Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence最新文献_第9页

Online Tuning for Offline Decentralized Multi-Agent Reinforcement Learning 离线分散多智能体强化学习的在线调优

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i7.25973

Jiechuan Jiang, Zongqing Lu

{"title":"Online Tuning for Offline Decentralized Multi-Agent Reinforcement Learning","authors":"Jiechuan Jiang, Zongqing Lu","doi":"10.1609/aaai.v37i7.25973","DOIUrl":"https://doi.org/10.1609/aaai.v37i7.25973","url":null,"abstract":"Offline reinforcement learning could learn effective policies from a fixed dataset, which is promising for real-world applications. However, in offline decentralized multi-agent reinforcement learning, due to the discrepancy between the behavior policy and learned policy, the transition dynamics in offline experiences do not accord with the transition dynamics in online execution, which creates severe errors in value estimates, leading to uncoordinated low-performing policies. One way to overcome this problem is to bridge offline training and online tuning. However, considering both deployment efficiency and sample efficiency, we could only collect very limited online experiences, making it insufficient to use merely online data for updating the agent policy. To utilize both offline and online experiences to tune the policies of agents, we introduce online transition correction (OTC) to implicitly correct the offline transition dynamics by modifying sampling probabilities. We design two types of distances, i.e., embedding-based and value-based distance, to measure the similarity between transitions, and further propose an adaptive rank-based prioritization to sample transitions according to the transition similarity. OTC is simple yet effective to increase data efficiency and improve agent policies in online tuning. Empirically, OTC outperforms baselines in a variety of tasks.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"44 1","pages":"8050-8059"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88618574","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: 1

Weakly Supervised 3D Segmentation via Receptive-Driven Pseudo Label Consistency and Structural Consistency 基于接受驱动的伪标签一致性和结构一致性的弱监督三维分割

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i1.25205

Yuxiang Lan, Yachao Zhang, Yanyun Qu, Cong Wang, Chengyang Li, Jia Cai, Yuan Xie, Zongze Wu

{"title":"Weakly Supervised 3D Segmentation via Receptive-Driven Pseudo Label Consistency and Structural Consistency","authors":"Yuxiang Lan, Yachao Zhang, Yanyun Qu, Cong Wang, Chengyang Li, Jia Cai, Yuan Xie, Zongze Wu","doi":"10.1609/aaai.v37i1.25205","DOIUrl":"https://doi.org/10.1609/aaai.v37i1.25205","url":null,"abstract":"As manual point-wise label is time and labor-intensive for fully supervised large-scale point cloud semantic segmentation, weakly supervised method is increasingly active. However, existing methods fail to generate high-quality pseudo labels effectively, leading to unsatisfactory results. In this paper, we propose a weakly supervised point cloud semantic segmentation framework via receptive-driven pseudo label consistency and structural consistency to mine potential knowledge. Specifically, we propose three consistency contrains: pseudo label consistency among different scales, semantic structure consistency between intra-class features and class-level relation structure consistency between pair-wise categories. Three consistency constraints are jointly used to effectively prepares and utilizes pseudo labels simultaneously for stable training. Finally, extensive experimental results on three challenging datasets demonstrate that our method significantly outperforms state-of-the-art weakly supervised methods and even achieves comparable performance to the fully supervised methods.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"20 1","pages":"1222-1230"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88774261","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

Learning Noise-Induced Reward Functions for Surpassing Demonstrations in Imitation Learning 模仿学习中超越示范的学习噪声诱导奖励函数

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i7.25962

Liangyu Huo, Zulin Wang, Mai Xu

{"title":"Learning Noise-Induced Reward Functions for Surpassing Demonstrations in Imitation Learning","authors":"Liangyu Huo, Zulin Wang, Mai Xu","doi":"10.1609/aaai.v37i7.25962","DOIUrl":"https://doi.org/10.1609/aaai.v37i7.25962","url":null,"abstract":"Imitation learning (IL) has recently shown impressive performance in training a reinforcement learning agent with human demonstrations, eliminating the difficulty of designing elaborate reward functions in complex environments. However, most IL methods work under the assumption of the optimality of the demonstrations and thus cannot learn policies to surpass the demonstrators. Some methods have been investigated to obtain better-than-demonstration (BD) performance with inner human feedback or preference labels. In this paper, we propose a method to learn rewards from suboptimal demonstrations via a weighted preference learning technique (LERP). Specifically, we first formulate the suboptimality of demonstrations as the inaccurate estimation of rewards. The inaccuracy is modeled with a reward noise random variable following the Gumbel distribution. Moreover, we derive an upper bound of the expected return with different noise coefficients and propose a theorem to surpass the demonstrations. Unlike existing literature, our analysis does not depend on the linear reward constraint. Consequently, we develop a BD model with a weighted preference learning technique. Experimental results on continuous control and high-dimensional discrete control tasks show the superiority of our LERP method over other state-of-the-art BD methods.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"50 1","pages":"7953-7961"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87259615","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

Unsupervised Legal Evidence Retrieval via Contrastive Learning with Approximate Aggregated Positive 基于近似聚合正的对比学习的无监督法律证据检索

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i4.25603

Feng Yao, Jingyuan Zhang, Yating Zhang, Xiaozhong Liu, Changlong Sun, Yun Liu, Weixing Shen

{"title":"Unsupervised Legal Evidence Retrieval via Contrastive Learning with Approximate Aggregated Positive","authors":"Feng Yao, Jingyuan Zhang, Yating Zhang, Xiaozhong Liu, Changlong Sun, Yun Liu, Weixing Shen","doi":"10.1609/aaai.v37i4.25603","DOIUrl":"https://doi.org/10.1609/aaai.v37i4.25603","url":null,"abstract":"Verifying the facts alleged by the prosecutors before the trial requires the judges to retrieve evidence within the massive materials accompanied.\u0000Existing Legal AI applications often assume the facts are already determined and fail to notice the difficulty of reconstructing them. To build a practical Legal AI application and free the judges from the manually searching work, we introduce the task of Legal Evidence Retrieval, which aims at automatically retrieving the precise fact-related verbal evidence within a single case. We formulate the task in a dense retrieval paradigm, and jointly learn the constrastive representations and alignments between facts and evidence. To get rid of the tedious annotations, we construct an approximated positive vector for a given fact by aggregating a set of evidence from the same case. An entropy-based denoise technique is further applied to mitigate the impact of false positive samples. We train our models on tens of thousands of unlabeled cases and evaluate them on a labeled dataset containing 919 cases and 4,336 queries. Experimental results indicate that our approach is effective and outperforms other state-of-the-art representation and retrieval models. The dataset and code are available at https://github.com/yaof20/LER.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"21 1","pages":"4783-4791"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87256005","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: 3

Tensorized Incomplete Multi-View Clustering with Intrinsic Graph Completion 具有内在图补全的张紧化不完全多视图聚类

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i9.26340

Shuping Zhao, Jie Wen, Lunke Fei, Bob Zhang

{"title":"Tensorized Incomplete Multi-View Clustering with Intrinsic Graph Completion","authors":"Shuping Zhao, Jie Wen, Lunke Fei, Bob Zhang","doi":"10.1609/aaai.v37i9.26340","DOIUrl":"https://doi.org/10.1609/aaai.v37i9.26340","url":null,"abstract":"Most of the existing incomplete multi-view clustering (IMVC) methods focus on attaining a consensus representation from different views but ignore the important information hidden in the missing views and the latent intrinsic structures in each view. To tackle these issues, in this paper, a unified and novel framework, named tensorized incomplete multi-view clustering with intrinsic graph completion (TIMVC_IGC) is proposed. Firstly, owing to the effectiveness of the low-rank representation in revealing the inherent structure of the data, we exploit it to infer the missing instances and construct the complete graph for each view. Afterwards, inspired by the structural consistency, a between-view consistency constraint is imposed to guarantee the similarity of the graphs from different views. More importantly, the TIMVC_IGC simultaneously learns the low-rank structures of the different views and explores the correlations of the different graphs in a latent manifold sub-space using a low-rank tensor constraint, such that the intrinsic graphs of the different views can be obtained. Finally, a consensus representation for each sample is gained with a co-regularization term for final clustering. Experimental results on several real-world databases illustrates that the proposed method can outperform the other state-of-the-art related methods for incomplete multi-view clustering.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"24 1","pages":"11327-11335"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87345086","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

Bayesian Cross-Modal Alignment Learning for Few-Shot Out-of-Distribution Generalization 基于贝叶斯跨模态学习的少镜头分布外泛化

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i9.26355

Lin Zhu, Xinbing Wang, Cheng Zhou, Nanyang Ye

{"title":"Bayesian Cross-Modal Alignment Learning for Few-Shot Out-of-Distribution Generalization","authors":"Lin Zhu, Xinbing Wang, Cheng Zhou, Nanyang Ye","doi":"10.1609/aaai.v37i9.26355","DOIUrl":"https://doi.org/10.1609/aaai.v37i9.26355","url":null,"abstract":"Recent advances in large pre-trained models showed promising results in few-shot learning. However, their generalization ability on two-dimensional Out-of-Distribution (OoD) data, i.e., correlation shift and diversity shift, has not been thoroughly investigated. Researches have shown that even with a significant amount of training data, few methods can achieve better performance than the standard empirical risk minimization method (ERM) in OoD generalization. This few-shot OoD generalization dilemma emerges as a challenging direction in deep neural network generalization research, where the performance suffers from overfitting on few-shot examples and OoD generalization errors. In this paper, leveraging a broader supervision source, we explore a novel Bayesian cross-modal image-text alignment learning method (Bayes-CAL) to address this issue. Specifically, the model is designed as only text representations are fine-tuned via a Bayesian modelling approach with gradient orthogonalization loss and invariant risk minimization (IRM) loss. The Bayesian approach is essentially introduced to avoid overfitting the base classes observed during training and improve generalization to broader unseen classes. The dedicated loss is introduced to achieve better image-text alignment by disentangling the causal and non-casual parts of image features. Numerical experiments demonstrate that Bayes-CAL achieved state-of-the-art OoD generalization performances on two-dimensional distribution shifts. Moreover, compared with CLIP-like models, Bayes-CAL yields more stable generalization performances on unseen classes. Our code is available at https://github.com/LinLLLL/BayesCAL.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"26 1","pages":"11461-11469"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80659733","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

WaveForM: Graph Enhanced Wavelet Learning for Long Sequence Forecasting of Multivariate Time Series 多变量时间序列长序列预测的波形图增强小波学习

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i9.26276

Fu-qiang Yang, Xin Li, Min Wang, Hongyu Zang, W. Pang, Mingzhong Wang

{"title":"WaveForM: Graph Enhanced Wavelet Learning for Long Sequence Forecasting of Multivariate Time Series","authors":"Fu-qiang Yang, Xin Li, Min Wang, Hongyu Zang, W. Pang, Mingzhong Wang","doi":"10.1609/aaai.v37i9.26276","DOIUrl":"https://doi.org/10.1609/aaai.v37i9.26276","url":null,"abstract":"Multivariate time series (MTS) analysis and forecasting are crucial in many real-world applications, such as smart traffic management and weather forecasting. However, most existing work either focuses on short sequence forecasting or makes predictions predominantly with time domain features, which is not effective at removing noises with irregular frequencies in MTS. Therefore, we propose WaveForM, an end-to-end graph enhanced Wavelet learning framework for long sequence FORecasting of MTS. WaveForM first utilizes Discrete Wavelet Transform (DWT) to represent MTS in the wavelet domain, which captures both frequency and time domain features with a sound theoretical basis. To enable the effective learning in the wavelet domain, we further propose a graph constructor, which learns a global graph to represent the relationships between MTS variables, and graph-enhanced prediction modules, which utilize dilated convolution and graph convolution to capture the correlations between time series and predict the wavelet coefficients at different levels. Extensive experiments on five real-world forecasting datasets show that our model can achieve considerable performance improvement over different prediction lengths against the most competitive baseline of each dataset.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"9 1","pages":"10754-10761"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85171922","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

Augmenting Affective Dependency Graph via Iterative Incongruity Graph Learning for Sarcasm Detection 基于迭代不一致图学习的情感依赖图增强反讽检测

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i4.25594

Xiaobao Wang, Yiqi Dong, Di Jin, Yawen Li, Longbiao Wang, J. Dang

{"title":"Augmenting Affective Dependency Graph via Iterative Incongruity Graph Learning for Sarcasm Detection","authors":"Xiaobao Wang, Yiqi Dong, Di Jin, Yawen Li, Longbiao Wang, J. Dang","doi":"10.1609/aaai.v37i4.25594","DOIUrl":"https://doi.org/10.1609/aaai.v37i4.25594","url":null,"abstract":"Recently, progress has been made towards improving automatic sarcasm detection in computer science. Among existing models, manually constructing static graphs for texts and then using graph neural networks (GNNs) is one of the most effective approaches for drawing long-range incongruity patterns. However, the manually constructed graph structure might be prone to errors (e.g., noisy or incomplete) and not optimal for the sarcasm detection task. Errors produced during the graph construction step cannot be remedied and may accrue to the following stages, resulting in poor performance. To surmount the above limitations, we explore a novel Iterative Augmenting Affective Graph and Dependency Graph (IAAD) framework to jointly and iteratively learn the incongruity graph structure. IAAD can alternatively update the incongruity graph structure and node representation until the learning graph structure is optimal for the metrics of sarcasm detection. More concretely, we begin with deriving an affective and a dependency graph for each instance, then an iterative incongruity graph learning module is employed to augment affective and dependency graphs for obtaining the optimal inconsistent semantic graph with the goal of optimizing the graph for the sarcasm detection task. Extensive experiments on three datasets demonstrate that the proposed model outperforms state-of-the-art baselines for sarcasm detection with significant margins.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"31 1","pages":"4702-4710"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86997075","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

NL2LTL - a Python Package for Converting Natural Language (NL) Instructions to Linear Temporal Logic (LTL) Formulas NL2LTL -一个Python包，用于将自然语言(NL)指令转换为线性时间逻辑(LTL)公式

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i13.27068

Francesco Fuggitti, T. Chakraborti

引用次数: 5

Script, Language, and Labels: Overcoming Three Discrepancies for Low-Resource Language Specialization 文字、语言和标签:克服低资源语言专门化的三个差异

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i11.26528

Jaeseong Lee, Dohyeon Lee, Seung-won Hwang

{"title":"Script, Language, and Labels: Overcoming Three Discrepancies for Low-Resource Language Specialization","authors":"Jaeseong Lee, Dohyeon Lee, Seung-won Hwang","doi":"10.1609/aaai.v37i11.26528","DOIUrl":"https://doi.org/10.1609/aaai.v37i11.26528","url":null,"abstract":"Although multilingual pretrained models (mPLMs) enabled support of various natural language processing in diverse languages, its limited coverage of 100+ languages lets 6500+ languages remain ‘unseen’. One common approach for an unseen language is specializing the model for it as target, by performing additional masked language modeling (MLM) with the target language corpus. However, we argue that, due to the discrepancy from multilingual MLM pretraining, a naive specialization as such can be suboptimal. Specifically, we pose three discrepancies to overcome. Script and linguistic discrepancy of the target language from the related seen languages, hinder a positive transfer, for which we propose to maximize representation similarity, unlike existing approaches maximizing overlaps. In addition, label space for MLM prediction can vary across languages, for which we propose to reinitialize top layers for a more effective adaptation. Experiments over four different language families and three tasks shows that our method improves the task performance of unseen languages with statistical significance, while previous approach fails to.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"33 1","pages":"13004-13013"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91254954","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