Advances in Knowledge Discovery and Data Mining : 21st Pacific-Asia Conference, PAKDD 2017, Jeju, South Korea, May 23-26, 2017, Proceedings. Part I. Pacific-Asia Conference on Knowledge Discovery and Data Mining (21st : 2017 : Cheju Isl...最新文献
{"title":"GroupMixNorm Layer for Learning Fair Models","authors":"Anubha Pandey, Aditi Rai, Maneet Singh, Deepak L. Bhatt, Tanmoy Bhowmik","doi":"10.1007/978-3-031-33374-3_41","DOIUrl":"https://doi.org/10.1007/978-3-031-33374-3_41","url":null,"abstract":"","PeriodicalId":91995,"journal":{"name":"Advances in Knowledge Discovery and Data Mining : 21st Pacific-Asia Conference, PAKDD 2017, Jeju, South Korea, May 23-26, 2017, Proceedings. Part I. Pacific-Asia Conference on Knowledge Discovery and Data Mining (21st : 2017 : Cheju Isl...","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80889481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-18DOI: 10.1007/978-3-031-05936-0_31
David Hason Rudd, H. Huo, Guandong Xu
{"title":"Leveraged Mel Spectrograms Using Harmonic and Percussive Components in Speech Emotion Recognition","authors":"David Hason Rudd, H. Huo, Guandong Xu","doi":"10.1007/978-3-031-05936-0_31","DOIUrl":"https://doi.org/10.1007/978-3-031-05936-0_31","url":null,"abstract":"","PeriodicalId":91995,"journal":{"name":"Advances in Knowledge Discovery and Data Mining : 21st Pacific-Asia Conference, PAKDD 2017, Jeju, South Korea, May 23-26, 2017, Proceedings. Part I. Pacific-Asia Conference on Knowledge Discovery and Data Mining (21st : 2017 : Cheju Isl...","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75640033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-18DOI: 10.1007/978-3-031-33380-4_17
David Hason Rudd, H. Huo, Guandong Xu
{"title":"An Extended Variational Mode Decomposition Algorithm Developed Speech Emotion Recognition Performance","authors":"David Hason Rudd, H. Huo, Guandong Xu","doi":"10.1007/978-3-031-33380-4_17","DOIUrl":"https://doi.org/10.1007/978-3-031-33380-4_17","url":null,"abstract":"","PeriodicalId":91995,"journal":{"name":"Advances in Knowledge Discovery and Data Mining : 21st Pacific-Asia Conference, PAKDD 2017, Jeju, South Korea, May 23-26, 2017, Proceedings. Part I. Pacific-Asia Conference on Knowledge Discovery and Data Mining (21st : 2017 : Cheju Isl...","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81399523","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-27DOI: 10.1007/978-3-031-33380-4_13
Neel Kanwal, T. Eftestøl, Farbod Khoraminia, T. Zuiverloon, K. Engan
{"title":"Vision Transformers for Small Histological Datasets Learned Through Knowledge Distillation","authors":"Neel Kanwal, T. Eftestøl, Farbod Khoraminia, T. Zuiverloon, K. Engan","doi":"10.1007/978-3-031-33380-4_13","DOIUrl":"https://doi.org/10.1007/978-3-031-33380-4_13","url":null,"abstract":"","PeriodicalId":91995,"journal":{"name":"Advances in Knowledge Discovery and Data Mining : 21st Pacific-Asia Conference, PAKDD 2017, Jeju, South Korea, May 23-26, 2017, Proceedings. Part I. Pacific-Asia Conference on Knowledge Discovery and Data Mining (21st : 2017 : Cheju Isl...","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74706670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-15DOI: 10.48550/arXiv.2305.08750
Shenyang Huang, Jacob Danovitch, Guillaume Rabusseau, Reihaneh Rabbany
How can we detect traffic disturbances from international flight transportation logs or changes to collaboration dynamics in academic networks? These problems can be formulated as detecting anomalous change points in a dynamic graph. Current solutions do not scale well to large real-world graphs, lack robustness to large amounts of node additions/deletions, and overlook changes in node attributes. To address these limitations, we propose a novel spectral method: Scalable Change Point Detection (SCPD). SCPD generates an embedding for each graph snapshot by efficiently approximating the distribution of the Laplacian spectrum at each step. SCPD can also capture shifts in node attributes by tracking correlations between attributes and eigenvectors. Through extensive experiments using synthetic and real-world data, we show that SCPD (a) achieves state-of-the art performance, (b) is significantly faster than the state-of-the-art methods and can easily process millions of edges in a few CPU minutes, (c) can effectively tackle a large quantity of node attributes, additions or deletions and (d) discovers interesting events in large real-world graphs. The code is publicly available at https://github.com/shenyangHuang/SCPD.git
{"title":"Fast and Attributed Change Detection on Dynamic Graphs with Density of States","authors":"Shenyang Huang, Jacob Danovitch, Guillaume Rabusseau, Reihaneh Rabbany","doi":"10.48550/arXiv.2305.08750","DOIUrl":"https://doi.org/10.48550/arXiv.2305.08750","url":null,"abstract":"How can we detect traffic disturbances from international flight transportation logs or changes to collaboration dynamics in academic networks? These problems can be formulated as detecting anomalous change points in a dynamic graph. Current solutions do not scale well to large real-world graphs, lack robustness to large amounts of node additions/deletions, and overlook changes in node attributes. To address these limitations, we propose a novel spectral method: Scalable Change Point Detection (SCPD). SCPD generates an embedding for each graph snapshot by efficiently approximating the distribution of the Laplacian spectrum at each step. SCPD can also capture shifts in node attributes by tracking correlations between attributes and eigenvectors. Through extensive experiments using synthetic and real-world data, we show that SCPD (a) achieves state-of-the art performance, (b) is significantly faster than the state-of-the-art methods and can easily process millions of edges in a few CPU minutes, (c) can effectively tackle a large quantity of node attributes, additions or deletions and (d) discovers interesting events in large real-world graphs. The code is publicly available at https://github.com/shenyangHuang/SCPD.git","PeriodicalId":91995,"journal":{"name":"Advances in Knowledge Discovery and Data Mining : 21st Pacific-Asia Conference, PAKDD 2017, Jeju, South Korea, May 23-26, 2017, Proceedings. Part I. Pacific-Asia Conference on Knowledge Discovery and Data Mining (21st : 2017 : Cheju Isl...","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85775162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-02DOI: 10.48550/arXiv.2305.01794
Zhiqi Bu, Zongyu Dai, Yiliang Zhang, Q. Long
Multiple imputation (MI) has been widely applied to missing value problems in biomedical, social and econometric research, in order to avoid improper inference in the downstream data analysis. In the presence of high-dimensional data, imputation models that include feature selection, especially $ell_1$ regularized regression (such as Lasso, adaptive Lasso, and Elastic Net), are common choices to prevent the model from underdetermination. However, conducting MI with feature selection is difficult: existing methods are often computationally inefficient and poor in performance. We propose MISNN, a novel and efficient algorithm that incorporates feature selection for MI. Leveraging the approximation power of neural networks, MISNN is a general and flexible framework, compatible with any feature selection method, any neural network architecture, high/low-dimensional data and general missing patterns. Through empirical experiments, MISNN has demonstrated great advantages over state-of-the-art imputation methods (e.g. Bayesian Lasso and matrix completion), in terms of imputation accuracy, statistical consistency and computation speed.
{"title":"MISNN: Multiple Imputation via Semi-parametric Neural Networks","authors":"Zhiqi Bu, Zongyu Dai, Yiliang Zhang, Q. Long","doi":"10.48550/arXiv.2305.01794","DOIUrl":"https://doi.org/10.48550/arXiv.2305.01794","url":null,"abstract":"Multiple imputation (MI) has been widely applied to missing value problems in biomedical, social and econometric research, in order to avoid improper inference in the downstream data analysis. In the presence of high-dimensional data, imputation models that include feature selection, especially $ell_1$ regularized regression (such as Lasso, adaptive Lasso, and Elastic Net), are common choices to prevent the model from underdetermination. However, conducting MI with feature selection is difficult: existing methods are often computationally inefficient and poor in performance. We propose MISNN, a novel and efficient algorithm that incorporates feature selection for MI. Leveraging the approximation power of neural networks, MISNN is a general and flexible framework, compatible with any feature selection method, any neural network architecture, high/low-dimensional data and general missing patterns. Through empirical experiments, MISNN has demonstrated great advantages over state-of-the-art imputation methods (e.g. Bayesian Lasso and matrix completion), in terms of imputation accuracy, statistical consistency and computation speed.","PeriodicalId":91995,"journal":{"name":"Advances in Knowledge Discovery and Data Mining : 21st Pacific-Asia Conference, PAKDD 2017, Jeju, South Korea, May 23-26, 2017, Proceedings. Part I. Pacific-Asia Conference on Knowledge Discovery and Data Mining (21st : 2017 : Cheju Isl...","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85953178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-28DOI: 10.48550/arXiv.2304.14585
Feng Xie, Xiangji Zeng, Bin Zhou, Yusong Tan
Entity alignment (EA) which links equivalent entities across different knowledge graphs (KGs) plays a crucial role in knowledge fusion. In recent years, graph neural networks (GNNs) have been successfully applied in many embedding-based EA methods. However, existing GNN-based methods either suffer from the structural heterogeneity issue that especially appears in the real KG distributions or ignore the heterogeneous representation learning for unseen (unlabeled) entities, which would lead the model to overfit on few alignment seeds (i.e., training data) and thus cause unsatisfactory alignment performance. To enhance the EA ability, we propose GAEA, a novel EA approach based on graph augmentation. In this model, we design a simple Entity-Relation (ER) Encoder to generate latent representations for entities via jointly modeling comprehensive structural information and rich relation semantics. Moreover, we use graph augmentation to create two graph views for margin-based alignment learning and contrastive entity representation learning, thus mitigating structural heterogeneity and further improving the model's alignment performance. Extensive experiments conducted on benchmark datasets demonstrate the effectiveness of our method.
{"title":"Improving Knowledge Graph Entity Alignment with Graph Augmentation","authors":"Feng Xie, Xiangji Zeng, Bin Zhou, Yusong Tan","doi":"10.48550/arXiv.2304.14585","DOIUrl":"https://doi.org/10.48550/arXiv.2304.14585","url":null,"abstract":"Entity alignment (EA) which links equivalent entities across different knowledge graphs (KGs) plays a crucial role in knowledge fusion. In recent years, graph neural networks (GNNs) have been successfully applied in many embedding-based EA methods. However, existing GNN-based methods either suffer from the structural heterogeneity issue that especially appears in the real KG distributions or ignore the heterogeneous representation learning for unseen (unlabeled) entities, which would lead the model to overfit on few alignment seeds (i.e., training data) and thus cause unsatisfactory alignment performance. To enhance the EA ability, we propose GAEA, a novel EA approach based on graph augmentation. In this model, we design a simple Entity-Relation (ER) Encoder to generate latent representations for entities via jointly modeling comprehensive structural information and rich relation semantics. Moreover, we use graph augmentation to create two graph views for margin-based alignment learning and contrastive entity representation learning, thus mitigating structural heterogeneity and further improving the model's alignment performance. Extensive experiments conducted on benchmark datasets demonstrate the effectiveness of our method.","PeriodicalId":91995,"journal":{"name":"Advances in Knowledge Discovery and Data Mining : 21st Pacific-Asia Conference, PAKDD 2017, Jeju, South Korea, May 23-26, 2017, Proceedings. Part I. Pacific-Asia Conference on Knowledge Discovery and Data Mining (21st : 2017 : Cheju Isl...","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87169467","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the widespread popularity of user-generated short videos, it becomes increasingly challenging for content creators to promote their content to potential viewers. Automatically generating appealing titles and covers for short videos can help grab viewers' attention. Existing studies on video captioning mostly focus on generating factual descriptions of actions, which do not conform to video titles intended for catching viewer attention. Furthermore, research for cover selection based on multimodal information is sparse. These problems motivate the need for tailored methods to specifically support the joint task of short video title generation and cover selection (TG-CS) as well as the demand for creating corresponding datasets to support the studies. In this paper, we first collect and present a real-world dataset named Short Video Title Generation (SVTG) that contains videos with appealing titles and covers. We then propose a Title generation and Cover selection with attention Refinement (TCR) method for TG-CS. The refinement procedure progressively selects high-quality samples and highly relevant frames and text tokens within each sample to refine model training. Extensive experiments show that our TCR method is superior to various existing video captioning methods in generating titles and is able to select better covers for noisy real-world short videos.
{"title":"TCR: Short Video Title Generation and Cover Selection with Attention Refinement","authors":"Yu, Jiuding Yang, Weidong Guo, Hui Liu, Yu Xu, Di Niu","doi":"10.48550/arXiv.2304.12561","DOIUrl":"https://doi.org/10.48550/arXiv.2304.12561","url":null,"abstract":"With the widespread popularity of user-generated short videos, it becomes increasingly challenging for content creators to promote their content to potential viewers. Automatically generating appealing titles and covers for short videos can help grab viewers' attention. Existing studies on video captioning mostly focus on generating factual descriptions of actions, which do not conform to video titles intended for catching viewer attention. Furthermore, research for cover selection based on multimodal information is sparse. These problems motivate the need for tailored methods to specifically support the joint task of short video title generation and cover selection (TG-CS) as well as the demand for creating corresponding datasets to support the studies. In this paper, we first collect and present a real-world dataset named Short Video Title Generation (SVTG) that contains videos with appealing titles and covers. We then propose a Title generation and Cover selection with attention Refinement (TCR) method for TG-CS. The refinement procedure progressively selects high-quality samples and highly relevant frames and text tokens within each sample to refine model training. Extensive experiments show that our TCR method is superior to various existing video captioning methods in generating titles and is able to select better covers for noisy real-world short videos.","PeriodicalId":91995,"journal":{"name":"Advances in Knowledge Discovery and Data Mining : 21st Pacific-Asia Conference, PAKDD 2017, Jeju, South Korea, May 23-26, 2017, Proceedings. Part I. Pacific-Asia Conference on Knowledge Discovery and Data Mining (21st : 2017 : Cheju Isl...","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76891888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-04DOI: 10.48550/arXiv.2304.01547
Talal Algumaei, Rubén Solozabal, Réda Alami, Hakim Hacid, M. Debbah, Martin Takác
This work studies non-cooperative Multi-Agent Reinforcement Learning (MARL) where multiple agents interact in the same environment and whose goal is to maximize the individual returns. Challenges arise when scaling up the number of agents due to the resultant non-stationarity that the many agents introduce. In order to address this issue, Mean Field Games (MFG) rely on the symmetry and homogeneity assumptions to approximate games with very large populations. Recently, deep Reinforcement Learning has been used to scale MFG to games with larger number of states. Current methods rely on smoothing techniques such as averaging the q-values or the updates on the mean-field distribution. This work presents a different approach to stabilize the learning based on proximal updates on the mean-field policy. We name our algorithm Mean Field Proximal Policy Optimization (MF-PPO), and we empirically show the effectiveness of our method in the OpenSpiel framework.
本文研究了多智能体在同一环境中以个体收益最大化为目标进行交互的非合作多智能体强化学习(MARL)。当增加代理数量时，由于许多代理引入的非平稳性而产生挑战。为了解决这个问题，平均场游戏(Mean Field Games, MFG)依靠对称性和同质性假设来近似具有大量人口的游戏。最近，深度强化学习被用于将MFG扩展到具有更多状态的游戏。目前的方法依赖于平滑技术，如平均q值或更新平均场分布。这项工作提出了一种基于平均场策略的近端更新来稳定学习的不同方法。我们将我们的算法命名为平均域近端策略优化(MF-PPO)，并在OpenSpiel框架中实证地证明了我们的方法的有效性。
{"title":"Regularization of the policy updates for stabilizing Mean Field Games","authors":"Talal Algumaei, Rubén Solozabal, Réda Alami, Hakim Hacid, M. Debbah, Martin Takác","doi":"10.48550/arXiv.2304.01547","DOIUrl":"https://doi.org/10.48550/arXiv.2304.01547","url":null,"abstract":"This work studies non-cooperative Multi-Agent Reinforcement Learning (MARL) where multiple agents interact in the same environment and whose goal is to maximize the individual returns. Challenges arise when scaling up the number of agents due to the resultant non-stationarity that the many agents introduce. In order to address this issue, Mean Field Games (MFG) rely on the symmetry and homogeneity assumptions to approximate games with very large populations. Recently, deep Reinforcement Learning has been used to scale MFG to games with larger number of states. Current methods rely on smoothing techniques such as averaging the q-values or the updates on the mean-field distribution. This work presents a different approach to stabilize the learning based on proximal updates on the mean-field policy. We name our algorithm Mean Field Proximal Policy Optimization (MF-PPO), and we empirically show the effectiveness of our method in the OpenSpiel framework.","PeriodicalId":91995,"journal":{"name":"Advances in Knowledge Discovery and Data Mining : 21st Pacific-Asia Conference, PAKDD 2017, Jeju, South Korea, May 23-26, 2017, Proceedings. Part I. Pacific-Asia Conference on Knowledge Discovery and Data Mining (21st : 2017 : Cheju Isl...","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77109443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-03DOI: 10.48550/arXiv.2304.00813
Chi Zhang, Wenjie Ruan, Fu Lee Wang, Peipei Xu, Geyong Min, Xiaowei Huang
Verification plays an essential role in the formal analysis of safety-critical systems. Most current verification methods have specific requirements when working on Deep Neural Networks (DNNs). They either target one particular network category, e.g., Feedforward Neural Networks (FNNs), or networks with specific activation functions, e.g., RdLU. In this paper, we develop a model-agnostic verification framework, called DeepAgn, and show that it can be applied to FNNs, Recurrent Neural Networks (RNNs), or a mixture of both. Under the assumption of Lipschitz continuity, DeepAgn analyses the reachability of DNNs based on a novel optimisation scheme with a global convergence guarantee. It does not require access to the network's internal structures, such as layers and parameters. Through reachability analysis, DeepAgn can tackle several well-known robustness problems, including computing the maximum safe radius for a given input, and generating the ground-truth adversarial examples. We also empirically demonstrate DeepAgn's superior capability and efficiency in handling a broader class of deep neural networks, including both FNNs, and RNNs with very deep layers and millions of neurons, than other state-of-the-art verification approaches.
{"title":"Model-Agnostic Reachability Analysis on Deep Neural Networks","authors":"Chi Zhang, Wenjie Ruan, Fu Lee Wang, Peipei Xu, Geyong Min, Xiaowei Huang","doi":"10.48550/arXiv.2304.00813","DOIUrl":"https://doi.org/10.48550/arXiv.2304.00813","url":null,"abstract":"Verification plays an essential role in the formal analysis of safety-critical systems. Most current verification methods have specific requirements when working on Deep Neural Networks (DNNs). They either target one particular network category, e.g., Feedforward Neural Networks (FNNs), or networks with specific activation functions, e.g., RdLU. In this paper, we develop a model-agnostic verification framework, called DeepAgn, and show that it can be applied to FNNs, Recurrent Neural Networks (RNNs), or a mixture of both. Under the assumption of Lipschitz continuity, DeepAgn analyses the reachability of DNNs based on a novel optimisation scheme with a global convergence guarantee. It does not require access to the network's internal structures, such as layers and parameters. Through reachability analysis, DeepAgn can tackle several well-known robustness problems, including computing the maximum safe radius for a given input, and generating the ground-truth adversarial examples. We also empirically demonstrate DeepAgn's superior capability and efficiency in handling a broader class of deep neural networks, including both FNNs, and RNNs with very deep layers and millions of neurons, than other state-of-the-art verification approaches.","PeriodicalId":91995,"journal":{"name":"Advances in Knowledge Discovery and Data Mining : 21st Pacific-Asia Conference, PAKDD 2017, Jeju, South Korea, May 23-26, 2017, Proceedings. Part I. Pacific-Asia Conference on Knowledge Discovery and Data Mining (21st : 2017 : Cheju Isl...","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86978074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Advances in Knowledge Discovery and Data Mining : 21st Pacific-Asia Conference, PAKDD 2017, Jeju, South Korea, May 23-26, 2017, Proceedings. Part I. Pacific-Asia Conference on Knowledge Discovery and Data Mining (21st : 2017 : Cheju Isl...
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：