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
Representation learning is an important step in the machine learning pipeline. Given the current biological sequencing data volume, learning an explicit representation is prohibitive due to the dimensionality of the resulting feature vectors. Kernel-based methods, e.g., SVM, are a proven efficient and useful alternative for several machine learning (ML) tasks such as sequence classification. Three challenges with kernel methods are (i) the computation time, (ii) the memory usage (storing an $ntimes n$ matrix), and (iii) the usage of kernel matrices limited to kernel-based ML methods (difficult to generalize on non-kernel classifiers). While (i) can be solved using approximate methods, challenge (ii) remains for typical kernel methods. Similarly, although non-kernel-based ML methods can be applied to kernel matrices by extracting principal components (kernel PCA), it may result in information loss, while being computationally expensive. In this paper, we propose a general-purpose representation learning approach that embodies kernel methods' qualities while avoiding computation, memory, and generalizability challenges. This involves computing a low-dimensional embedding of each sequence, using random projections of its $k$-mer frequency vectors, significantly reducing the computation needed to compute the dot product and the memory needed to store the resulting representation. Our proposed fast and alignment-free embedding method can be used as input to any distance (e.g., $k$ nearest neighbors) and non-distance (e.g., decision tree) based ML method for classification and clustering tasks. Using different forms of biological sequences as input, we perform a variety of real-world classification tasks, such as SARS-CoV-2 lineage and gene family classification, outperforming several state-of-the-art embedding and kernel methods in predictive performance.
{"title":"BioSequence2Vec: Efficient Embedding Generation For Biological Sequences","authors":"Sarwan Ali, Usama Sardar, Murray Patterson, Imdadullah Khan","doi":"10.48550/arXiv.2304.00291","DOIUrl":"https://doi.org/10.48550/arXiv.2304.00291","url":null,"abstract":"Representation learning is an important step in the machine learning pipeline. Given the current biological sequencing data volume, learning an explicit representation is prohibitive due to the dimensionality of the resulting feature vectors. Kernel-based methods, e.g., SVM, are a proven efficient and useful alternative for several machine learning (ML) tasks such as sequence classification. Three challenges with kernel methods are (i) the computation time, (ii) the memory usage (storing an $ntimes n$ matrix), and (iii) the usage of kernel matrices limited to kernel-based ML methods (difficult to generalize on non-kernel classifiers). While (i) can be solved using approximate methods, challenge (ii) remains for typical kernel methods. Similarly, although non-kernel-based ML methods can be applied to kernel matrices by extracting principal components (kernel PCA), it may result in information loss, while being computationally expensive. In this paper, we propose a general-purpose representation learning approach that embodies kernel methods' qualities while avoiding computation, memory, and generalizability challenges. This involves computing a low-dimensional embedding of each sequence, using random projections of its $k$-mer frequency vectors, significantly reducing the computation needed to compute the dot product and the memory needed to store the resulting representation. Our proposed fast and alignment-free embedding method can be used as input to any distance (e.g., $k$ nearest neighbors) and non-distance (e.g., decision tree) based ML method for classification and clustering tasks. Using different forms of biological sequences as input, we perform a variety of real-world classification tasks, such as SARS-CoV-2 lineage and gene family classification, outperforming several state-of-the-art embedding and kernel methods in predictive performance.","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":"2023-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82349195","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 : 2023-03-26DOI: 10.48550/arXiv.2303.14668
Tri Dung Duong, Qian Li, Guandong Xu
Counterfactual explanation is a form of interpretable machine learning that generates perturbations on a sample to achieve the desired outcome. The generated samples can act as instructions to guide end users on how to observe the desired results by altering samples. Although state-of-the-art counterfactual explanation methods are proposed to use variational autoencoder (VAE) to achieve promising improvements, they suffer from two major limitations: 1) the counterfactuals generation is prohibitively slow, which prevents algorithms from being deployed in interactive environments; 2) the counterfactual explanation algorithms produce unstable results due to the randomness in the sampling procedure of variational autoencoder. In this work, to address the above limitations, we design a robust and efficient counterfactual explanation framework, namely CeFlow, which utilizes normalizing flows for the mixed-type of continuous and categorical features. Numerical experiments demonstrate that our technique compares favorably to state-of-the-art methods. We release our source at https://github.com/tridungduong16/fairCE.git for reproducing the results.
{"title":"CeFlow: A Robust and Efficient Counterfactual Explanation Framework for Tabular Data using Normalizing Flows","authors":"Tri Dung Duong, Qian Li, Guandong Xu","doi":"10.48550/arXiv.2303.14668","DOIUrl":"https://doi.org/10.48550/arXiv.2303.14668","url":null,"abstract":"Counterfactual explanation is a form of interpretable machine learning that generates perturbations on a sample to achieve the desired outcome. The generated samples can act as instructions to guide end users on how to observe the desired results by altering samples. Although state-of-the-art counterfactual explanation methods are proposed to use variational autoencoder (VAE) to achieve promising improvements, they suffer from two major limitations: 1) the counterfactuals generation is prohibitively slow, which prevents algorithms from being deployed in interactive environments; 2) the counterfactual explanation algorithms produce unstable results due to the randomness in the sampling procedure of variational autoencoder. In this work, to address the above limitations, we design a robust and efficient counterfactual explanation framework, namely CeFlow, which utilizes normalizing flows for the mixed-type of continuous and categorical features. Numerical experiments demonstrate that our technique compares favorably to state-of-the-art methods. We release our source at https://github.com/tridungduong16/fairCE.git for reproducing the results.","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":"2023-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74244268","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 : 2023-03-22DOI: 10.48550/arXiv.2303.12952
S. Saravanan, Tie Luo, Mao V. Ngo
Anomaly detection is widely used in network intrusion detection, autonomous driving, medical diagnosis, credit card frauds, etc. However, several key challenges remain open, such as lack of ground truth labels, presence of complex temporal patterns, and generalizing over different datasets. This paper proposes TSI-GAN, an unsupervised anomaly detection model for time-series that can learn complex temporal patterns automatically and generalize well, i.e., no need for choosing dataset-specific parameters, making statistical assumptions about underlying data, or changing model architectures. To achieve these goals, we convert each input time-series into a sequence of 2D images using two encoding techniques with the intent of capturing temporal patterns and various types of deviance. Moreover, we design a reconstructive GAN that uses convolutional layers in an encoder-decoder network and employs cycle-consistency loss during training to ensure that inverse mappings are accurate as well. In addition, we also instrument a Hodrick-Prescott filter in post-processing to mitigate false positives. We evaluate TSI-GAN using 250 well-curated and harder-than-usual datasets and compare with 8 state-of-the-art baseline methods. The results demonstrate the superiority of TSI-GAN to all the baselines, offering an overall performance improvement of 13% and 31% over the second-best performer MERLIN and the third-best performer LSTM-AE, respectively.
{"title":"TSI-GAN: Unsupervised Time Series Anomaly Detection using Convolutional Cycle-Consistent Generative Adversarial Networks","authors":"S. Saravanan, Tie Luo, Mao V. Ngo","doi":"10.48550/arXiv.2303.12952","DOIUrl":"https://doi.org/10.48550/arXiv.2303.12952","url":null,"abstract":"Anomaly detection is widely used in network intrusion detection, autonomous driving, medical diagnosis, credit card frauds, etc. However, several key challenges remain open, such as lack of ground truth labels, presence of complex temporal patterns, and generalizing over different datasets. This paper proposes TSI-GAN, an unsupervised anomaly detection model for time-series that can learn complex temporal patterns automatically and generalize well, i.e., no need for choosing dataset-specific parameters, making statistical assumptions about underlying data, or changing model architectures. To achieve these goals, we convert each input time-series into a sequence of 2D images using two encoding techniques with the intent of capturing temporal patterns and various types of deviance. Moreover, we design a reconstructive GAN that uses convolutional layers in an encoder-decoder network and employs cycle-consistency loss during training to ensure that inverse mappings are accurate as well. In addition, we also instrument a Hodrick-Prescott filter in post-processing to mitigate false positives. We evaluate TSI-GAN using 250 well-curated and harder-than-usual datasets and compare with 8 state-of-the-art baseline methods. The results demonstrate the superiority of TSI-GAN to all the baselines, offering an overall performance improvement of 13% and 31% over the second-best performer MERLIN and the third-best performer LSTM-AE, respectively.","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":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75386415","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 : 2023-03-20DOI: 10.48550/arXiv.2303.11053
A. Ganesh, Prajakta Nimbhorkar, Pratik Ghosal, HV VishwaPrakash
Allocation of scarce healthcare resources under limited logistic and infrastructural facilities is a major issue in the modern society. We consider the problem of allocation of healthcare resources like vaccines to people or hospital beds to patients in an online manner. Our model takes into account the arrival of resources on a day-to-day basis, different categories of agents, the possible unavailability of agents on certain days, and the utility associated with each allotment as well as its variation over time. We propose a model where priorities for various categories are modelled in terms of utilities of agents. We give online and offline algorithms to compute an allocation that respects eligibility of agents into different categories, and incentivizes agents not to hide their eligibility for some category. The offline algorithm gives an optimal allocation while the on-line algorithm gives an approximation to the optimal allocation in terms of total utility. Our algorithms are efficient, and maintain fairness among different categories of agents. Our models have applications in other areas like refugee settlement and visa allocation. We evaluate the performance of our algorithms on real-life and synthetic datasets. The experimental results show that the online algorithm is fast and performs better than the given theoretical bound in terms of total utility. Moreover, the experimental results confirm that our utility-based model correctly captures the priorities of categories
{"title":"Fair Healthcare Rationing to Maximize Dynamic Utilities","authors":"A. Ganesh, Prajakta Nimbhorkar, Pratik Ghosal, HV VishwaPrakash","doi":"10.48550/arXiv.2303.11053","DOIUrl":"https://doi.org/10.48550/arXiv.2303.11053","url":null,"abstract":"Allocation of scarce healthcare resources under limited logistic and infrastructural facilities is a major issue in the modern society. We consider the problem of allocation of healthcare resources like vaccines to people or hospital beds to patients in an online manner. Our model takes into account the arrival of resources on a day-to-day basis, different categories of agents, the possible unavailability of agents on certain days, and the utility associated with each allotment as well as its variation over time. We propose a model where priorities for various categories are modelled in terms of utilities of agents. We give online and offline algorithms to compute an allocation that respects eligibility of agents into different categories, and incentivizes agents not to hide their eligibility for some category. The offline algorithm gives an optimal allocation while the on-line algorithm gives an approximation to the optimal allocation in terms of total utility. Our algorithms are efficient, and maintain fairness among different categories of agents. Our models have applications in other areas like refugee settlement and visa allocation. We evaluate the performance of our algorithms on real-life and synthetic datasets. The experimental results show that the online algorithm is fast and performs better than the given theoretical bound in terms of total utility. Moreover, the experimental results confirm that our utility-based model correctly captures the priorities of categories","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":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77444098","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 : 2023-03-20DOI: 10.48550/arXiv.2303.11224
Tobias Weber, M. Ingrisch, Bernd Bischl, David Rügamer
While recent advances in large-scale foundational models show promising results, their application to the medical domain has not yet been explored in detail. In this paper, we progress into the realms of large-scale modeling in medical synthesis by proposing Cheff - a foundational cascaded latent diffusion model, which generates highly-realistic chest radiographs providing state-of-the-art quality on a 1-megapixel scale. We further propose MaCheX, which is a unified interface for public chest datasets and forms the largest open collection of chest X-rays up to date. With Cheff conditioned on radiological reports, we further guide the synthesis process over text prompts and unveil the research area of report-to-chest-X-ray generation.
{"title":"Cascaded Latent Diffusion Models for High-Resolution Chest X-ray Synthesis","authors":"Tobias Weber, M. Ingrisch, Bernd Bischl, David Rügamer","doi":"10.48550/arXiv.2303.11224","DOIUrl":"https://doi.org/10.48550/arXiv.2303.11224","url":null,"abstract":"While recent advances in large-scale foundational models show promising results, their application to the medical domain has not yet been explored in detail. In this paper, we progress into the realms of large-scale modeling in medical synthesis by proposing Cheff - a foundational cascaded latent diffusion model, which generates highly-realistic chest radiographs providing state-of-the-art quality on a 1-megapixel scale. We further propose MaCheX, which is a unified interface for public chest datasets and forms the largest open collection of chest X-rays up to date. With Cheff conditioned on radiological reports, we further guide the synthesis process over text prompts and unveil the research area of report-to-chest-X-ray generation.","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":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85410496","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 : 2023-03-17DOI: 10.48550/arXiv.2303.09960
Gözde Özcan, Stratis Ioannidis
In this paper, we study stochastic submodular maximization problems with general matroid constraints, that naturally arise in online learning, team formation, facility location, influence maximization, active learning and sensing objective functions. In other words, we focus on maximizing submodular functions that are defined as expectations over a class of submodular functions with an unknown distribution. We show that for monotone functions of this form, the stochastic continuous greedy algorithm attains an approximation ratio (in expectation) arbitrarily close to $(1-1/e) approx 63%$ using a polynomial estimation of the gradient. We argue that using this polynomial estimator instead of the prior art that uses sampling eliminates a source of randomness and experimentally reduces execution time.
{"title":"Stochastic Submodular Maximization via Polynomial Estimators","authors":"Gözde Özcan, Stratis Ioannidis","doi":"10.48550/arXiv.2303.09960","DOIUrl":"https://doi.org/10.48550/arXiv.2303.09960","url":null,"abstract":"In this paper, we study stochastic submodular maximization problems with general matroid constraints, that naturally arise in online learning, team formation, facility location, influence maximization, active learning and sensing objective functions. In other words, we focus on maximizing submodular functions that are defined as expectations over a class of submodular functions with an unknown distribution. We show that for monotone functions of this form, the stochastic continuous greedy algorithm attains an approximation ratio (in expectation) arbitrarily close to $(1-1/e) approx 63%$ using a polynomial estimation of the gradient. We argue that using this polynomial estimator instead of the prior art that uses sampling eliminates a source of randomness and experimentally reduces execution time.","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":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74202307","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 : 2023-03-17DOI: 10.48550/arXiv.2303.10255
Zidi Xiu, Kai-Chen Cheng, David Q. Sun, Jiannan Lu, Hadas Kotek, Yuhan Zhang, Paul McCarthy, Christopher Klein, S. Pulman, Jason D. Williams
With the growing popularity of intelligent assistants (IAs), evaluating IA quality becomes an increasingly active field of research. This paper identifies and quantifies the feedback effect, a novel component in IA-user interactions: how the capabilities and limitations of the IA influence user behavior over time. First, we demonstrate that unhelpful responses from the IA cause users to delay or reduce subsequent interactions in the short term via an observational study. Next, we expand the time horizon to examine behavior changes and show that as users discover the limitations of the IA's understanding and functional capabilities, they learn to adjust the scope and wording of their requests to increase the likelihood of receiving a helpful response from the IA. Our findings highlight the impact of the feedback effect at both the micro and meso levels. We further discuss its macro-level consequences: unsatisfactory interactions continuously reduce the likelihood and diversity of future user engagements in a feedback loop.
{"title":"Feedback Effect in User Interaction with Intelligent Assistants: Delayed Engagement, Adaption and Drop-out","authors":"Zidi Xiu, Kai-Chen Cheng, David Q. Sun, Jiannan Lu, Hadas Kotek, Yuhan Zhang, Paul McCarthy, Christopher Klein, S. Pulman, Jason D. Williams","doi":"10.48550/arXiv.2303.10255","DOIUrl":"https://doi.org/10.48550/arXiv.2303.10255","url":null,"abstract":"With the growing popularity of intelligent assistants (IAs), evaluating IA quality becomes an increasingly active field of research. This paper identifies and quantifies the feedback effect, a novel component in IA-user interactions: how the capabilities and limitations of the IA influence user behavior over time. First, we demonstrate that unhelpful responses from the IA cause users to delay or reduce subsequent interactions in the short term via an observational study. Next, we expand the time horizon to examine behavior changes and show that as users discover the limitations of the IA's understanding and functional capabilities, they learn to adjust the scope and wording of their requests to increase the likelihood of receiving a helpful response from the IA. Our findings highlight the impact of the feedback effect at both the micro and meso levels. We further discuss its macro-level consequences: unsatisfactory interactions continuously reduce the likelihood and diversity of future user engagements in a feedback loop.","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":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87112581","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 : 2023-03-09DOI: 10.48550/arXiv.2303.05082
Jing Yang, Bin Ji, Shasha Li, Jun Ma, Long Peng, Jie Yu
Recently, many studies incorporate external knowledge into character-level feature based models to improve the performance of Chinese relation extraction. However, these methods tend to ignore the internal information of the Chinese character and cannot filter out the noisy information of external knowledge. To address these issues, we propose a mixture-of-view-experts framework (MoVE) to dynamically learn multi-view features for Chinese relation extraction. With both the internal and external knowledge of Chinese characters, our framework can better capture the semantic information of Chinese characters. To demonstrate the effectiveness of the proposed framework, we conduct extensive experiments on three real-world datasets in distinct domains. Experimental results show consistent and significant superiority and robustness of our proposed framework. Our code and dataset will be released at: https://gitee.com/tmg-nudt/multi-view-of-expert-for-chineserelation-extraction
{"title":"Dynamic Multi-View Fusion Mechanism For Chinese Relation Extraction","authors":"Jing Yang, Bin Ji, Shasha Li, Jun Ma, Long Peng, Jie Yu","doi":"10.48550/arXiv.2303.05082","DOIUrl":"https://doi.org/10.48550/arXiv.2303.05082","url":null,"abstract":"Recently, many studies incorporate external knowledge into character-level feature based models to improve the performance of Chinese relation extraction. However, these methods tend to ignore the internal information of the Chinese character and cannot filter out the noisy information of external knowledge. To address these issues, we propose a mixture-of-view-experts framework (MoVE) to dynamically learn multi-view features for Chinese relation extraction. With both the internal and external knowledge of Chinese characters, our framework can better capture the semantic information of Chinese characters. To demonstrate the effectiveness of the proposed framework, we conduct extensive experiments on three real-world datasets in distinct domains. Experimental results show consistent and significant superiority and robustness of our proposed framework. Our code and dataset will be released at: https://gitee.com/tmg-nudt/multi-view-of-expert-for-chineserelation-extraction","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":"2023-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87647726","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 : 2023-03-09DOI: 10.48550/arXiv.2303.07199
Hai Zhu, Qingyang Zhao, Yuren Wu
Natural language processing models based on neural networks are vulnerable to adversarial examples. These adversarial examples are imperceptible to human readers but can mislead models to make the wrong predictions. In a black-box setting, attacker can fool the model without knowing model's parameters and architecture. Previous works on word-level attacks widely use single semantic space and greedy search as a search strategy. However, these methods fail to balance the attack success rate, quality of adversarial examples and time consumption. In this paper, we propose BeamAttack, a textual attack algorithm that makes use of mixed semantic spaces and improved beam search to craft high-quality adversarial examples. Extensive experiments demonstrate that BeamAttack can improve attack success rate while saving numerous queries and time, e.g., improving at most 7% attack success rate than greedy search when attacking the examples from MR dataset. Compared with heuristic search, BeamAttack can save at most 85% model queries and achieve a competitive attack success rate. The adversarial examples crafted by BeamAttack are highly transferable and can effectively improve model's robustness during adversarial training. Code is available at https://github.com/zhuhai-ustc/beamattack/tree/master
{"title":"BeamAttack: Generating High-quality Textual Adversarial Examples through Beam Search and Mixed Semantic Spaces","authors":"Hai Zhu, Qingyang Zhao, Yuren Wu","doi":"10.48550/arXiv.2303.07199","DOIUrl":"https://doi.org/10.48550/arXiv.2303.07199","url":null,"abstract":"Natural language processing models based on neural networks are vulnerable to adversarial examples. These adversarial examples are imperceptible to human readers but can mislead models to make the wrong predictions. In a black-box setting, attacker can fool the model without knowing model's parameters and architecture. Previous works on word-level attacks widely use single semantic space and greedy search as a search strategy. However, these methods fail to balance the attack success rate, quality of adversarial examples and time consumption. In this paper, we propose BeamAttack, a textual attack algorithm that makes use of mixed semantic spaces and improved beam search to craft high-quality adversarial examples. Extensive experiments demonstrate that BeamAttack can improve attack success rate while saving numerous queries and time, e.g., improving at most 7% attack success rate than greedy search when attacking the examples from MR dataset. Compared with heuristic search, BeamAttack can save at most 85% model queries and achieve a competitive attack success rate. The adversarial examples crafted by BeamAttack are highly transferable and can effectively improve model's robustness during adversarial training. Code is available at https://github.com/zhuhai-ustc/beamattack/tree/master","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":"2023-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88004754","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 : 2023-03-08DOI: 10.48550/arXiv.2303.04343
Xiulong Yang, Shihao Ji
Energy-based models (EBMs) exhibit a variety of desirable properties in predictive tasks, such as generality, simplicity and compositionality. However, training EBMs on high-dimensional datasets remains unstable and expensive. In this paper, we present a Manifold EBM (M-EBM) to boost the overall performance of unconditional EBM and Joint Energy-based Model (JEM). Despite its simplicity, M-EBM significantly improves unconditional EBMs in training stability and speed on a host of benchmark datasets, such as CIFAR10, CIFAR100, CelebA-HQ, and ImageNet 32x32. Once class labels are available, label-incorporated M-EBM (M-JEM) further surpasses M-EBM in image generation quality with an over 40% FID improvement, while enjoying improved accuracy. The code can be found at https://github.com/sndnyang/mebm.
{"title":"M-EBM: Towards Understanding the Manifolds of Energy-Based Models","authors":"Xiulong Yang, Shihao Ji","doi":"10.48550/arXiv.2303.04343","DOIUrl":"https://doi.org/10.48550/arXiv.2303.04343","url":null,"abstract":"Energy-based models (EBMs) exhibit a variety of desirable properties in predictive tasks, such as generality, simplicity and compositionality. However, training EBMs on high-dimensional datasets remains unstable and expensive. In this paper, we present a Manifold EBM (M-EBM) to boost the overall performance of unconditional EBM and Joint Energy-based Model (JEM). Despite its simplicity, M-EBM significantly improves unconditional EBMs in training stability and speed on a host of benchmark datasets, such as CIFAR10, CIFAR100, CelebA-HQ, and ImageNet 32x32. Once class labels are available, label-incorporated M-EBM (M-JEM) further surpasses M-EBM in image generation quality with an over 40% FID improvement, while enjoying improved accuracy. The code can be found at https://github.com/sndnyang/mebm.","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":"2023-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87651882","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：