International Joint Conference on Artificial Intelligence最新文献_第10页

SeRO: Self-Supervised Reinforcement Learning for Recovery from Out-of-Distribution Situations SeRO:自监督强化学习从非分布情况中恢复

International Joint Conference on Artificial Intelligence Pub Date : 2023-08-01 DOI: 10.24963/ijcai.2023/432

Chan Kim, JaeKyung Cho, C. Bobda, Seung-Woo Seo, Seong-Woo Kim

{"title":"SeRO: Self-Supervised Reinforcement Learning for Recovery from Out-of-Distribution Situations","authors":"Chan Kim, JaeKyung Cho, C. Bobda, Seung-Woo Seo, Seong-Woo Kim","doi":"10.24963/ijcai.2023/432","DOIUrl":"https://doi.org/10.24963/ijcai.2023/432","url":null,"abstract":"Robotic agents trained using reinforcement learning have the problem of taking unreliable actions in an out-of-distribution (OOD) state. Agents can easily become OOD in real-world environments because it is almost impossible for them to visit and learn the entire state space during training. Unfortunately, unreliable actions do not ensure that agents perform their original tasks successfully. Therefore, agents should be able to recognize whether they are in OOD states and learn how to return to the learned state distribution rather than continue to take unreliable actions. In this study, we propose a novel method for retraining agents to recover from OOD situations in a self-supervised manner when they fall into OOD states. Our in-depth experimental results demonstrate that our method substantially improves the agent’s ability to recover from OOD situations in terms of sample efficiency and restoration of the performance for the original tasks. Moreover, we show that our method can retrain the agent to recover from OOD situations even when in-distribution states are difficult to visit through exploration. Code and supplementary materials are available at https://github.com/SNUChanKim/SeRO.","PeriodicalId":394530,"journal":{"name":"International Joint Conference on Artificial Intelligence","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128078158","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 Optimization with Switching Cost: Regret Analysis and Lookahead Variants 具有切换代价的贝叶斯优化:后悔分析和前瞻变量

International Joint Conference on Artificial Intelligence Pub Date : 2023-08-01 DOI: 10.24963/ijcai.2023/446

Peng Liu, Haowei Wang, Wei Qiyu

{"title":"Bayesian Optimization with Switching Cost: Regret Analysis and Lookahead Variants","authors":"Peng Liu, Haowei Wang, Wei Qiyu","doi":"10.24963/ijcai.2023/446","DOIUrl":"https://doi.org/10.24963/ijcai.2023/446","url":null,"abstract":"Bayesian Optimization (BO) has recently received increasing attention due to its efficiency in optimizing expensive-to-evaluate functions. For some practical problems, it is essential to consider the path-dependent switching cost between consecutive sampling locations given a total traveling budget. For example, when using a drone to locate cracks in a building wall or search for lost survivors in the wild, the search path needs to be efficiently planned given the limited battery power of the drone. Tackling such problems requires a careful cost-benefit analysis of candidate locations and balancing exploration and exploitation. In this work, we formulate such a problem as a constrained Markov Decision Process (MDP) and solve it by proposing a new distance-adjusted multi-step look-ahead acquisition function, the distUCB, and using rollout approximation. We also provide a theoretical regret analysis of the distUCB-based Bayesian optimization algorithm. In addition, the empirical performance of the proposed algorithm is tested based on both synthetic and real data experiments, and it shows that our cost-aware non-myopic algorithm performs better than other popular alternatives.","PeriodicalId":394530,"journal":{"name":"International Joint Conference on Artificial Intelligence","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132525800","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

Front-to-End Bidirectional Heuristic Search with Consistent Heuristics: Enumerating and Evaluating Algorithms and Bounds 具有一致启发式的前端到端双向启发式搜索:枚举和评估算法和边界

International Joint Conference on Artificial Intelligence Pub Date : 2023-08-01 DOI: 10.24963/ijcai.2023/625

Lior Siag, Shahaf S. Shperberg, Ariel Felner, Nathan R Sturtevant

引用次数: 0

Plansformer Tool: Demonstrating Generation of Symbolic Plans Using Transformers 变压器工具:示范生成的符号计划使用变压器

International Joint Conference on Artificial Intelligence Pub Date : 2023-08-01 DOI: 10.24963/ijcai.2023/839

Vishal Pallagani, Bharath Muppasani, Biplav Srivastava, F. Rossi, L. Horesh, K. Murugesan, Andrea Loreggia, F. Fabiano, Rony Joseph, Yathin Kethepalli

{"title":"Plansformer Tool: Demonstrating Generation of Symbolic Plans Using Transformers","authors":"Vishal Pallagani, Bharath Muppasani, Biplav Srivastava, F. Rossi, L. Horesh, K. Murugesan, Andrea Loreggia, F. Fabiano, Rony Joseph, Yathin Kethepalli","doi":"10.24963/ijcai.2023/839","DOIUrl":"https://doi.org/10.24963/ijcai.2023/839","url":null,"abstract":"Plansformer is a novel tool that utilizes a fine-tuned language model based on transformer architecture to generate symbolic plans. Transformers are a type of neural network architecture that have been shown to be highly effective in a range of natural language processing tasks. Unlike traditional planning systems that use heuristic-based search strategies, Plansformer is fine-tuned on specific classical planning domains to generate high-quality plans that are both fluent and feasible. Plansformer takes the domain and problem files as input (in PDDL) and outputs a sequence of actions that can be executed to solve the problem. We demonstrate the effectiveness of Plansformer on a variety of benchmark problems and provide both qualitative and quantitative results obtained during our evaluation, including its limitations. Plansformer has the potential to significantly improve the efficiency and effectiveness of planning in various domains, from logistics and scheduling to natural language processing and human-computer interaction. In addition, we provide public access to Plansformer via a website as well as an API endpoint; this enables other researchers to utilize our tool for planning and execution. The demo video is available at https://youtu.be/_1rlctCGsrk","PeriodicalId":394530,"journal":{"name":"International Joint Conference on Artificial Intelligence","volume":"5 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132287389","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

Annealing Genetic-based Preposition Substitution for Text Rubbish Example Generation 基于退火遗传的介词替换文本垃圾样例生成

International Joint Conference on Artificial Intelligence Pub Date : 2023-08-01 DOI: 10.24963/ijcai.2023/569

Chen Li, Xinghao Yang, Baodi Liu, Weifeng Liu, Honglong Chen

{"title":"Annealing Genetic-based Preposition Substitution for Text Rubbish Example Generation","authors":"Chen Li, Xinghao Yang, Baodi Liu, Weifeng Liu, Honglong Chen","doi":"10.24963/ijcai.2023/569","DOIUrl":"https://doi.org/10.24963/ijcai.2023/569","url":null,"abstract":"Modern Natural Language Processing (NLP) models expose under-sensitivity towards text rubbish examples. The text rubbish example is the heavily modified input text which is nonsensical to humans but does not change the model’s prediction. Prior work crafts rubbish examples by iteratively deleting words and determining the deletion order with beam search. However, the produced rubbish examples usually cause a reduction in model confidence and sometimes deliver human-readable text. To address these problems, we propose an Annealing Genetic based Preposition Substitution (AGPS) algorithm for text rubbish sample generation with two major merits. Firstly, the AGPS crafts rubbish text examples by substituting input words with meaningless prepositions instead of directly removing them, which brings less degradation to the model’s confidence. Secondly, we design an Annealing Genetic algorithm to optimize the word replacement priority, which allows the Genetic Algorithm (GA) to jump out the local optima with probabilities. This is significant in achieving better objectives, i.e., a high word modification rate and a high model confidence. Experimental results on five popular datasets manifest the superiority of AGPS compared with the baseline and expose the fact: the NLP models can not really understand the semantics of sentences, as they give the same prediction with even higher confidence for the nonsensical preposition sequences.","PeriodicalId":394530,"journal":{"name":"International Joint Conference on Artificial Intelligence","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134532812","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

Automatic Recognition of the General-Purpose Communicative Functions Defined by the ISO 24617-2 Standard for Dialog Act Annotation (Extended Abstract) ISO 24617-2对话动作注释标准中通用交际功能的自动识别(扩展摘要)

International Joint Conference on Artificial Intelligence Pub Date : 2023-08-01 DOI: 10.24963/ijcai.2023/788

Eugénio Ribeiro, Ricardo Ribeiro, David Martins de Matos

{"title":"Automatic Recognition of the General-Purpose Communicative Functions Defined by the ISO 24617-2 Standard for Dialog Act Annotation (Extended Abstract)","authors":"Eugénio Ribeiro, Ricardo Ribeiro, David Martins de Matos","doi":"10.24963/ijcai.2023/788","DOIUrl":"https://doi.org/10.24963/ijcai.2023/788","url":null,"abstract":"From the perspective of a dialog system, the identification of the intention behind the segments in a dialog is important, as it provides cues regarding the information present in the segments and how they should be interpreted. The ISO 24617-2 standard for dialog act annotation defines a hierarchically organized set of general-purpose communicative functions that correspond to different intentions that are relevant in the context of a dialog. In this paper, we explore the automatic recognition of these functions. To do so, we propose to adapt existing approaches to dialog act recognition, so that they can deal with the hierarchical classification problem. More specifically, we propose the use of an end-to-end hierarchical network with cascading outputs and maximum a posteriori path estimation to predict the communicative function at each level of the hierarchy, preserve the dependencies between the functions in the path, and decide at which level to stop. Additionally, we rely on transfer learning processes to address the data scarcity problem. Our experiments on the DialogBank show that this approach outperforms both flat and hierarchical approaches based on multiple classifiers and that each of its components plays an important role in the recognition of general-purpose communicative functions.","PeriodicalId":394530,"journal":{"name":"International Joint Conference on Artificial Intelligence","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134072340","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

Fluid Dynamics-Inspired Network for Infrared Small Target Detection 基于流体动力学的红外小目标检测网络

International Joint Conference on Artificial Intelligence Pub Date : 2023-08-01 DOI: 10.24963/ijcai.2023/66

Tianxiang Chen, Q. Chu, B. Liu, Nenghai Yu

{"title":"Fluid Dynamics-Inspired Network for Infrared Small Target Detection","authors":"Tianxiang Chen, Q. Chu, B. Liu, Nenghai Yu","doi":"10.24963/ijcai.2023/66","DOIUrl":"https://doi.org/10.24963/ijcai.2023/66","url":null,"abstract":"Most infrared small target detection (ISTD) networks focus on building effective neural blocks or feature fusion modules but none describes the ISTD process from the image evolution perspective. The directional evolution of image pixels influenced by convolution, pooling and surrounding pixels is analogous to the movement of fluid elements constrained by surrounding variables ang particles. Inspired by this, we explore a novel research routine by abstracting the movement of pixels in the ISTD process as the flow of fluid in fluid dynamics (FD). Specifically, a new Fluid Dynamics-Inspired Network (FDI-Net) is devised for ISTD. Based on Taylor Central Difference (TCD) method, the TCD feature extraction block is designed, where convolution and Transformer structures are combined for local and global information. The pixel motion equation during the ISTD process is derived from the Navier–Stokes (N-S) equation, constructing a N-S Refinement Module that refines extracted features with edge details. Thus, the TCD feature extraction block determines the primary movement direction of pixels during detection, while the N-S Refinement Module corrects some skewed directions of the pixel stream to supplement the edge details. Experiments on IRSTD-1k and SIRST demonstrate that our method achieves SOTA performance in terms of evaluation metrics.","PeriodicalId":394530,"journal":{"name":"International Joint Conference on Artificial Intelligence","volume":"283 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122960653","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

AI Planning for Hybrid Systems 混合系统的人工智能规划

International Joint Conference on Artificial Intelligence Pub Date : 2023-08-01 DOI: 10.24963/ijcai.2023/805

Enrico Scala

引用次数: 0

SSML-QNet: Scale-Separative Metric Learning Quadruplet Network for Multi-modal Image Patch Matching SSML-QNet:用于多模态图像Patch匹配的尺度分离度量学习四重网络

International Joint Conference on Artificial Intelligence Pub Date : 2023-08-01 DOI: 10.24963/ijcai.2023/511

Xiuwei Zhang, Yi Sun, Yamin Han, Yanping Li, Hanlin Yin, Yinghui Xing, Yanning Zhang

{"title":"SSML-QNet: Scale-Separative Metric Learning Quadruplet Network for Multi-modal Image Patch Matching","authors":"Xiuwei Zhang, Yi Sun, Yamin Han, Yanping Li, Hanlin Yin, Yinghui Xing, Yanning Zhang","doi":"10.24963/ijcai.2023/511","DOIUrl":"https://doi.org/10.24963/ijcai.2023/511","url":null,"abstract":"Multi-modal image matching is very challenging due to the significant diversities in visual appearance of different modal images. Typically, the existing well-performed methods mainly focus on learning invariant and discriminative features for measuring the relation between multi-modal image pairs. However, these methods often take the features as a whole and largely overlook the fact that different scale features for a same image pair may have different similarity, which may lead to sub-optimal results only. In this work, we propose a Scale-Separative Metric Learning Quadruplet network (SSML-QNet) for multi-modal image patch matching. Specifically, SSML-QNet can extract both relevant and irrelevant features of imaging modality with the proposed quadruplet network architecture. Then, the proposed Scale-Separative Metric Learning module separately encodes the similarity of different scale features with the pyramid structure. And for each scale, cross-modal consistent features are extracted and measured by coordinate and channel-wise attention sequentially. This makes our network robust to appearance divergence caused by different imaging mechanism. Experiments on the benchmark dataset (VIS-NIR, VIS-LWIR, Optical-SAR, and Brown) have verified that the proposed SSML-QNet is able to outperform other state-of-the-art methods. Furthermore, the cross-dataset transferring experiments on these four datasets also have shown that the proposed method has powerful ability of cross-dataset transferring.","PeriodicalId":394530,"journal":{"name":"International Joint Conference on Artificial Intelligence","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125433364","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

Beyond Homophily: Robust Graph Anomaly Detection via Neural Sparsification 超越同态:基于神经稀疏化的鲁棒图异常检测

International Joint Conference on Artificial Intelligence Pub Date : 2023-08-01 DOI: 10.24963/ijcai.2023/234

Zheng Gong, Guifeng Wang, Ying Sun, Qi Liu, Yuting Ning, H. Xiong, Jingyu Peng

引用次数: 0