检索结果-内蒙古大学图书馆

37th Conference on Neural information processing Systems, NeurIPS 2023

作者： Wang, Zitai Xu, Qianqian Yang, Zhiyong He, Yuan Cao, Xiaochun Huang, Qingming SKLOIS Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Alibaba Group China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China BDKM University of Chinese Academy of Sciences China

ISBN: (纸本)9781713899921

Real-world datasets are typically imbalanced in the sense that only a few classes have numerous samples, while many classes are associated with only a few samples. As a result, a naïve ERM learning process will be biased towards the majority classes, making it difficult to generalize to the minority classes. To address this issue, one simple but effective approach is to modify the loss function to emphasize the learning on minority classes, such as re-weighting the losses or adjusting the logits via class-dependent terms. However, existing generalization analysis of such losses is still coarse-grained and fragmented, failing to explain some empirical results. To bridge this gap, we propose a novel technique named data-dependent contraction to capture how these modified losses handle different classes. On top of this technique, a fine-grained generalization bound is established for imbalanced learning, which helps reveal the mystery of re-weighting and logit-adjustment in a unified manner. Furthermore, a principled learning algorithm is developed based on the theoretical insights. Finally, the empirical results on benchmark datasets not only validate the theoretical results but also demonstrate the effectiveness of the proposed method. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Approach for Diagnosing Unexpected Faults in Web Service Flows

An Approach for Diagnosing Unexpected Faults in Web Service ...

引用

International Conference on Grid and Cooperative computing (GCC)

作者： Xu Han Zhongzhi Shi Wenjia Niu Fen Lin Donglei Zhang Key Lab. of Intell. Inf. Process. Chinese Acad. of Sci. Beijing Beijing China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China

Potential faults have greatly reduced the dependability of business processes, so fault diagnosis is becoming an important issue which aims at supporting self-healing service flow execution. The existing fault handling mechanism provided by BPEL can only identify the faults which have been pre-defined in standards or by users. However, unexpected faults are also the main cause of failures in service flow execution. Therefore an effective diagnosis approach is needed to solve this problem. In this paper, we propose a logic-based approach for diagnosing unexpected faults in Web service flows. This approach uses dynamic description logic (DDL) to model business processes, and diagnoses faults based on DDL reasoning. We provide the DDL-based diagnosing algorithm, which takes process description and runtime information as inputs, and returns the related information of possible faults as the result. Moreover, to improve the efficiency of online diagnosis, the incremental DDL-based diagnosing algorithm is presented. Experimental results on a demo system show the effectiveness of this approach.

关键词： Web services Fault diagnosis Logic Grid computing lab.ratories information processing Computers Testing Runtime Engines

来源：评论

学校读者我要写书评

暂无评论

The minority matters: a diversity-promoting collab.rative 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

Collab.rative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collab.rative 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 Collab.rative 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

DRAUC: an instance-wise distributionally robust AUC optimization framework 23

DRAUC: an instance-wise distributionally robust AUC optimiza...

引用

Proceedings of the 37th International Conference on Neural information processing Systems

作者： Siran Dai Qianqian Xu Zhiyong Yang Xiaochun Cao Qingming Huang SKLOIS 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 Tech. CAS School of Computer Science and Tech. University of Chinese Academy of Sciences School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS and BDKM University of Chinese Academy of Sciences

The Area Under the ROC Curve (AUC) is a widely employed metric in long-tailed classification scenarios. Nevertheless, most existing methods primarily assume that training and testing examples are drawn i.i.d. from the same distribution, which is often unachievable in practice. Distributionally Robust Optimization (DRO) enhances model performance by optimizing it for the local worst-case scenario, but directly integrating AUC optimization with DRO results in an intractable optimization problem. To tackle this challenge, methodically we propose an instance-wise surrogate loss of Distributionally Robust AUC (DRAUC) and build our optimization framework on top of it. Moreover, we highlight that conventional DRAUC may induce lab.l bias, hence introducing distribution-aware DRAUC as a more suitable metric for robust AUC learning. Theoretically, we affirm that the generalization gap between the training loss and testing error diminishes if the training set is sufficiently large. Empirically, experiments on corrupted benchmark datasets demonstrate the effectiveness of our proposed method. Code is availab.e at: https://***/EldercatSAM/DRAUC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A unified generalization analysis of re-weighting and logit-adjustment for imbalanced learning 23

A unified generalization analysis of re-weighting and logit-...

引用

Proceedings of the 37th International Conference on Neural information processing Systems

作者： Zitai Wang Qianqian Xu Zhiyong Yang Yuan He Xiaochun Cao Qingming Huang SKLOIS 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 Tech. CAS School of Computer Science and Tech. University of Chinese Academy of Sciences Alibaba Group School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS and BDKM University of Chinese Academy of Sciences

关键词：

来源：评论

学校读者我要写书评

暂无评论

SSE-SAM: Balancing Head and Tail Classes Gradually through Stage-Wise SAM

arXiv

引用

arXiv 2024年

作者： Lyu, Xingyu Xu, Qianqian Yang, Zhiyong Lyu, Shaojie Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS China School of Computer Science and Tech University of Chinese Academy of Sciences China Tencent Corporate China BDKM University of Chinese Academy of Sciences China

Real-world datasets often exhibit a long-tailed distribution, where vast majority of classes known as tail classes have only few samples. Traditional methods tend to overfit on these tail classes. Recently, a new approach called Imbalanced SAM (ImbSAM) is proposed to leverage the generalization benefits of Sharpness-Aware Minimization (SAM) for long-tailed distributions. The main strategy is to merely enhance the smoothness of the loss function for tail classes. However, we argue that improving generalization in long-tail scenarios requires a careful balance between head and tail classes. We show that neither SAM nor ImbSAM alone can fully achieve this balance. For SAM, we prove that although it enhances the model’s generalization ability by escaping saddle point in the overall loss landscape, it does not effectively address this for tail-class losses. Conversely, while ImbSAM is more effective at avoiding saddle points in tail classes, the head classes are trained insufficiently, resulting in significant performance drops. Based on these insights, we propose Stage-wise Saddle Escaping SAM (SSE-SAM), which uses complementary strengths of ImbSAM and SAM in a phased approach. Initially, SSE-SAM follows the majority sample to avoid saddle points of the head-class loss. During the later phase, it focuses on tail-classes to help them escape saddle points. Our experiments confirm that SSE-SAM has better ability in escaping saddles both on head and tail classes, and shows performance improvements. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficiently Finding Top-K Items from Evolving Distributed Data Streams

Efficiently Finding Top-K Items from Evolving Distributed Da...

引用

International Conference on Semantics, Knowledge and Grid (SKG)

作者： Baoyuan Qi Gang Ma Zhongzhi Shi Wei Wang University of Chinese Academy of Sciences Beijing China Key Lab of Intelligent Information Processing Institute of Computing Technology Cas Beijing China Key Lab. of Intell. Inf. Process. Institute of Computing Technology Chinese Academy of Sciences Beijing CN Beijing Lexo Technologies Co. Ltd. Beijing China

ISBN: (纸本)9781479967162

The problem of efficiently finding top-k frequent items has attracted much attention in recent years. Storage constraints in the processing node and intrinsic evolving feature of the data streams are two main challenges. In this paper, we propose a method to tackle these two challenges based on space-saving and gossip-based algorithms respectively. Our method is implemented on SAMOA, a scalab.e advanced massive online analysis machine learning framework. The experimental results show its effectiveness and scalab.lity.

关键词： Peer-to-peer computing Data mining Distributed databases Protocols Machine learning algorithms Monitoring Radiation detectors

来源：评论

学校读者我要写书评

暂无评论

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： Han, Boyu Xu, Qianqian Yang, Zhiyong Bao, Shilong Wen, Peisong Jiang, Yangbangyan Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Peng Cheng Laboratory China Key Laboratory of Big Data Mining and Knowledge Management CAS China

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm’s generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is availab.e at https://***/boyuh/AUCSeg. © 2024, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Ranking Sentences in scientific Literatures

Ranking Sentences in Scientific Literatures

引用

International Conference on Semantics, Knowledge and Grid (SKG)

作者： Jiao Tian Mengyun Cao Jin Liu Xiaoping Sun Zhuge Hai University of Chinese Academy of Sciences Beijing China Knowledge Grid Group CAS Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Wuhan University CAS Key Lab. of Intell. Inf. Process. Institute of Computing Technology Chinese Academy of Sciences Beijing CN

Sentence ranking is one of the most important research issues in text analysis. It can be used in extracted textual summarization and information retrieval. Graph-based methods are a common way of ranking and extracting sentences. In graph based methods, sentences are nodes of graph and edges are built based on the sentence similarities or on sentence co-occurrence relationship. PageRank style algorithms can be applied to get sentence ranks. In this paper, we focus on how to rank sentences in a single scientific paper. A scientific literature has more structural information than general texts and this structural information has not been fully explored yet in graph based ranking models. We investigated several different methods that used structural information such as paragraph and section information to construct a heterogeneous graph for ranking sentences. We conducted experiments on these methods to compare the results on sentence ranking. It shows that structural information can help identify more representative sentences.

关键词： Semantics Algorithm design and analysis Web pages Data mining Iterative methods Current measurement

来源：评论

学校读者我要写书评

暂无评论

OpenAUC: towards AUC-oriented open-set recognition 22

OpenAUC: towards AUC-oriented open-set recognition

引用

Proceedings of the 36th International Conference on Neural information processing Systems

作者： Zitai Wang Qianqian Xu Zhiyong Yang Yuan He Xiaochun Cao Qingming Huang SKLOIS 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 Tech. CAS School of Computer Science and Tech. University of Chinese Academy of Sciences Alibaba Group School of Cyber Science and Tech. Shenzhen Campus Sun Yat-sen University and SKLOIS Institute of Information Engineering CAS School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS and BDKM University of Chinese Academy of Sciences and Peng Cheng Laboratory

ISBN: (纸本)9781713871088

Traditional machine learning follows a close-set assumption that the training and test set share the same lab.l space. While in many practical scenarios, it is inevitable that some test samples belong to unknown classes (open-set). To fix this issue, Open-Set Recognition (OSR), whose goal is to make correct predictions on both close-set samples and open-set samples, has attracted rising attention. In this direction, the vast majority of literature focuses on the pattern of open-set samples. However, how to evaluate model performance in this challenging task is still unsolved. In this paper, a systematic analysis reveals that most existing metrics are essentially inconsistent with the aforementioned goal of OSR: (1) For metrics extended from close-set classification, such as Open-set F-score, Youden's index, and Normalized Accuracy, a poor open-set prediction can escape from a low performance score with a superior close-set prediction. (2) Novelty detection AUC, which measures the ranking performance between close-set and open-set samples, ignores the close-set performance. To fix these issues, we propose a novel metric named OpenAUC. Compared with existing metrics, OpenAUC enjoys a concise pairwise formulation that evaluates open-set performance and close-set performance in a coupling manner. Further analysis shows that OpenAUC is free from the aforementioned inconsistency properties. Finally, an end-to-end learning method is proposed to minimize the OpenAUC risk, and the experimental results on popular benchmark datasets speak to its effectiveness.

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：