检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Pang, Liang Lan, Yanyan Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China Institute for AI Industry Research Tsinghua University Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

Neural text matching models have been widely used in community question answering, information retrieval, and dialogue. However, these models designed for short texts cannot well address the long-form text matching problem, because there are many contexts in long-form texts can not be directly aligned with each other, and it is difficult for existing models to capture the key matching signals from such noisy data. Besides, these models are computationally expensive for simply use all textual data indiscriminately. To tackle the effectiveness and efficiency problem, we propose a novel hierarchical noise filtering model, namely Match-Ignition. The main idea is to plug the well-known PageRank algorithm into the Transformer, to identify and filter both sentence and word level noisy information in the matching process. Noisy sentences are usually easy to detect because previous work has shown that their similarity can be explicitly evaluated by the word overlapping, so we directly use PageRank to filter such information based on a sentence similarity graph. Unlike sentences, words rely on their contexts to express concrete meanings, so we propose to jointly learn the filtering and matching process, to well capture the critical word-level matching signals. Specifically, a word graph is first built based on the attention scores in each self-attention block of Transformer, and key words are then selected by applying PageRank on this graph. In this way, noisy words will be filtered out layer by layer in the matching process. Experimental results show that Match-Ignition outperforms both SOTA short text matching models and recent long-form text matching models. We also conduct detailed analysis to show that Match-Ignition efficiently captures important sentences and words, to facilitate the long-form text matching process. © 2021, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The minority matters: a diversity-promoting collaborative metric learning algorithm 22

The minority matters: a diversity-promoting collaborative me...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Shilong Bao Qianqian Xu Zhiyong Yang Yuan He Xiaochun Cao Qingming Huang State Key Laboratory of Information Security Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Computer Science and Tech. University of Chinese Academy of Sciences Alibaba Group School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Laboratory of Big Data Mining and Knowledge Management CAS and Peng Cheng Laboratory

ISBN: (纸本)9781713871088

Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collaborative Filtering. Following the convention of RS, existing methods exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, we argue that the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collaborative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to include a multiple set of representations for each user in the system. Based on this embedding paradigm, user preference toward an item is aggregated from different embeddings by taking the minimum item-user distance among the user embedding set. Furthermore, we observe that the diversity of the embeddings for the same user also plays an essential role in the model. To this end, we propose a Diversity Control Regularization Scheme (DCRS) to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could generalize well to unseen test data by tackling the challenge of the annoying operation that comes from the minimum value. Experiments over a range of benchmark datasets speak to the efficacy of DPCML.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deepfake network Architecture Attribution

arXiv

引用

arXiv 2022年

作者： Yang, Tianyun Huang, Ziyao Cao, Juan Li, Lei Li, Xirong Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China China

With the rapid progress of generation technology, it has become necessary to attribute the origin of fake images. Existing works on fake image attribution perform multi-class classification on several Generative Adversarial network (GAN) models and obtain high accuracies. While encouraging, these works are restricted to model-level attribution, only capable of handling images generated by seen models with a specific seed, loss and dataset, which is limited in real-world scenarios when fake images may be generated by privately trained models. This motivates us to ask whether it is possible to attribute fake images to the source models’ architectures even if they are finetuned or retrained under different configurations. In this work, we present the first study on Deepfake network Architecture Attribution to attribute fake images on architecture-level. Based on an observation that GAN architecture is likely to leave globally consistent fingerprints while traces left by model weights vary in different regions, we provide a simple yet effective solution named DNA-Det for this problem. Extensive experiments on multiple cross-test setups and a large-scale dataset demonstrate the effectiveness of DNA-Det. Our source code and dataset can be found here: https://***/ICTMCG/DNA-Det Copyright © 2022, The Authors. All rights reserved.

关键词： network architecture

来源：评论

学校读者我要写书评

暂无评论

Transductive learning for unsupervised text style transfer

arXiv

引用

arXiv 2021年

作者： Xiao, Fei Pang, Liang Lan, Yanyan Wang, Yan Shen, Huawei Cheng, Xueqi Data Intelligence System Research Center Cas Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Institute for Ai Industry Research Tsinghua University University of Chinese Academy of Sciences Tencent Ai Lab

Unsupervised style transfer models are mainly based on an inductive learning approach, which represents the style as embeddings, decoder parameters, or discriminator parameters and directly applies these general rules to the test cases. However, the lacking of parallel corpus hinders the ability of these inductive learning methods on this task. As a result, it is likely to cause severe inconsistent style expressions, like the salad is rude. To tackle this problem, we propose a novel transductive learning approach in this paper, based on a retrieval-based context-aware style representation. Specifically, an attentional encoderdecoder with a retriever framework is utilized. It involves top-K relevant sentences in the target style in the transfer process. In this way, we can learn a context-aware style embedding to alleviate the above inconsistency problem. In this paper, both sparse (BM25) and dense retrieval functions (MIPS) are used, and two objective functions are designed to facilitate joint learning. Experimental results show that our method outperforms several strong baselines. The proposed transductive learning approach is general and effective to the task of unsupervised style transfer, and we will apply it to the other two typical methods in the future. © 2021, CC BY.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

BiKT: Unleashing the potential of GNNs via Bi-directional Knowledge Transfer

arXiv

引用

arXiv 2023年

作者： Zheng, Shuai Liu, Zhizhe Zhu, Zhenfeng Zhang, Xingxing Li, Jianxin Zhao, Yao The Institute of Information Science Beijing Jiaotong University Beijing100044 China The Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China Qiyuan Lab Beijing China The Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing100083 China

Based on the message-passing paradigm, there has been an amount of research proposing diverse and impressive feature propagation mechanisms to improve the performance of GNNs. However, less focus has been put on feature transformation, another major operation of the message-passing framework. In this paper, we first empirically investigate the performance of the feature transformation operation in several typical GNNs. Unexpectedly, we notice that GNNs do not completely free up the power of the inherent feature transformation operation. By this observation, we propose the Bi-directional Knowledge Transfer (BiKT), a plug-and-play approach to unleash the potential of the feature transformation operations without modifying the original architecture. Taking the feature transformation operation as a derived representation learning model that shares parameters with the original GNN, the direct prediction by this model provides a topological-agnostic knowledge feedback that can further instruct the learning of GNN and the feature transformations therein. On this basis, BiKT not only allows us to acquire knowledge from both the GNN and its derived model but promotes each other by injecting the knowledge into the other. In addition, a theoretical analysis is further provided to demonstrate that BiKT improves the generalization bound of the GNNs from the perspective of domain adaption. An extensive group of experiments on up to 7 datasets with 5 typical GNNs demonstrates that BiKT brings up to 0.5% - 4% performance gain over the original GNN, which means a boosted GNN is obtained. Meanwhile, the derived model also shows a powerful performance to compete with or even surpass the original GNN, enabling us to flexibly apply it independently to some other specific downstream tasks. Copyright © 2023, The Authors. All rights reserved.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

PGGAN: Improve Password Cover Rate Using the Controller

PGGAN: Improve Password Cover Rate Using the Controller

引用

2021 International Conference on Computer network Security and Software Engineering, CNSSE 2021

作者： Guo, Xiaozhou Liu, Yi Tan, Kaijun Jin, Min Lu, Huaxiang Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China University of Chinese Academy of Sciences Beijing100089 China Cas Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Beijing200031 China Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing Key Lab Beijing100083 China

Password generation model based on generative adversarial network usually has the problem of high duplicate rate, which further leads to low cover rate. In this regard, we propose PGGAN model. It sets up an additional controller network which is similar to the discriminator in the aspect of structure and function. The discriminator and the controller respectively learn the measure between the distribution of generated password with the real password distribution and the uniform distribution, and then use two measures to teach generator meanwhile. By changing the activation function and loss function of the controller, different measure functions can be selected. The experimental results show that compared with GAN, our PGGAN performs better both in cover rate and duplicate rate. Moreover, Wasserstein distance usually has a better effect to the other measure in model. Specifically, PGGAN with Wasserstein distance can increase the cover rate by 3.57% and reduce the duplicate rate by 30.85% on rockyou dataset. © Published under licence by IOP Publishing Ltd.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

SAFL-Net: Semantic-Agnostic Feature Learning network with Auxiliary Plugins for Image Manipulation Detection

SAFL-Net: Semantic-Agnostic Feature Learning Network with Au...

引用

International Conference on Computer Vision (ICCV)

作者： Zhihao Sun Haoran Jiang Danding Wang Xirong Li Juan Cao Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences School of Mathematics Science University of Chinese Academy of Sciences MoE Key Lab of Data Engineering and Knowledge Engineering Renmin University of China

Since image editing methods in real world scenarios cannot be exhausted, generalization is a core challenge for image manipulation detection, which could be severely weakened by semantically related features. In this paper we propose SAFL-Net, which constrains a feature extractor to learn semantic-agnostic features by designing specific modules with corresponding auxiliary tasks. Applying constraints directly to the features extracted by the encoder helps it learn semantic-agnostic manipulation trace features, which prevents the biases related to semantic information within the limited training data and improves generalization capabilities. The consistency of auxiliary boundary prediction task and original region prediction task is guaranteed by a feature transformation structure. Experiments on various public datasets and comparisons in multiple dimensions demonstrate that SAFL-Net is effective for image manipulation detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sdgan: Improve Speech Enhancement Quality by Information Filter 6

Sdgan: Improve Speech Enhancement Quality by Information Fil...

引用

2021 6th International Symposium on Advances in Electrical, Electronics and Computer Engineering, ISAEECE 2021

作者： Guo, Xiaozhou Liu, Yi Mao, Wenyu Li, Jixing Li, Wenchang Gong, Guoliang Lu, Huaxiang Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China University of Chinese Academy of Sciences Beijing100089 China CAS Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Beijing200031 China Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing Key Lab Beijing100083 China

The speech denoising model based on adversarial generative network has achieved better results than the traditional machine learning model. In this paper, for the short cut connection in the generator, we discuss its influence on the information transfer between encoder and decoder, and propose SDGAN at target. SDGAN sets linear and convolution filters in the short cut connection which adaptively learn the optimal information processing. The information filter still enables the generator to solve the gradient vanishing problem, and it can also avoid information redundancy and improve expression ability. In addition, SDGAN replaces the L1 regularization term in loss function with the L2 regularization term, which not only makes the output speech of the generator closer to the clean speech, but also avoids sparsity. In the experiments, SDGAN significantly performs better than other traditional GAN in five performance metrics (such as PESQ), and the effect of convolution filter is better than that of linear filter. © Published under licence by IOP Publishing Ltd.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Self-supervised GANs with label augmentation 21

Self-supervised GANs with label augmentation

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Liang Hou Huawei Shen Qi Cao Xueqi Cheng Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences

ISBN: (纸本)9781713845393

Recently, transformation-based self-supervised learning has been applied to generative adversarial networks (GANs) to mitigate catastrophic forgetting in the discriminator by introducing a stationary learning environment. However, the separate self-supervised tasks in existing self-supervised GANs cause a goal inconsistent with generative modeling due to the fact that their self-supervised classifiers are agnostic to the generator distribution. To address this problem, we propose a novel self-supervised GAN that unifies the GAN task with the self-supervised task by augmenting the GAN labels (real or fake) via self-supervision of data transformation. Specifically, the original discriminator and self-supervised classifier are unified into a label-augmented discriminator that predicts the augmented labels to be aware of both the generator distribution and the data distribution under every transformation, and then provide the discrepancy between them to optimize the generator. Theoretically, we prove that the optimal generator could converge to replicate the real data distribution. Empirically, we show that the proposed method significantly outperforms previous self-supervised and data augmentation GANs on both generative modeling and representation learning across benchmark datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online Midgress-Sensitive Traffic Allocation for Percentile Charging in Pracitcal CDNs

Online Midgress-Sensitive Traffic Allocation for Percentile ...

引用

International Workshop on Quality of Service

作者： Huiyou Zhan Haisheng Tan Huang Xu Chi Zhang Hongqiu Ni Pengfei Zhang Weihua Shan Xiang-Yang Li CAS Key Lab of Wireless-Optical Communications University of Science and Technology of China China USTC-Deqing Alpha Innovation Research Institute Zhejiang China Algorithm Innovation Lab Huawei Cloud Computing Technologies Co. Ltd. Xi'an China

The traffic bandwidth costs comprise a significant amount of operating expenditure in CDNs, induced by the traffic from the end-users to edge servers (edge cost) and from the edge to the center servers (midgress cost). Traffic allocation is the main approach to minimizing the total bandwidth cost. The joint optimization of the total costs is challenging, specifically when the percentile charging mechanism as well as some other practical issues are considered, such as the dynamicity of midgress traffic and the granularity of traffic allocation. In this work, based on our novel miss ratio prediction mechanism, we propose the first online framework, named Iris, jointly optimizing the edge and midgress costs under the 95th percentile charging in commercial CDNs. Iris can theoretically achieve a competitive ratio of $1+\frac{p_{e}}{\beta\cdot p_{c}}$ , when the miss ratio of all domains is set as $\beta$ . Here $p_{e}$ and $p_{c}$ are the unit bandwidth price of the edge and midgress cost, respectively. Iris is tolerant to prediction errors which can be deployed in practical CDN systems. Extensive experiments based on real data indicate that Iris can dramatically reduce bandwidth costs by about 8.149% compared with the SOTA schemes, potentially saving millions of dollars per month for our large-scale commercial CDN collaborator.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：