Pub Date : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892378
Lijun Zha, Le Dai, Tong Xu, Di Wu
Investment is a common economics task in which investors maximize future profits by continuously reallocating their current assets. A large number of studies are based on specifying stocks and constantly adjusting the ratio between these stocks to gain more benefits. However, the question of which stocks should be included in the portfolio is not addressed, while some investment strategies only select stocks and buy them without portfolio optimization, which may also cause unexpected loss owing to market oscillation. We try to integrate stock selection and portfolio optimization as a complete process to address this problem using hierarchical reinforcement learning. The high-level policy selects stocks with a high profitable probability, and then the low-level policy makes portfolio optimization on the selected stocks to gain more profit. The performance in China market demonstrates that our hierarchical agents can over performance a single stock selection agent.
{"title":"A Hierarchical Reinforcement Learning Framework for Stock Selection and Portfolio","authors":"Lijun Zha, Le Dai, Tong Xu, Di Wu","doi":"10.1109/IJCNN55064.2022.9892378","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892378","url":null,"abstract":"Investment is a common economics task in which investors maximize future profits by continuously reallocating their current assets. A large number of studies are based on specifying stocks and constantly adjusting the ratio between these stocks to gain more benefits. However, the question of which stocks should be included in the portfolio is not addressed, while some investment strategies only select stocks and buy them without portfolio optimization, which may also cause unexpected loss owing to market oscillation. We try to integrate stock selection and portfolio optimization as a complete process to address this problem using hierarchical reinforcement learning. The high-level policy selects stocks with a high profitable probability, and then the low-level policy makes portfolio optimization on the selected stocks to gain more profit. The performance in China market demonstrates that our hierarchical agents can over performance a single stock selection agent.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127175738","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 : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892216
Deepak Mohapatra, Ankush Ojha, H. Khadilkar, Supratim Ghosh
The problem of optimal and efficient scheduling and navigation of trains in large railway networks has attracted attention from both operations research (OR) and artificial intelligence (AI) communities. At its core, this problem is comprised of two inter-linked sub-problems: the vehicle re-scheduling problem (VRSP) and the multi-agent path-finding problem (MAPF). In this paper, we propose Gatekeeper: a reinforcement-learning-cum-heuristic based approach for scheduling and path planning of trains in complex environments. By extensive experiments on the Flatland (a public customisable environment for multi-train scheduling and path planning), we show that Gatekeeper outperforms top RL baselines both in terms of normalized scores and makespan, while remaining competitive against pure heuristic algorithms.
{"title":"Gatekeeper: A deep reinforcement learning-cum-heuristic based algorithm for scheduling and routing trains in complex environments","authors":"Deepak Mohapatra, Ankush Ojha, H. Khadilkar, Supratim Ghosh","doi":"10.1109/IJCNN55064.2022.9892216","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892216","url":null,"abstract":"The problem of optimal and efficient scheduling and navigation of trains in large railway networks has attracted attention from both operations research (OR) and artificial intelligence (AI) communities. At its core, this problem is comprised of two inter-linked sub-problems: the vehicle re-scheduling problem (VRSP) and the multi-agent path-finding problem (MAPF). In this paper, we propose Gatekeeper: a reinforcement-learning-cum-heuristic based approach for scheduling and path planning of trains in complex environments. By extensive experiments on the Flatland (a public customisable environment for multi-train scheduling and path planning), we show that Gatekeeper outperforms top RL baselines both in terms of normalized scores and makespan, while remaining competitive against pure heuristic algorithms.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127277286","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}
Social networks have been the widespread popular tools for communication and socialization, and it also been the ideal platform for bots to publish malicious information. Therefore, social bot detection is essential for the social network's security. Existing methods almost ignore the differences in bot behaviors in multiple domains. Thus, we first propose a DomainAware detection method with Multi-Relational Graph neural networks (DA-MRG) to improve detection performance. Specifically, DA-MRG constructs multi-relational graphs with users' features and relationships, obtains the user presentations with graph embedding and distinguishes bots from humans with domainaware classifiers. Meanwhile, considering the similarity between bot behaviors in different social networks, we believe that sharing data among them could boost detection performance. However, the data privacy of users needs to be strictly protected. To overcome the problem, we implement a study of federated learning framework for DA-MRG to achieve data sharing between different social networks and protect data privacy simultaneously. We conduct extensive experiments on TwiBot-20, and the results demonstrate that the proposed method can effectively achieve federated social bot detection.
{"title":"Domain-Aware Federated Social Bot Detection with Multi-Relational Graph Neural Networks","authors":"Huailiang Peng, Yujun Zhang, Hao Sun, Xu Bai, Yangyang Li, Shuhai Wang","doi":"10.1109/IJCNN55064.2022.9892366","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892366","url":null,"abstract":"Social networks have been the widespread popular tools for communication and socialization, and it also been the ideal platform for bots to publish malicious information. Therefore, social bot detection is essential for the social network's security. Existing methods almost ignore the differences in bot behaviors in multiple domains. Thus, we first propose a DomainAware detection method with Multi-Relational Graph neural networks (DA-MRG) to improve detection performance. Specifically, DA-MRG constructs multi-relational graphs with users' features and relationships, obtains the user presentations with graph embedding and distinguishes bots from humans with domainaware classifiers. Meanwhile, considering the similarity between bot behaviors in different social networks, we believe that sharing data among them could boost detection performance. However, the data privacy of users needs to be strictly protected. To overcome the problem, we implement a study of federated learning framework for DA-MRG to achieve data sharing between different social networks and protect data privacy simultaneously. We conduct extensive experiments on TwiBot-20, and the results demonstrate that the proposed method can effectively achieve federated social bot detection.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127435761","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 : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892717
Carlos H. C. Pena, Ing Ren Tsang, Pedro D. Marrero-Fernández, F. Guerrero-Peña, Alexandre Cunha
The segmentation of cells present in microscope images is an essential step in many tasks, including determining protein concentration and analysis of gene expression per cell. In single-cell genomics studies, cell segmentations are vital to assess the genetic makeup of individual cells and their relative spatial location. Several methods and tools have been developed to offer robust segmentation, with deep learning models currently being the most promising solutions. As an alternative to developing another cell segmentation targeted model, we propose a learning ensemble strategy that aggregates many independent candidate segmentations of the same image to produce a single consensus segmentation. We are particularly interested in learning how to ensemble crowdsource image segmentations created by experts and non-experts in laboratories and data houses. We compare our trained ensemble model with other fusion methods adopted by the biomedical community and assess the robustness of the results on three aspects: fusion with outliers, missing data, and synthetic deformations. Our approach outperforms these methods in efficiency and quality, especially when there is a high disagreement among candidate segmentations of the same image.
{"title":"An Ensemble Learning Method for Segmentation Fusion","authors":"Carlos H. C. Pena, Ing Ren Tsang, Pedro D. Marrero-Fernández, F. Guerrero-Peña, Alexandre Cunha","doi":"10.1109/IJCNN55064.2022.9892717","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892717","url":null,"abstract":"The segmentation of cells present in microscope images is an essential step in many tasks, including determining protein concentration and analysis of gene expression per cell. In single-cell genomics studies, cell segmentations are vital to assess the genetic makeup of individual cells and their relative spatial location. Several methods and tools have been developed to offer robust segmentation, with deep learning models currently being the most promising solutions. As an alternative to developing another cell segmentation targeted model, we propose a learning ensemble strategy that aggregates many independent candidate segmentations of the same image to produce a single consensus segmentation. We are particularly interested in learning how to ensemble crowdsource image segmentations created by experts and non-experts in laboratories and data houses. We compare our trained ensemble model with other fusion methods adopted by the biomedical community and assess the robustness of the results on three aspects: fusion with outliers, missing data, and synthetic deformations. Our approach outperforms these methods in efficiency and quality, especially when there is a high disagreement among candidate segmentations of the same image.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124809986","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 : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892156
Yao Cheng, Hao–Zhou Hao, Yi Ji, Ying Li, Chunping Liu
Camouflaged Object Detection (COD) aims to discover objects that are finely disguised in the environment. Its challenge is that the targets generally have similar textures and colors to their surroundings. In this paper, we propose a novel network, named attention-based neighbor selective aggregation network (ANSA-Net), which can effectively and efficiently detect camouflaged objects. Specifically, our ANSA-Net contains two novel modules, namely, neighbor selective aggregation (NSA) and high-level feature guided attention (HLGA). The NSA is designed to locate concealed targets by fusing multi-scale features adaptively. Furthermore, the HLGA is designed to improve the semantic information of features by employing attention maps derived from high-level features. Experiments show that ANSA-Net exhibits relatively accurate detection performance on four COD datasets, outperforming existing state-of-the-art methods.
{"title":"Attention-based Neighbor Selective Aggregation Network for Camouflaged Object Detection","authors":"Yao Cheng, Hao–Zhou Hao, Yi Ji, Ying Li, Chunping Liu","doi":"10.1109/IJCNN55064.2022.9892156","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892156","url":null,"abstract":"Camouflaged Object Detection (COD) aims to discover objects that are finely disguised in the environment. Its challenge is that the targets generally have similar textures and colors to their surroundings. In this paper, we propose a novel network, named attention-based neighbor selective aggregation network (ANSA-Net), which can effectively and efficiently detect camouflaged objects. Specifically, our ANSA-Net contains two novel modules, namely, neighbor selective aggregation (NSA) and high-level feature guided attention (HLGA). The NSA is designed to locate concealed targets by fusing multi-scale features adaptively. Furthermore, the HLGA is designed to improve the semantic information of features by employing attention maps derived from high-level features. Experiments show that ANSA-Net exhibits relatively accurate detection performance on four COD datasets, outperforming existing state-of-the-art methods.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124880905","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 : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892162
Xingyu Zhu, Jin Wang, Xuejie Zhang
Multi-party dialogue machine reading comprehension (MRC) is more challenging than plain text MRC because it involves multiple speakers, more complex information flow interaction, and discourse structure. Previously most researchers focus on decoupling the speaker-aware and utterance-aware information to overcome such difficulties. Based on this, the self- and pseudo-self-supervised prediction auxiliary tasks on speakers and key-utterance are proposed. However, the information interaction among key-utterance, question, and dialogue context was ignored in these works, and there should also be a constraint between the two additional tasks. Herein, we proposed an enhanced key-utterance interaction model. It takes the key-utterance predicted by auxiliary task as prior information. Moreover, the co-attention mechanism is used to capture the critical information interaction among dialogue contexts, question, and key-utterance from the two perspectives of question-to-dialogue and dialogue-to-question, respectively. In addition, we introduced minimizing mutual information (MI) between the two auxiliary tasks to prevent mutual interference and overlap of information. Experimental results show that the proposed model achieves significant improvements than the dialogue MRC baseline models in Molweni and FriendsQA datasets.
{"title":"An Enhanced Key-utterance Interactive Model with Decouped Auxiliary Tasks for Multi-party Dialogue Reading Comprehension","authors":"Xingyu Zhu, Jin Wang, Xuejie Zhang","doi":"10.1109/IJCNN55064.2022.9892162","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892162","url":null,"abstract":"Multi-party dialogue machine reading comprehension (MRC) is more challenging than plain text MRC because it involves multiple speakers, more complex information flow interaction, and discourse structure. Previously most researchers focus on decoupling the speaker-aware and utterance-aware information to overcome such difficulties. Based on this, the self- and pseudo-self-supervised prediction auxiliary tasks on speakers and key-utterance are proposed. However, the information interaction among key-utterance, question, and dialogue context was ignored in these works, and there should also be a constraint between the two additional tasks. Herein, we proposed an enhanced key-utterance interaction model. It takes the key-utterance predicted by auxiliary task as prior information. Moreover, the co-attention mechanism is used to capture the critical information interaction among dialogue contexts, question, and key-utterance from the two perspectives of question-to-dialogue and dialogue-to-question, respectively. In addition, we introduced minimizing mutual information (MI) between the two auxiliary tasks to prevent mutual interference and overlap of information. Experimental results show that the proposed model achieves significant improvements than the dialogue MRC baseline models in Molweni and FriendsQA datasets.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124904996","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 : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892730
Weihao Jiang, Yao Fu, Hong Zhao, Junhong Wan, Shi Pu
Reasoning over knowledge graph explores valuable information for amounts of tasks. However, most methods adopt the coarse-grained and single representation of each entity for reasoning, ignoring simultaneously processing various semantics contained in internal information and external information. On the one hand, the surrounding nodes and relations existing in the graph structure express the internal information of the entity, which contains abundant graph context information, but the extracted internal features are still limited. On the other hand, different scenarios as the external information focus on different aspects of the certain entity, meanwhile the external information should have message interaction with the internal information to learn the adaptive embedding, both of which are seldom considered by the existing methods. In this paper, we propose a Graph Intention Neural Network (GINN) for knowledge graph reasoning to explore fine-grained entity representations, which use external-intention and internal-intention simultaneously. For external-intention, a novel constructed matrix is used to calculate the triple-attention that determines the aggregated information to learn different embeddings adapting to the different scenarios. Furthermore, a communication bridge is leveraged to have message interaction between the external information and the internal information. For the internal-intention, the surrounding nodes and relations are integrated to update the entity embedding with the consideration of the interaction features between the external and internal information. The triple-attention can capture relevancy among the reasoning hops, which contributes to figuring out reasonable paths. We evaluate our approach on real-world datasets, achieving better performance compared to the state-of-the-art methods and showing plausible interpretability for the results.
{"title":"Graph Intention Neural Network for Knowledge Graph Reasoning","authors":"Weihao Jiang, Yao Fu, Hong Zhao, Junhong Wan, Shi Pu","doi":"10.1109/IJCNN55064.2022.9892730","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892730","url":null,"abstract":"Reasoning over knowledge graph explores valuable information for amounts of tasks. However, most methods adopt the coarse-grained and single representation of each entity for reasoning, ignoring simultaneously processing various semantics contained in internal information and external information. On the one hand, the surrounding nodes and relations existing in the graph structure express the internal information of the entity, which contains abundant graph context information, but the extracted internal features are still limited. On the other hand, different scenarios as the external information focus on different aspects of the certain entity, meanwhile the external information should have message interaction with the internal information to learn the adaptive embedding, both of which are seldom considered by the existing methods. In this paper, we propose a Graph Intention Neural Network (GINN) for knowledge graph reasoning to explore fine-grained entity representations, which use external-intention and internal-intention simultaneously. For external-intention, a novel constructed matrix is used to calculate the triple-attention that determines the aggregated information to learn different embeddings adapting to the different scenarios. Furthermore, a communication bridge is leveraged to have message interaction between the external information and the internal information. For the internal-intention, the surrounding nodes and relations are integrated to update the entity embedding with the consideration of the interaction features between the external and internal information. The triple-attention can capture relevancy among the reasoning hops, which contributes to figuring out reasonable paths. We evaluate our approach on real-world datasets, achieving better performance compared to the state-of-the-art methods and showing plausible interpretability for the results.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125054872","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 : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9891960
Haoze Yang, Kunyao Lan, Jiawei You, Liping Shen
Answer-aware question generation aims to generate answerable questions from a given paragraph and answer. Most of the current models concatenated entity information into word embeddings to improve the model's learning ability for special entities, but this method is inefficient for utilizing these information and has accumulated errors. In addition, the majority of research focuses on English, with less exploration in languages such as Chinese. Combining the differences between languages, we propose three methods for incorporating entity information in paragraphs and answers into the training corpus. The corpus processed by these methods can enable the model to have the ability to learn entities autonomously. The experimental results show that our methods can improve most mainstream models and enhance the learning ability of the model for special entities.
{"title":"A simple but practical method: How to improve the usage of entities in the Chinese question generation","authors":"Haoze Yang, Kunyao Lan, Jiawei You, Liping Shen","doi":"10.1109/IJCNN55064.2022.9891960","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9891960","url":null,"abstract":"Answer-aware question generation aims to generate answerable questions from a given paragraph and answer. Most of the current models concatenated entity information into word embeddings to improve the model's learning ability for special entities, but this method is inefficient for utilizing these information and has accumulated errors. In addition, the majority of research focuses on English, with less exploration in languages such as Chinese. Combining the differences between languages, we propose three methods for incorporating entity information in paragraphs and answers into the training corpus. The corpus processed by these methods can enable the model to have the ability to learn entities autonomously. The experimental results show that our methods can improve most mainstream models and enhance the learning ability of the model for special entities.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125924668","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}
Cooperative multi-agent reinforcement learning has been considered promising to complete many complex cooperative tasks in the real world such as coordination of robot swarms and self-driving. To promote multi-agent cooperation, Centralized Training with Decentralized Execution emerges as a popular learning paradigm due to partial observability and communication constraints during execution and computational complexity in training. Value decomposition has been known to produce competitive performance to other methods in complex environment within this paradigm such as VDN and QMIX, which approximates the global joint Q-value function with multiple local individual Q-value functions. However, existing works often neglect the uncertainty of multiple agents resulting from the partial observability and very large action space in the multi-agent setting and can only obtain the sub-optimal policy. To alleviate the limitations above, building upon the value decomposition, we propose a novel method called multi-agent uncertainty sharing (MAUS). This method utilizes the Bayesian neural network to explicitly capture the uncertainty of all agents and combines with Thompson sampling to select actions for policy learning. Besides, we impose the uncertainty-sharing mechanism among agents to stabilize training as well as coordinate the behaviors of all the agents for multi-agent cooperation. Extensive experiments on the StarCraft Multi-Agent Challenge (SMAC) environment demonstrate that our approach achieves significant performance to exceed the prior baselines and verify the effectiveness of our method.
{"title":"Multi-Agent Uncertainty Sharing for Cooperative Multi-Agent Reinforcement Learning","authors":"Haoxing Chen, Guangkai Yang, Junge Zhang, Qiyue Yin, Kaiqi Huang","doi":"10.1109/IJCNN55064.2022.9891948","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9891948","url":null,"abstract":"Cooperative multi-agent reinforcement learning has been considered promising to complete many complex cooperative tasks in the real world such as coordination of robot swarms and self-driving. To promote multi-agent cooperation, Centralized Training with Decentralized Execution emerges as a popular learning paradigm due to partial observability and communication constraints during execution and computational complexity in training. Value decomposition has been known to produce competitive performance to other methods in complex environment within this paradigm such as VDN and QMIX, which approximates the global joint Q-value function with multiple local individual Q-value functions. However, existing works often neglect the uncertainty of multiple agents resulting from the partial observability and very large action space in the multi-agent setting and can only obtain the sub-optimal policy. To alleviate the limitations above, building upon the value decomposition, we propose a novel method called multi-agent uncertainty sharing (MAUS). This method utilizes the Bayesian neural network to explicitly capture the uncertainty of all agents and combines with Thompson sampling to select actions for policy learning. Besides, we impose the uncertainty-sharing mechanism among agents to stabilize training as well as coordinate the behaviors of all the agents for multi-agent cooperation. Extensive experiments on the StarCraft Multi-Agent Challenge (SMAC) environment demonstrate that our approach achieves significant performance to exceed the prior baselines and verify the effectiveness of our method.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126022065","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 : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892071
Rushirajsinh Parmar, M. Kuribayashi, Hiroto Takiwaki, M. Raval
Researchers are increasingly interested to study novel attacks on machine learning models. The classifiers are fooled by making small perturbation to the input or by learning patches that can be applied to objects. In this paper we present an iterative approach to generate a patch that when digitally placed on the face can successfully fool the facial recognition system. We focus on dodging attack where a target face is misidentified as any other face. The proof of concept is show-cased using FGSM and FaceNet face recognition system under the white-box attack. The framework is generic and it can be extended to other noise model and recognition system. It has been evaluated for different - patch size, noise strength, patch location, number of patches and dataset. The experiments shows that the proposed approach can significantly lower the recognition accuracy. Compared to state of the art digital-world attacks, the proposed approach is simpler and can generate inconspicuous natural looking patch with comparable fool rate and smallest patch size.
{"title":"On Fooling Facial Recognition Systems using Adversarial Patches","authors":"Rushirajsinh Parmar, M. Kuribayashi, Hiroto Takiwaki, M. Raval","doi":"10.1109/IJCNN55064.2022.9892071","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892071","url":null,"abstract":"Researchers are increasingly interested to study novel attacks on machine learning models. The classifiers are fooled by making small perturbation to the input or by learning patches that can be applied to objects. In this paper we present an iterative approach to generate a patch that when digitally placed on the face can successfully fool the facial recognition system. We focus on dodging attack where a target face is misidentified as any other face. The proof of concept is show-cased using FGSM and FaceNet face recognition system under the white-box attack. The framework is generic and it can be extended to other noise model and recognition system. It has been evaluated for different - patch size, noise strength, patch location, number of patches and dataset. The experiments shows that the proposed approach can significantly lower the recognition accuracy. Compared to state of the art digital-world attacks, the proposed approach is simpler and can generate inconspicuous natural looking patch with comparable fool rate and smallest patch size.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123292066","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}
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：