检索结果-内蒙古大学图书馆

Web page malicious code detection based on embedded fingerprints

学校读者我要写书评

暂无评论

Qinghua Daxue Xuebao/Journal of Tsinghua University 2009年第SUPPL. 2期49卷 2208-2214页

作者： Huang, Jianjun Liang, Bin Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education School of Information Renmin University of China Beijing 100872 China

Web sites have become the main targets of many attackers. Signature-based detection needs to maintain a large signature database and Honeypot based methods are not efficient. Since attackers always make the malicious codes in Web pages difficult to detect by the browser users, their methods can be classified into various fingerprints. Various malicious codes were analyzed to identify 6 types of fingerprints. The system utilizes a spider integrated with script interpretation to fetch target Web pages and extract specific tags for detection by HTML parsing for matching with the fingerprints to detect malicious codes. This method needs fewer fingerprints than traditional detection methods and is more efficient. Results for 60 websites show that the system has a false negative rate of 2.63% and a false positive rate of 1.99%.

关键词： Websites

Meta-Path Based Graph Contrastive Learning for Micro-Video Recommendation

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： He, Ying Wu, Gongqing Cai, Desheng Hu, Xuegang Key Laboratory of Knowledge Engineering with Big Data The Ministry of Education of China Hefei University of Technology China School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Intelligent Interconnected Systems Laboratory of Anhui Province Hefei230009 China

Nowadays, micro-video sharing platforms have become popular tools for people creating and viewing micro-videos in daily life. Micro-video recommendation task has attracted significant attention from researchers, recently. The key to a high-quality micro-video recommendation system is learning meaningful user and micro-video representations. Recently, many graph neural networks (GNNs) are proposed to learn node representations in graphs, which could be useful for recommendation tasks. However, we argue that directly utilizing existing GNNs in micro-video recommendations is ill-posed. The reasons are: (1) most previous GNNs fail to capture the heterogeneity of heterogeneous graphs since they are designed for homogeneous graphs;(2) they overemphasize node proximity and could hurt the robustness of node embeddings. In contrast to previous work, we propose a meta-path-based graph contrastive learning network (MPGCL) that learns more meaningful user and video embeddings for recommendation. Specifically, we yield homogeneous graphs for user type and video type to better capture heterogeneity based on a well-designed meta-path-based random walk strategy. Furthermore, to learn more robust node embeddings that are less sensitive to noise, we propose a graph contrastive learning network on different types of homogeneous graphs, which maximizes the consistency between graph representations with different views. We do extensive experiments on three real-world datasets and the results show that our model can learn more meaningful embeddings for user and micro-videos and outperforms the strong baselines. © 2022, The Authors. All rights reserved.

关键词： Graph neural networks

NEW BOOLEAN SATISFIABILITY PROBLEM HEURISTIC STRATEGY: MINIMAL POSITIVE NEGATIVE PRODUCT STRATEGY

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Qun, Zhao Xintao, Wang Menghui, Yang School of Information Resource Management Renmin University of China Beijing100872 China Institute of Economics Chinese Academy of Social Sciences Beijing100872 China Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education Beijing100872 China

This study presents a novel heuristic algorithm called the "Minimal Positive Negative Product Strategy" to guide the CDCL algorithm in solving the Boolean satisfiability problem. It provides a mathematical explanation for the superiority of this algorithm over widely used heuristics such as the Dynamic Largest Individual Sum (DLIS) and the Variable State Independent Decaying Sum (VSIDS). Experimental results further confirm the effectiveness of this heuristic strategy in *** Codes 03 Copyright © 2023, The Authors. All rights reserved.

关键词： Heuristic algorithms

SALI: A Scalable Adaptive Learned Index Framework based on Probability Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ge, Jiake Zhang, Huanchen Shi, Boyu Luo, Yuanhui Guo, Yunda Chai, Yunpeng Chen, Yuxing Pan, Anqun Key Laboratory of Data Engineering and Knowledge Engineering MOE China Engineering Research Center of Database and Business Intelligence MOE China School of Information Renmin University of China China China and Shanghai Qi Zhi Institute China Tsinghua University China Tencent Inc China

The growth in data storage capacity and the increasing demands for high performance have created several challenges for concurrent indexing structures. One promising solution is learned indexes, which use a learning-based approach to fit the distribution of stored data and predictively locate target keys, significantly improving lookup performance. Despite their advantages, prevailing learned indexes exhibit constraints and encounter issues of scalability on multi-core data storage. This paper introduces SALI, the Scalable Adaptive Learned Index framework, which incorporates two strategies aimed at achieving high scalability, improving efficiency, and enhancing the robustness of the learned index. Firstly, a set of node-evolving strategies is defined to enable the learned index to adapt to various workload skews and enhance its concurrency performance in such scenarios. Secondly, a lightweight strategy is proposed to maintain statistical information within the learned index, with the goal of further improving the scalability of the index. Furthermore, to validate their effectiveness, SALI applied the two strategies mentioned above to the learned index structure that utilizes fine-grained write locks, known as LIPP. The experimental results have demonstrated that SALI significantly enhances the insertion throughput with 64 threads by an average of 2.04× compared to the second-best learned index. Furthermore, SALI accomplishes a lookup throughput similar to that of LIPP+. © 2023, CC BY-NC-ND.

关键词： Scalability

Synonyms weighted LDA for product aspects extraction

学校读者我要写书评

暂无评论

International Journal of Applied Mathematics and Statistics 2013年第24期51卷 283-291页

作者： Peng, Yun Wan, Changxuan School of Information and Technology Jiangxi University of Finance and Economics Nanchang 330013 Jiangxi China Computer and Information Engineering College Jiangxi Normal University Nanchang 330022 Jiangxi China Jiangxi Key Laboratory of Data and Knowledge Engineering Jiangxi University of Finance and Economics Nanchang 330013 Jiangxi China

It is important to extract the aspects from the comments of shoppers about certain products. Product aspect descriptions often contain words of same meaning, and discriminating these synonyms effectively can improve the efficiency of aspects extraction. Standard topic model in identifying those words, because of the absent introduction of priori knowledge, will largely ignore the relations of words meaning. An improved aspects extracting model of LDA by adding synonymous words constraint is proposed in this paper. In the process of words clustering analysis, words with high similarity are aggregated in the same cluster. In the stage of aspects extraction, we introduce words clustering and cluster membership weights as priori knowledge to strengthen the original LDA topic model for features clustering, which can improve the accuracy of product aspects extraction. Our experiments show that synonyms weighted LDA proposed in this paper outperforms the original LDA by a large margin. © 2013 by CESER Publications.

关键词： Extraction

Semi-supervised Short Text Classification Based On Dual-channel data Augmentation

学校读者我要写书评

暂无评论

Semi-supervised Short Text Classification Based On Dual-chan...

International Joint Conference on Neural Networks (IJCNN)

作者： Jiajun Li Peipei Li Xuegang Hu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology Hefei City Anhui Province China Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei City Anhui Province China

In practical applications, high-quality labeled data is critical for short text classification. But in many cases, it is expensive and time-consuming to obtain labeled information. Semi-supervised short text classification is hence attracting more attention. However, due to the sparsity of short texts, the performance of existing short text classification models always needs to be improved. Therefore, in this paper, we propose a semi-supervised Short text classification method based on Dual-Channel data Augmentation called SDCA. More specifically, in order to solve the sparsity of short texts, this model first adopts the multi-stage word-level TCN (Temporal Convolutional Network)-based attention to enhanced semantic features and an one-dimensional convolution-based attention mechanism to augment the relevance of surrounding short texts. Secondly, the unlabeled data are augmented by word embedding weighted augmentation and word replacement augmentation, so that the model can make full use of the unlabeled short texts and further enhance the network training. Finally, extensive experiments conducted on four benchmark datasets demonstrate the effectiveness of the proposed model on semi-supervised short text classification.

关键词：

Privileged graph distillation for cold start recommendation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Shuai Zhang, Kun Wu, Le Ma, Haiping Hong, Richang Wang, Meng Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology China School of Computer Science and Information Engineering Hefei University of Technology China Institute of Artificial Intelligence Hefei Comprehensive National Science Center China Anhui University China

The cold start problem in recommender systems is a long-standing challenge, which requires recommending to new users (items) based on attributes without any historical interaction records. In these recommendation systems, warm users (items) have privileged collaborative signals of interaction records compared to cold start users (items), and these Collaborative Filtering (CF) signals are shown to have competing performance for recommendation. Many researchers proposed to learn the correlation between collaborative signal embedding space and the attribute embedding space to improve the cold start recommendation, in which user and item categorical attributes are available in many online platforms. However, the cold start recommendation is still limited by two embedding spaces modeling and simple assumptions of space transformation. As user-item interaction behaviors and user (item) attributes naturally form a heterogeneous graph structure, in this paper, we propose a privileged graph distillation model (PGD). The teacher model is composed of a heterogeneous graph structure for warm users and items with privileged CF links. The student model is composed of an entity-attribute graph without CF links. Specifically, the teacher model can learn better embeddings of each entity by injecting complex higher-order relationships from the constructed heterogeneous graph. The student model can learn the distilled output with privileged CF embeddings from the teacher embeddings. Our proposed model is generally applicable to different cold start scenarios with new user, new item, or new user-new item. Finally, extensive experimental results on the real-world datasets clearly show the effectiveness of our proposed model on different types of cold start problems, with average 6.6%, 5.6%, and 17.1% improvement over state-of-the-art baselines on three datasets, respectively. © 2021, CC BY.

关键词： Embeddings

SP3: Enhancing Structured Pruning via PCA Projection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hu, Yuxuan Zhang, Jing Zhao, Zhe Zhao, Chen Chen, Xiaodong Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering MOE China Engineering Research Center of Database and Business Intelligence MOE China Tencent AI Lab Tencent Beijing China School of Computer Science and Technology Xi'an Jiaotong University Xi'An China

Structured pruning is a widely used technique for reducing the size of pre-trained language models (PLMs), but current methods often overlook the potential of compressing the hidden dimension (d) in PLMs, a dimension critical to model size and efficiency. This paper introduces a novel structured pruning approach, Structured Pruning with PCA Projection (SP3), targeting the effective reduction of d by projecting features into a space defined by principal components before masking. Extensive experiments on benchmarks (GLUE and SQuAD) show that SP3 can reduce d by 70%, compress 94% of the BERTbase model, and maintain over 96% accuracy and outperform other methods that compress d by 6% in accuracy at the same compression ratio. SP3 has also proven effective with other models, including OPT and Llama. Our data and code are available at ours repo. © 2023, CC BY.

关键词：

Dynamic Tracking with Fuzzy Rules for Evolutionary Dynamic Constrained Optimization

学校读者我要写书评

暂无评论

Dynamic Tracking with Fuzzy Rules for Evolutionary Dynamic C...

IEEE International Conference on Systems, Man and Cybernetics

作者： Chenyang Bu Yuxin Liu Lizhong Zhang Tao Zhu Wenjian Luo Ministry of Education Key Laboratory of Knowledge Engineering with Big Data School of Computer Science and Information Engineering Hefei University of Technology Hefei Anhui China School of Computer Science and Information Engineering University of South China Hengyang Hunan China School of Computer Science and Technology Harbin Institute of Technology Shenzhen Guangdong China

Nature-inspired population-based stochastic search algorithms (SSA) have demonstrated effectiveness in solving many real-world dynamic optimization problems (DOPs), such as dynamic optimal power flow (DOPF) problems. The basic idea of solving DOPs using SSAs is to “track the moving optima”, rather than solving the changed problems from scratch. Its hidden assumption is that the problems are slightly changed in general, and it is expected that the search process can be accelerated by learning from past search experiences. However, the hidden assumption that the current search process can always benefit from previous search experiences might not be true for certain cases. For example, if the current problem is not similar to any of its previous problems, the historical solutions might not be helpful for the current search. To reduce such negative transfer, the following issues are worthy of study: how to choose which historical problems to learn from, and how to determine the degree of learning from historical problems. To solve the above problems, we propose a dynamic processing framework based on fuzzy rules from the perspective of incorporating human knowledge for optima tracking. The experimental results on the DOPF problems show that the SSA with the proposed optima tracking strategy outperforms other comparative algorithms. We open up the code and data of our algorithm 4 4 https://***/DMiC-Lab-HFUT/SMDE-Transfer.

关键词：