Shikun Zhang

Liaocheng University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Distributed adaptive finite-time and fixed-time cluster synchronization of complex networks

Journal of the Franklin Institute (2025)

Shikun Zhang Dan Liu Xiaohong Cui Kun Zhou Binrui Wang

10.1016/j.jfranklin.2025.107533

Cite

Citations (0)

Correctness verification of synchronization based workflow model

Cai Jian Wen Zhao Shikun Zhang Lifu Wang

Workflow management systems facilitate the everyday operation of business processes by taking care of the logistic control of work. In contrast to traditional information systems, they attempt to support frequent changes of the workflows at hand. Therefore, the need for analysis methods to verify the correctness of workflows is becoming more prominent. In this paper, we present a method for correctness verification of synchronization based workflow model. Moreover, the method can give a counterexample when an error exists in model, this will help to improve the model

Counterexample

10.1109/icebe.2005.43

Cite

Citations (1)

Graph Enhanced Dual Attention Network for Document-Level Relation Extraction

Proceedings of the 17th international conference on Computational linguistics - (2020)

Bo Li Wei Ye Zhonghao Sheng Rui Xie Xiangyu Xi

Document-level relation extraction requires inter-sentence reasoning capabilities to capture local and global contextual information for multiple relational facts. To improve inter-sentence reasoning, we propose to characterize the complex interaction between sentences and potential relation instances via a Graph Enhanced Dual Attention network (GEDA). In GEDA, sentence representation generated by the sentence-to-relation (S2R) attention is refined and synthesized by a Heterogeneous Graph Convolutional Network before being fed into the relation-to-sentence (R2S) attention . We further design a simple yet effective regularizer based on the natural duality of the S2R and R2S attention, whose weights are also supervised by the supporting evidence of relation instances during training. An extensive set of experiments on an existing large-scale dataset show that our model achieve competitive performance, especially for the inter-sentence relation extraction, while the neural predictions can also be interpretable and easily observed.

Relationship extraction

Representation

10.18653/v1/2020.coling-main.136

Cite

Citations (63)

Exploring Vision-Language Models for Imbalanced Learning

International Journal of Computer Vision (2023)

Yidong Wang Zhuohao Yu Jindong Wang Qiang Heng Hao Chen

Softmax function

Code (set theory)

10.1007/s11263-023-01868-w

Cite

Citations (7)

Long Text Analysis Using Sliced Recurrent Neural Networks with Breaking Point Information Enrichment

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2019)

Bo Li Zehua Cheng Zhenghua Xu Wei Ye Thomas Lukasiewicz

Sliced recurrent neural networks (SRNNs) are the state-of-the-art efficient solution for long text analysis tasks; however, their slicing operations inevitably result in long-term dependency loss in lower-level networks and thus limit their accuracy. Therefore, we propose a breaking point information enrichment mechanism to strengthen dependencies between sliced subsequences without hindering parallelization. Then, the resulting BPIE-SRNN model is further extended to a bidirectional model, BPIE-BiSRNN, to utilize the dependency information in not only the previous but also the following contexts. Experiments on four large public real-world datasets demonstrate that the BPIE-SRNN and BPIE-BiSRNN models always achieve a much better accuracy than SRNNs and BiSRNNs, while maintaining a superior training efficiency.

Program slicing

10.1109/icassp.2019.8683812

Cite

Citations (9)

Improving Embedding-based Large-scale Retrieval via Label Enhancement

Peiyang Liu Xi Wang Sen Wang Wei Ye Xiangyu Xi

Current embedding-based large-scale retrieval models are trained with 0-1 hard label that indicates whether a query is relevant to a document, ignoring rich information of the relevance degree. This paper proposes to improve embedding-based retrieval from the perspective of better characterizing the query-document relevance degree by introducing label enhancement (LE) for the first time. To generate label distribution in the retrieval scenario, we design a novel and effective supervised LE method that incorporates prior knowledge from dynamic term weighting methods into contextual embeddings. Our method significantly outperforms four competitive existing retrieval models and its counterparts equipped with two alternative LE techniques by training models with the generated label distribution as auxiliary supervision information. The superiority can be easily observed on English and Chinese large-scale retrieval tasks under both standard and cold-start settings.

Relevance

Relevance Feedback

10.18653/v1/2021.findings-emnlp.13

Cite

Citations (2)

The value of ultrasonic parameters combined with clinicopathological parameters in predicting axillary lymph node metastasis in triple-negative breast cancer

European Journal of Gynaecological Oncology (2023)

Juan Zhao Haiyang Pan Shikun Zhang Qing Zhang Ting Zhang

The clinical data of 119 patients with triple-negative breast cancer (TNBC) were retrospectively analyzed, and comparisons revealed that the differences between those who developed axillary lymph node metastasis and those who did not were statistically significant when comparing the age, histological grading of the lesions, expression of Ki-67, and information about the morphology of the lesions, internal blood flow, and the ultrasonographic manifestations of axillary lymph nodes on ultrasonography of the distribution of the lesions in the lesions’ quadrants (p < 0.05). Multifactorial regression analysis suggested that age, histological grade, lesion quadrant, and axillary lymph node ultrasound performance were all relevant factors affecting axillary lymph node metastasis in TNBC patients; the predictive model of axillary lymph node metastasis in TNBC was constructed with the results of multifactorial regression analysis, and the results of the ROC curve analysis showed that the logistic regression model had an AUC of 0.761 and the sensitivity and specificity were 0.824 and 0.714, respectively, for predicting the metastasis of the axillary lymph nodes in TNBC patients. This suggests that ultrasound combined with pathological parameters has some value in helping clinical judgment of axillary lymph node metastasis in TNBC patients.

Axillary lymph nodes

Grading (engineering)

Triple-negative breast cancer

10.22514/ejgo.2023.084

Cite

Citations (0)

ISC4DGF: Enhancing Directed Grey-box Fuzzing with LLM-Driven Initial Seed Corpus Generation

arXiv (Cornell University) (2024)

Yijiang Xu Hongrui Jia Liguo Chen Xin Wang Zhengran Zeng

Fuzz testing is crucial for identifying software vulnerabilities, with coverage-guided grey-box fuzzers like AFL and Angora excelling in broad detection. However, as the need for targeted detection grows, directed grey-box fuzzing (DGF) has become essential, focusing on specific vulnerabilities. The initial seed corpus, which consists of carefully selected input samples that the fuzzer uses as a starting point, is fundamental in determining the paths that the fuzzer explores. A well-designed seed corpus can guide the fuzzer more effectively towards critical areas of the code, improving the efficiency and success of the fuzzing process. Even with its importance, many works concentrate on refining guidance mechanisms while paying less attention to optimizing the initial seed corpus. In this paper, we introduce ISC4DGF, a novel approach to generating optimized initial seed corpus for DGF using Large Language Models (LLMs). By leveraging LLMs' deep software understanding and refined user inputs, ISC4DGF creates precise seed corpus that efficiently trigger specific vulnerabilities. Implemented on AFL and tested against state-of-the-art fuzzers like AFLGo, FairFuzz, and Entropic using the Magma benchmark, ISC4DGF achieved a 35.63x speedup and 616.10x fewer target reaches. Moreover, ISC4DGF focused on more effectively detecting target vulnerabilities, enhancing efficiency while operating with reduced code coverage.

Fuzz testing

10.48550/arxiv.2409.14329

Cite

Citations (0)

When Parameter-efficient Tuning Meets General-purpose Vision-language Models

arXiv (Cornell University) (2023)

Yihang Zhai Haixin Wang Jianlong Chang Xinlong Yang Jinan Sun

Instruction tuning has shown promising potential for developing general-purpose AI capabilities by using large-scale pre-trained models and boosts growing research to integrate multimodal information for creative applications. However, existing works still face two main limitations: the high training costs and heavy computing resource dependence of full model fine-tuning, and the lack of semantic information in instructions, which hinders multimodal alignment. Addressing these challenges, this paper proposes a novel approach to utilize Parameter-Efficient Tuning for generAl-purpose vision-Language models, namely PETAL. PETAL revolutionizes the training process by requiring only 0.5% of the total parameters, achieved through a unique mode approximation technique, which significantly reduces the training costs and reliance on heavy computing resources. Furthermore, PETAL enhances the semantic depth of instructions in two innovative ways: 1) by introducing adaptive instruction mixture-of-experts(MOEs), and 2) by fortifying the score-based linkage between parameter-efficient tuning and mutual information. Our extensive experiments across five multimodal downstream benchmarks reveal that PETAL not only outperforms current state-of-the-art methods in most scenarios but also surpasses full fine-tuning models in effectiveness. Additionally, our approach demonstrates remarkable advantages in few-shot settings, backed by comprehensive visualization analyses. Our source code is available at: https://github. com/melonking32/PETAL.

Code (set theory)

10.48550/arxiv.2312.12458

Cite

Citations (0)

Formal Definition and Detection Algorithm for Passive Event in RFID Middleware

Lecture notes in computer science (2009)

Wei Ye Wen Zhao Yu Huang Wenhui Hu Shikun Zhang

Complex Event Processing

10.1007/978-3-642-00672-2_48

Cite

Citations (2)