检索结果-内蒙古大学图书馆

Learning efficient text-to-image synthesis via interstage cross-sample similarity distillation

学校读者我要写书评

暂无评论

science China(Information sciences) 2021年第2期64卷 19-30页

作者： Fengling MAO Bingpeng MA Hong CHANG Shiguang SHAN Xilin CHEN School of Information Science and Technology ShanghaiTech University Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing TechnologyChinese Academy of Sciences University of Chinese Academy of Sciences CAS Center for Excellence in Brain Science and Intelligence Technology

For a given text, previous text-to-image synthesis methods commonly utilize a multistage generation model to produce images with high resolution in a coarse-to-fine manner. However, these methods ignore the interaction among stages, and they do not constrain the consistent cross-sample relations of images generated in different stages. These deficiencies result in inefficient generation and discrimination. In this study, we propose an interstage cross-sample similarity distillation model based on a generative adversarial network(GAN) for learning efficient text-to-image synthesis. To strengthen the interaction among stages,we achieve interstage knowledge distillation from the refined stage to the coarse stages with novel interstage cross-sample similarity distillation blocks. To enhance the constraint on the cross-sample relations of the images generated at different stages, we conduct cross-sample similarity distillation among the stages. Extensive experiments on the Oxford-102 and Caltech-UCSD Birds-200-2011(CUB) datasets show that our model generates visually pleasing images and achieves quantitatively comparable performance with state-of-the-art methods.

关键词： generative adversarial network (GAN) text-to-image synthesis knowledge distillation

IVE: Accelerating Enumeration-Based Subgraph Matching via Exploring Isolated Vertices 40

学校读者我要写书评

暂无评论

IVE: Accelerating Enumeration-Based Subgraph Matching via Ex...

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Jiang, Zite Zhang, Shuai Hou, Xingzhong Yuan, Mengting You, Haihang Institute of Computing Technology CAS State Key Lab of Processors Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijinz China Zhongguancun Laboratory Beijing China School of Computer Science Wuhan University Wuhan China

ISBN: (纸本)9798350317152

The performance of the enumeration-based sub-graph matching, which searches all isomorphic subgraphs in the data graph, is crucial to various applications. The upper bound of the complexity for the enumeration-based method is exponential to the number of query graph vertices, denoted as n. We propose a novel subgraph matching algorithm called the Isolated Vertices Exploration (IVE). The IVE leverages isolated vertices during the reordering and enumeration phases, thereby significantly accelerating the subgraph matching process. During the enumeration, the isolated vertices can be matched by using a quick bipartite graph matching algorithm. Consequently, the complexity of matching the remaining non-isolated vertices is exponential to the number of non-isolated vertices, denoted as n'. For the reordering, we designed the Maximum Deleted Edges (MDE) to minimize n'. MDE iteratively selects the query vertex with the maximum edges. According to the experimental results, n' is less than 0.8n for 99.8% of arbitrary graphs. Moreover, IVE outperforms the state-of-the-art algorithms in various scenarios with different sizes, sparsities and fields, achieving a performance speedup of up to 80.3x. © 2024 IEEE.

关键词： Iterative methods

Impossible Differential Analysis on 8-Round PRINCE 9th

学校读者我要写书评

暂无评论

Impossible Differential Analysis on 8-Round PRINCE

9th International Conference on Computer Engineering and networks, CENet2019

作者： Ding, Yaoling Jia, Keting Wang, An Shi, Ying School of Computer Science Beijing Institute of Technology Beijing100081 China Department of Computer Science and Technology Tsinghua University Beijing100084 China Key Laboratory of Network Assessment Technology CAS Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China

ISBN: (纸本)9789811537523

PRINCE is a lightweight block cipher, which was proposed by Borghoff et al. in Asiacrypt 2012. Various cryptanalytic techniques have been employed to evaluate the security of PRINCE. In 2017, Ding et al. constructed a 4-round impossible differential based on some observations on M′ operation and launched impossible differential attacks on 6- and 7-round PRINCE and the underlying PRINCEcore. In this paper, we explore the differential distribution table (DDT) of the S-box employed in PRINCE and construct a more detailed DDT which contains the input/output values corresponding to each differential. Taking advantage of the table, we compute the subkeys instead of guessing them. With this technique, we extend the impossible differential attacks of PRINCE and PRINCEcore to eight rounds. The corresponding computational and complexities are 110.7 and 62.26 encryptions, respectively, which are much less than exhaustive search. And the data complexities are 64 and 60 chosen plaintexts, respectively. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Cryptography

Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Mingkun Li, Jianing Chen, Wei Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing China Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Adversarial purification is one of the promising approaches to defend neural networks against adversarial attacks. Recently, methods utilizing diffusion probabilistic models have achieved great success for adversarial purification in image classification tasks. However, such methods fall into the dilemma of balancing the needs for noise removal and information preservation. This paper points out that existing adversarial purification methods based on diffusion models gradually lose sample information during the core denoising process, causing occasional label shift in subsequent classification tasks. As a remedy, we suggest to suppress such information loss by introducing guidance from the classifier confidence. Specifically, we propose Classifier-cOnfidence gUided Purification (COUP) algorithm, which purifies adversarial examples while keeping away from the classifier decision boundary. Experimental results show that COUP can achieve better adversarial robustness under strong attack methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

ReCoSa: Detecting the relevant contexts with self-attention for multi-turn dialogue generation

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhang, Hainan Y., Lan L., Pang J., Guo X., Cheng CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China

In multi-turn dialogue generation, response is usually related with only a few contexts. Therefore, an ideal model should be able to detect these relevant contexts and produce a suitable response accordingly. However, the widely used hierarchical recurrent encoder-decoder models just treat all the contexts indiscriminately, which may hurt the following response generation process. Some researchers try to use the cosine similarity or the traditional attention mechanism to find the relevant contexts, but they suffer from either insufficient relevance assumption or position bias problem. In this paper, we propose a new model, named ReCoSa, to tackle this problem. Firstly, a word level LSTM encoder is conducted to obtain the initial representation of each context. Then, the self-attention mechanism is utilized to update both the context and masked response representation. Finally, the attention weights between each context and response representations are computed and used in the further decoding process. Experimental results on both Chinese customer services dataset and English Ubuntu dialogue dataset show that ReCoSa significantly outperforms baseline models, in terms of both metric-based and human evaluations. Further analysis on attention shows that the detected relevant contexts by ReCoSa are highly coherent with human's understanding, validating the correctness and interpretability of ReCoSa. Copyright © 2019, The Authors. All rights reserved.

关键词： Signal encoding

GERE: Generative Evidence Retrieval for Fact Verification

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Jiangui Zhang, Ruqing Guo, Jiafeng Fan, Yixing Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China

Fact verification (FV) is a challenging task which aims to verify a claim using multiple evidential sentences from trustworthy corpora, e.g., Wikipedia. Most existing approaches follow a three-step pipeline framework, including document retrieval, sentence retrieval and claim verification. High-quality evidences provided by the first two steps are the foundation of the effective reasoning in the last step. Despite being important, high-quality evidences are rarely studied by existing works for FV, which often adopt the off-the-shelf models to retrieve relevant documents and sentences in an "index-retrieve-then-rank" fashion. This classical approach has clear drawbacks as follows: i) a large document index as well as a complicated search process is required, leading to considerable memory and computational overhead;ii) independent scoring paradigms fail to capture the interactions among documents and sentences in ranking;iii) a fixed number of sentences are selected to form the final evidence set. In this work, we propose GERE, the first system that retrieves evidences in a generative fashion, i.e., generating the document titles as well as evidence sentence identifiers. This enables us to mitigate the aforementioned technical issues since: i) the memory and computational cost is greatly reduced because the document index is eliminated and the heavy ranking process is replaced by a light generative process;ii) the dependency between documents and that between sentences could be captured via sequential generation process;iii) the generative formulation allows us to dynamically select a precise set of relevant evidences for each claim. The experimental results on the FEVER dataset show that GERE achieves significant improvements over the state-of-the-art baselines, with both time-efficiency and memory-efficiency. Copyright © 2022, The Authors. All rights reserved.

关键词： Efficiency

Influence maximization with ε-almost submodular threshold functions 17

学校读者我要写书评

暂无评论

Influence maximization with ε-almost submodular threshold f...

Proceedings of the 31st International Conference on Neural Information Processing Systems

作者： Qiang Li Wei Chen Xiaoming Sun Jialin Zhang CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences Microsoft Research

ISBN: (纸本)9781510860964

Influence maximization is the problem of selecting k nodes in a social network to maximize their influence spread. The problem has been extensively studied but most works focus on the submodular influence diffusion models. In this paper, motivated by empirical evidences, we explore influence maximization in the non-submodular regime. In particular, we study the general threshold model in which a fraction of nodes have non-submodular threshold functions, but their threshold functions are closely upper- and lower-bounded by some submodular functions (we call them ε-almost submodular). We first show a strong hardness result: there is no l/nγ/c approximation for influence maximization (unless P = NP) for all networks with up to nγ ε-almost submodular nodes, where γ is in (0,1) and c is a parameter depending on ε. This indicates that influence maximization is still hard to approximate even though threshold functions are close to submodular. We then provide (l - ε)ℓ(1 - 1/ε) approximation algorithms when the number of ε-almost submodular nodes is ℓ. Finally, we conduct experiments on a number of real-world datasets, and the results demonstrate that our approximation algorithms outperform other baseline algorithms.

关键词：

HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Zixuan Hou, Zhongni Guan, Saiping Jin, Xiaolong Peng, Weihua Bai, Long Lyu, Yajuan Li, Wei Guo, Jiafeng Cheng, Xueqi School of Computer Science and Technology University of Chinese Academy of Sciences China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China Baidu Inc China

A Temporal Knowledge Graph (TKG) is a sequence of KGs with respective timestamps, which adopts quadruples in the form of (subject, relation, object, timestamp) to describe dynamic facts. TKG reasoning has facilitated many real-world applications via answering such queries as (query entity, query relation, ?, future timestamp) about future. This is actually a matching task between a query and candidate entities based on their historical structures, which reflect behavioral trends of the entities at different timestamps. In addition, recent KGs provide background knowledge of all the entities, which is also helpful for the matching. Thus, in this paper, we propose the Historical Structure Matching (HiSMatch) model. It applies two structure encoders to capture the semantic information contained in the historical structures of the query and candidate entities. Besides, it adopts another encoder to integrate the background knowledge into the model. TKG reasoning experiments on six benchmark datasets demonstrate the significant improvement of the proposed HiSMatch model, with up to 5.6% performance improvement in MRR, compared to the state-of-the-art baselines. Copyright © 2022, The Authors. All rights reserved.

关键词： Knowledge graph

Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Zixuan Guan, Saiping Jin, Xiaolong Peng, Weihua Lyu, Yajuan Zhu, Yong Bai, Long Li, Wei Guo, Jiafeng Cheng, Xueqi School of Computer Science and Technology University of Chinese Academy of Sciences China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China Baidu Inc China

A Temporal Knowledge Graph (TKG) is a sequence of KGs corresponding to different timestamps. TKG reasoning aims to predict potential facts in the future given the historical KG sequences. One key of this task is to mine and understand evolutional patterns of facts from these sequences. The evolutional patterns are complex in two aspects, length-diversity and time-variability. Existing models for TKG reasoning focus on modeling fact sequences of a fixed length, which cannot discover complex evolutional patterns that vary in length. Furthermore, these models are all trained offline, which cannot well adapt to the changes of evolutional patterns from then on. Thus, we propose a new model, called Complex Evolutional network (CEN), which uses a length-aware Convolutional Neural network (CNN) to handle evolutional patterns of different lengths via an easy-to-difficult curriculum learning strategy. Besides, we propose to learn the model under the online setting so that it can adapt to the changes of evolutional patterns over time. Extensive experiments demonstrate that CEN obtains substantial performance improvement under both the traditional offline and the proposed online settings. Copyright © 2022, The Authors. All rights reserved.

关键词： Knowledge graph