. We set to explain the connection between the AMM and Learning Vector Quantization (LVQ) algorithms, and introduce a novel Growing AMM (GAMM) classifier motivated by Growing LVQ, that imputes duplicate hyperplanes into the MM model during SGD training. We provide theoretical results showing that GAMM has favorable convergence properties, and analyze the generalization bound of the MM models. Experiments indicate that GAMM achieves significantly improved accuracy on non-linear problems, with only slightly slower training compared to AMM. On some tasks GAMM comes close to non-linear SVM, and outperforms other popular classifiers such as Neural Networks and Random Forests.

JMLR Journal 2013 Journal Article

BudgetedSVM: A Toolbox for Scalable SVM Approximations

• Nemanja Djuric
• Liang Lan
• Slobodan Vucetic
• Zhuang Wang

We present BudgetedSVM, an open-source C++ toolbox comprising highly-optimized implementations of recently proposed algorithms for scalable training of Support Vector Machine (SVM) approximators: Adaptive Multi-hyperplane Machines, Low-rank Linearization SVM, and Budgeted Stochastic Gradient Descent. BudgetedSVM trains models with accuracy comparable to LibSVM in time comparable to LibLinear, solving non-linear problems with millions of high-dimensional examples within minutes on a regular computer. We provide command-line and Matlab interfaces to BudgetedSVM, an efficient API for handling large-scale, high- dimensional data sets, as well as detailed documentation to help developers use and further extend the toolbox. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2013. ( edit, beta )

JMLR Journal 2012 Journal Article

Breaking the Curse of Kernelization: Budgeted Stochastic Gradient Descent for Large-Scale SVM Training

• Zhuang Wang
• Koby Crammer
• Slobodan Vucetic

Online algorithms that process one example at a time are advantageous when dealing with very large data or with data streams. Stochastic Gradient Descent (SGD) is such an algorithm and it is an attractive choice for online Support Vector Machine (SVM) training due to its simplicity and effectiveness. When equipped with kernel functions, similarly to other SVM learning algorithms, SGD is susceptible to the curse of kernelization that causes unbounded linear growth in model size and update time with data size. This may render SGD inapplicable to large data sets. We address this issue by presenting a class of Budgeted SGD (BSGD) algorithms for large-scale kernel SVM training which have constant space and constant time complexity per update. Specifically, BSGD keeps the number of support vectors bounded during training through several budget maintenance strategies. We treat the budget maintenance as a source of the gradient error, and show that the gap between the BSGD and the optimal SVM solutions depends on the model degradation due to budget maintenance. To minimize the gap, we study greedy budget maintenance methods based on removal, projection, and merging of support vectors. We propose budgeted versions of several popular online SVM algorithms that belong to the SGD family. We further derive BSGD algorithms for multi-class SVM training. Comprehensive empirical results show that BSGD achieves higher accuracy than the state-of-the-art budgeted online algorithms and comparable to non-budget algorithms, while achieving impressive computational efficiency both in time and space during training and prediction. [abs] [ pdf ][ bib ] &copy JMLR 2012. ( edit, beta )

ICML Conference 2010 Conference Paper

Multi-Class Pegasos on a Budget

• Zhuang Wang
• Koby Crammer
• Slobodan Vucetic