Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning最新文献

Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models 差异隐私、语言公平和训练数据影响:多语言模型的不可能性和可能性定理

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-08-17 DOI: 10.48550/arXiv.2308.08774

Phillip Rust, Anders Søgaard

引用次数: 0

Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition Ske2Grid:用于动作识别的骨架到网格表示学习

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-08-15 DOI: 10.48550/arXiv.2308.07571

Dongqi Cai, Yangyuxuan Kang, Anbang Yao, Yurong Chen

{"title":"Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition","authors":"Dongqi Cai, Yangyuxuan Kang, Anbang Yao, Yurong Chen","doi":"10.48550/arXiv.2308.07571","DOIUrl":"https://doi.org/10.48550/arXiv.2308.07571","url":null,"abstract":"This paper presents Ske2Grid, a new representation learning framework for improved skeleton-based action recognition. In Ske2Grid, we define a regular convolution operation upon a novel grid representation of human skeleton, which is a compact image-like grid patch constructed and learned through three novel designs. Specifically, we propose a graph-node index transform (GIT) to construct a regular grid patch through assigning the nodes in the skeleton graph one by one to the desired grid cells. To ensure that GIT is a bijection and enrich the expressiveness of the grid representation, an up-sampling transform (UPT) is learned to interpolate the skeleton graph nodes for filling the grid patch to the full. To resolve the problem when the one-step UPT is aggressive and further exploit the representation capability of the grid patch with increasing spatial size, a progressive learning strategy (PLS) is proposed which decouples the UPT into multiple steps and aligns them to multiple paired GITs through a compact cascaded design learned progressively. We construct networks upon prevailing graph convolution networks and conduct experiments on six mainstream skeleton-based action recognition datasets. Experiments show that our Ske2Grid significantly outperforms existing GCN-based solutions under different benchmark settings, without bells and whistles. Code and models are available at https://github.com/OSVAI/Ske2Grid","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"29 1","pages":"3431-3441"},"PeriodicalIF":0.0,"publicationDate":"2023-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76293058","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

Probabilistic Imputation for Time-series Classification with Missing Data 缺失数据下时间序列分类的概率估计

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-08-13 DOI: 10.48550/arXiv.2308.06738

Seunghyun Kim, Hyunsung Kim, Eunggu Yun, Hwa-Kyung Lee, Jaehun Lee, Juho Lee

{"title":"Probabilistic Imputation for Time-series Classification with Missing Data","authors":"Seunghyun Kim, Hyunsung Kim, Eunggu Yun, Hwa-Kyung Lee, Jaehun Lee, Juho Lee","doi":"10.48550/arXiv.2308.06738","DOIUrl":"https://doi.org/10.48550/arXiv.2308.06738","url":null,"abstract":"Multivariate time series data for real-world applications typically contain a significant amount of missing values. The dominant approach for classification with such missing values is to impute them heuristically with specific values (zero, mean, values of adjacent time-steps) or learnable parameters. However, these simple strategies do not take the data generative process into account, and more importantly, do not effectively capture the uncertainty in prediction due to the multiple possibilities for the missing values. In this paper, we propose a novel probabilistic framework for classification with multivariate time series data with missing values. Our model consists of two parts; a deep generative model for missing value imputation and a classifier. Extending the existing deep generative models to better capture structures of time-series data, our deep generative model part is trained to impute the missing values in multiple plausible ways, effectively modeling the uncertainty of the imputation. The classifier part takes the time series data along with the imputed missing values and classifies signals, and is trained to capture the predictive uncertainty due to the multiple possibilities of imputations. Importantly, we show that na\"ively combining the generative model and the classifier could result in trivial solutions where the generative model does not produce meaningful imputations. To resolve this, we present a novel regularization technique that can promote the model to produce useful imputation values that help classification. Through extensive experiments on real-world time series data with missing values, we demonstrate the effectiveness of our method.","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"26 1","pages":"16654-16667"},"PeriodicalIF":0.0,"publicationDate":"2023-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87908499","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

Decoding Layer Saliency in Language Transformers 语言转换器译码层显著性研究

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-08-09 DOI: 10.48550/arXiv.2308.05219

Elizabeth M. Hou, Greg Castañón

引用次数: 0

Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detection 你还记得吗?克服灾难性遗忘的假音频检测

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-08-07 DOI: 10.48550/arXiv.2308.03300

Xiaohui Zhang, Jiangyan Yi, J. Tao, Chenglong Wang, Chuyuan Zhang

{"title":"Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detection","authors":"Xiaohui Zhang, Jiangyan Yi, J. Tao, Chenglong Wang, Chuyuan Zhang","doi":"10.48550/arXiv.2308.03300","DOIUrl":"https://doi.org/10.48550/arXiv.2308.03300","url":null,"abstract":"Current fake audio detection algorithms have achieved promising performances on most datasets. However, their performance may be significantly degraded when dealing with audio of a different dataset. The orthogonal weight modification to overcome catastrophic forgetting does not consider the similarity of genuine audio across different datasets. To overcome this limitation, we propose a continual learning algorithm for fake audio detection to overcome catastrophic forgetting, called Regularized Adaptive Weight Modification (RAWM). When fine-tuning a detection network, our approach adaptively computes the direction of weight modification according to the ratio of genuine utterances and fake utterances. The adaptive modification direction ensures the network can effectively detect fake audio on the new dataset while preserving its knowledge of old model, thus mitigating catastrophic forgetting. In addition, genuine audio collected from quite different acoustic conditions may skew their feature distribution, so we introduce a regularization constraint to force the network to remember the old distribution in this regard. Our method can easily be generalized to related fields, like speech emotion recognition. We also evaluate our approach across multiple datasets and obtain a significant performance improvement on cross-dataset experiments.","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"4 1","pages":"41819-41831"},"PeriodicalIF":0.0,"publicationDate":"2023-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87383174","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

SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image Translation 非配对图像到图像转换流形上的分数分解扩散模型

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-08-04 DOI: 10.48550/arXiv.2308.02154

Shikun Sun, Longhui Wei, Junliang Xing, Jia Jia, Qi Tian

{"title":"SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image Translation","authors":"Shikun Sun, Longhui Wei, Junliang Xing, Jia Jia, Qi Tian","doi":"10.48550/arXiv.2308.02154","DOIUrl":"https://doi.org/10.48550/arXiv.2308.02154","url":null,"abstract":"Recent score-based diffusion models (SBDMs) show promising results in unpaired image-to-image translation (I2I). However, existing methods, either energy-based or statistically-based, provide no explicit form of the interfered intermediate generative distributions. This work presents a new score-decomposed diffusion model (SDDM) on manifolds to explicitly optimize the tangled distributions during image generation. SDDM derives manifolds to make the distributions of adjacent time steps separable and decompose the score function or energy guidance into an image ``denoising\"part and a content ``refinement\"part. To refine the image in the same noise level, we equalize the refinement parts of the score function and energy guidance, which permits multi-objective optimization on the manifold. We also leverage the block adaptive instance normalization module to construct manifolds with lower dimensions but still concentrated with the perturbed reference image. SDDM outperforms existing SBDM-based methods with much fewer diffusion steps on several I2I benchmarks.","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"108 1","pages":"33115-33134"},"PeriodicalIF":0.0,"publicationDate":"2023-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75911367","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

Variance Control for Distributional Reinforcement Learning 分布式强化学习的方差控制

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-07-30 DOI: 10.48550/arXiv.2307.16152

Qi Kuang, Zhoufan Zhu, Liwen Zhang, Fan Zhou

引用次数: 0

Learning to Design Analog Circuits to Meet Threshold Specifications 学习设计模拟电路以满足阈值规格

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-07-25 DOI: 10.48550/arXiv.2307.13861

Dmitrii Krylov, Pooya Khajeh, Junhan Ouyang, Thomas Reeves, Tongkai Liu, Hiba Ajmal, Hamidreza Aghasi, Roy Fox

{"title":"Learning to Design Analog Circuits to Meet Threshold Specifications","authors":"Dmitrii Krylov, Pooya Khajeh, Junhan Ouyang, Thomas Reeves, Tongkai Liu, Hiba Ajmal, Hamidreza Aghasi, Roy Fox","doi":"10.48550/arXiv.2307.13861","DOIUrl":"https://doi.org/10.48550/arXiv.2307.13861","url":null,"abstract":"Automated design of analog and radio-frequency circuits using supervised or reinforcement learning from simulation data has recently been studied as an alternative to manual expert design. It is straightforward for a design agent to learn an inverse function from desired performance metrics to circuit parameters. However, it is more common for a user to have threshold performance criteria rather than an exact target vector of feasible performance measures. In this work, we propose a method for generating from simulation data a dataset on which a system can be trained via supervised learning to design circuits to meet threshold specifications. We moreover perform the to-date most extensive evaluation of automated analog circuit design, including experimenting in a significantly more diverse set of circuits than in prior work, covering linear, nonlinear, and autonomous circuit configurations, and show that our method consistently reaches success rate better than 90% at 5% error margin, while also improving data efficiency by upward of an order of magnitude. A demo of this system is available at circuits.streamlit.app","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"87 2 1","pages":"17858-17873"},"PeriodicalIF":0.0,"publicationDate":"2023-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85665650","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

The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation 错定非策略值函数估计中的最优逼近因子

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-07-25 DOI: 10.48550/arXiv.2307.13332

P. Amortila, Nan Jiang, Csaba Szepesvari

引用次数: 0

Predicting Ordinary Differential Equations with Transformers 用变压器预测常微分方程

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-07-24 DOI: 10.48550/arXiv.2307.12617

Soren Becker, M. Klein, Alexander Neitz, Giambattista Parascandolo, Niki Kilbertus

引用次数: 3