Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence最新文献_第6页

PGSS: Pitch-Guided Speech Separation 音高引导语音分离

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i11.26542

Xiang Li, Yiwen Wang, Yifan Sun, Xihong Wu, J. Chen

{"title":"PGSS: Pitch-Guided Speech Separation","authors":"Xiang Li, Yiwen Wang, Yifan Sun, Xihong Wu, J. Chen","doi":"10.1609/aaai.v37i11.26542","DOIUrl":"https://doi.org/10.1609/aaai.v37i11.26542","url":null,"abstract":"Monaural speech separation aims to separate concurrent speakers from a single-microphone mixture recording. Inspired by the effect of pitch priming in auditory scene analysis (ASA) mechanisms, a novel pitch-guided speech separation framework is proposed in this work. The prominent advantage of this framework is that both the permutation problem and the unknown speaker number problem existing in general models can be avoided by using pitch contours as the primary means to guide the target speaker. In addition, adversarial training is applied, instead of a traditional time-frequency mask, to improve the perceptual quality of separated speech. Specifically, the proposed framework can be divided into two phases: pitch extraction and speech separation. The former aims to extract pitch contour candidates for each speaker from the mixture, modeling the bottom-up process in ASA mechanisms. Any pitch contour can be selected as the condition in the second phase to separate the corresponding speaker, where a conditional generative adversarial network (CGAN) is applied. The second phase models the effect of pitch priming in ASA. Experiments on the WSJ0-2mix corpus reveal that the proposed approaches can achieve higher pitch extraction accuracy and better separation performance, compared to the baseline models, and have the potential to be applied to SOTA architectures.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"29 1","pages":"13130-13138"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82040326","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}

引用次数: 0

BETA-CD: A Bayesian Meta-Learned Cognitive Diagnosis Framework for Personalized Learning 个性化学习的贝叶斯元学习认知诊断框架

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i4.25629

Haoyang Bi, Enhong Chen, Weidong He, Han Wu, Weihao Zhao, Shijin Wang, Jinze Wu

{"title":"BETA-CD: A Bayesian Meta-Learned Cognitive Diagnosis Framework for Personalized Learning","authors":"Haoyang Bi, Enhong Chen, Weidong He, Han Wu, Weihao Zhao, Shijin Wang, Jinze Wu","doi":"10.1609/aaai.v37i4.25629","DOIUrl":"https://doi.org/10.1609/aaai.v37i4.25629","url":null,"abstract":"Personalized learning is a promising educational approach that aims to provide high-quality personalized services for each student with minimum demands for practice data. The key to achieving that lies in the cognitive diagnosis task, which estimates the cognitive state of the student through his/her logged data of doing practice quizzes. Nevertheless, in the personalized learning scenario, existing cognitive diagnosis models suffer from the inability to (1) quickly adapt to new students using a small amount of data, and (2) measure the reliability of the diagnosis result to avoid improper services that mismatch the student's actual state. In this paper, we propose a general Bayesian mETA-learned Cognitive Diagnosis framework (BETA-CD), which addresses the two challenges by prior knowledge exploitation and model uncertainty quantification, respectively. Specifically, we firstly introduce Bayesian hierarchical modeling to associate each student's cognitive state with a shared prior distribution encoding prior knowledge and a personal posterior distribution indicating model uncertainty. Furthermore, we formulate a meta-learning objective to automatically exploit prior knowledge from historical students, and efficiently solve it with a gradient-based variational inference method. The code will be publicly available at https://github.com/AyiStar/pyat.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"72 1","pages":"5018-5026"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85703765","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}

引用次数: 0

Scene-Level Sketch-Based Image Retrieval with Minimal Pairwise Supervision 最小成对监督的基于场景级草图的图像检索

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i1.25141

Ce Ge, Jingyu Wang, Q. Qi, Haifeng Sun, Tong Xu, Jianxin Liao

{"title":"Scene-Level Sketch-Based Image Retrieval with Minimal Pairwise Supervision","authors":"Ce Ge, Jingyu Wang, Q. Qi, Haifeng Sun, Tong Xu, Jianxin Liao","doi":"10.1609/aaai.v37i1.25141","DOIUrl":"https://doi.org/10.1609/aaai.v37i1.25141","url":null,"abstract":"The sketch-based image retrieval (SBIR) task has long been researched at the instance level, where both query sketches and candidate images are assumed to contain only one dominant object. This strong assumption constrains its application, especially with the increasingly popular intelligent terminals and human-computer interaction technology. In this work, a more general scene-level SBIR task is explored, where sketches and images can both contain multiple object instances. The new general task is extremely challenging due to several factors: (i) scene-level SBIR inherently shares sketch-specific difficulties with instance-level SBIR (e.g., sparsity, abstractness, and diversity), (ii) the cross-modal similarity is measured between two partially aligned domains (i.e., not all objects in images are drawn in scene sketches), and (iii) besides instance-level visual similarity, a more complex multi-dimensional scene-level feature matching problem is imposed (including appearance, semantics, layout, etc.). Addressing these challenges, a novel Conditional Graph Autoencoder model is proposed to deal with scene-level sketch-images retrieval. More importantly, the model can be trained with only pairwise supervision, which distinguishes our study from others in that elaborate instance-level annotations (for example, bounding boxes) are no longer required. Extensive experiments confirm the ability of our model to robustly retrieve multiple related objects at the scene level and exhibit superior performance beyond strong competitors.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"11 1","pages":"650-657"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84148600","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}

引用次数: 0

Electrophysiological Brain Source Imaging via Combinatorial Search with Provable Optimality 基于可证明最优性组合搜索的脑电生理源成像

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i10.26471

Guihong Wan, Meng Jiao, Xinglong Ju, Yu Zhang, H. Schweitzer, Feng Liu

{"title":"Electrophysiological Brain Source Imaging via Combinatorial Search with Provable Optimality","authors":"Guihong Wan, Meng Jiao, Xinglong Ju, Yu Zhang, H. Schweitzer, Feng Liu","doi":"10.1609/aaai.v37i10.26471","DOIUrl":"https://doi.org/10.1609/aaai.v37i10.26471","url":null,"abstract":"Electrophysiological Source Imaging (ESI) refers to reconstructing the underlying brain source activation from non-invasive Electroencephalography (EEG) and Magnetoencephalography (MEG) measurements on the scalp. Estimating the source locations and their extents is a fundamental tool in clinical and neuroscience applications. However, the estimation is challenging because of the ill-posedness and high coherence in the leadfield matrix as well as the noise in the EEG/MEG data. In this work, we proposed a combinatorial search framework to address the ESI problem with a provable optimality guarantee. Specifically, by exploiting the graph neighborhood information in the brain source space, we converted the ESI problem into a graph search problem and designed a combinatorial search algorithm under the framework of A* to solve it. The proposed algorithm is guaranteed to give an optimal solution to the ESI problem. Experimental results on both synthetic data and real epilepsy EEG data demonstrated that the proposed algorithm could faithfully reconstruct the source activation in the brain.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"62 1","pages":"12491-12499"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78339379","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}

引用次数: 0

Generating Transferable 3D Adversarial Point Cloud via Random Perturbation Factorization 随机扰动分解生成可转移的三维对抗点云

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i1.25154

Bangyan He, J. Liu, Yiming Li, Siyuan Liang, Jingzhi Li, Xiaojun Jia, Xiaochun Cao

{"title":"Generating Transferable 3D Adversarial Point Cloud via Random Perturbation Factorization","authors":"Bangyan He, J. Liu, Yiming Li, Siyuan Liang, Jingzhi Li, Xiaojun Jia, Xiaochun Cao","doi":"10.1609/aaai.v37i1.25154","DOIUrl":"https://doi.org/10.1609/aaai.v37i1.25154","url":null,"abstract":"Recent studies have demonstrated that existing deep neural networks (DNNs) on 3D point clouds are vulnerable to adversarial examples, especially under the white-box settings where the adversaries have access to model parameters. However, adversarial 3D point clouds generated by existing white-box methods have limited transferability across different DNN architectures. They have only minor threats in real-world scenarios under the black-box settings where the adversaries can only query the deployed victim model. In this paper, we revisit the transferability of adversarial 3D point clouds. We observe that an adversarial perturbation can be randomly factorized into two sub-perturbations, which are also likely to be adversarial perturbations. It motivates us to consider the effects of the perturbation and its sub-perturbations simultaneously to increase the transferability for sub-perturbations also contain helpful information. In this paper, we propose a simple yet effective attack method to generate more transferable adversarial 3D point clouds. Specifically, rather than simply optimizing the loss of perturbation alone, we combine it with its random factorization. We conduct experiments on benchmark dataset, verifying our method's effectiveness in increasing transferability while preserving high efficiency.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"2 1","pages":"764-772"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78477112","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}

引用次数: 6

Ultrafast Euclidean Shortest Path Computation Using Hub Labeling 基于轮毂标记的超快速欧氏最短路径计算

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i10.26463

Jinchun Du, Bojie Shen, M. A. Cheema

引用次数: 2

Structurally Restricted Fragments of Numeric Planning - a Complexity Analysis 数字规划的结构限制片段-复杂性分析

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i10.26428

Alexander Shleyfman, Daniel Gnad, P. Jonsson

{"title":"Structurally Restricted Fragments of Numeric Planning - a Complexity Analysis","authors":"Alexander Shleyfman, Daniel Gnad, P. Jonsson","doi":"10.1609/aaai.v37i10.26428","DOIUrl":"https://doi.org/10.1609/aaai.v37i10.26428","url":null,"abstract":"Numeric planning is known to be undecidable even under severe restrictions. Prior work has investigated the decidability boundaries by restricting the expressiveness of the planning formalism in terms of the numeric functions allowed in conditions and effects. We study a well-known restricted form of Hoffmann's simple numeric planning, which is undecidable. We analyze the complexity by imposing restrictions on the causal structure, exploiting a novel method for bounding variable domain sizes. First, we show that plan existence for tasks where all numeric variables are root nodes in the causal graph is in PSPACE.\u0000Second, we show that for tasks with only numeric leaf variables the problem is decidable, and that it is in PSPACE if the propositional state space has a fixed size. Our work lays a strong foundation for future investigations of structurally more complex tasks. From a practical perspective, our method allows to employ heuristics and methods that are geared towards finite variable domains (such as pattern database heuristics or decoupled search) to solve non-trivial families of numeric planning problems.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"163 1","pages":"12112-12119"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76634971","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}

引用次数: 0

Self-Supervised Logic Induction for Explainable Fuzzy Temporal Commonsense Reasoning 可解释模糊时间常识推理的自监督逻辑归纳

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i11.26481

Bibo Cai, Xiao Ding, Zhouhao Sun, Bing Qin, Ting Liu, Baojun Wang, Lifeng Shang

{"title":"Self-Supervised Logic Induction for Explainable Fuzzy Temporal Commonsense Reasoning","authors":"Bibo Cai, Xiao Ding, Zhouhao Sun, Bing Qin, Ting Liu, Baojun Wang, Lifeng Shang","doi":"10.1609/aaai.v37i11.26481","DOIUrl":"https://doi.org/10.1609/aaai.v37i11.26481","url":null,"abstract":"Understanding temporal commonsense concepts, such as times of occurrence and durations is crucial for event-centric language understanding. Reasoning about such temporal concepts in a complex context requires reasoning over both the stated context and the world knowledge that underlines it. A recent study shows massive pre-trained LM still struggle with such temporal reasoning under complex contexts (e.g., dialog) because they only implicitly encode the relevant contexts and fail to explicitly uncover the underlying logical compositions for complex inference, thus may not be robust enough. In this work, we propose to augment LMs with the temporal logic induction ability, which frames the temporal reasoning by defining three modular components: temporal dependency inducer and temporal concept defuzzifier and logic validator. The former two components disentangle the explicit/implicit dependency between temporal concepts across context (before, after, ...) and the specific meaning of fuzzy temporal concepts, respectively, while the validator combines the intermediate reasoning clues for robust contextual reasoning about the temporal concepts. Extensive experimental results on TIMEDIAL, a challenging dataset for temporal reasoning over dialog, show that our method, Logic Induction Enhanced Contextualized TEmporal Reasoning (LECTER), can yield great improvements over the traditional language model for temporal reasoning.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"1 1","pages":"12580-12588"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77174303","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}

引用次数: 2

A Fair Incentive Scheme for Community Health Workers 社区卫生工作者公平奖励计划

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i12.26653

Avinandan Bose, Tracey Li, Arunesh Sinha, Tien Mai

{"title":"A Fair Incentive Scheme for Community Health Workers","authors":"Avinandan Bose, Tracey Li, Arunesh Sinha, Tien Mai","doi":"10.1609/aaai.v37i12.26653","DOIUrl":"https://doi.org/10.1609/aaai.v37i12.26653","url":null,"abstract":"Community health workers (CHWs) play a crucial role in\u0000the last mile delivery of essential health services to underserved\u0000populations in low-income countries. Many nongovernmental\u0000organizations (NGOs) provide training and\u0000support to enable CHWs to deliver health services to their\u0000communities, with no charge to the recipients of the services.\u0000This includes monetary compensation for the work that\u0000CHWs perform, which is broken down into a series of well defined\u0000tasks. In this work, we partner with a NGO D-Tree\u0000International to design a fair monetary compensation scheme\u0000for tasks performed by CHWs in the semi-autonomous region\u0000of Zanzibar in Tanzania, Africa. In consultation with\u0000stakeholders, we interpret fairness as the equal opportunity\u0000to earn, which means that each CHW has the opportunity to\u0000earn roughly the same total payment over a given T month\u0000period, if the CHW reacts to the incentive scheme almost rationally.\u0000We model this problem as a reward design problem\u0000for a Markov Decision Process (MDP) formulation for the\u0000CHWs’ earning. There is a need for the mechanism to be\u0000simple so that it is understood by the CHWs, thus, we explore\u0000linear and piecewise linear rewards in the CHWs’ measured\u0000units of work. We solve this design problem via a novel\u0000policy-reward gradient result. Our experiments using two real\u0000world parameters from the ground provide evidence of reasonable\u0000incentive output by our scheme.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"46 1","pages":"14127-14135"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77176073","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}

引用次数: 0

Iteratively Enhanced Semidefinite Relaxations for Efficient Neural Network Verification 高效神经网络验证的迭代增强半定松弛

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i12.26744

Jianglin Lan, Yang Zheng, A. Lomuscio

引用次数: 0