Proceedings of machine learning research最新文献_第5页

Half-Hop: A graph upsampling approach for slowing down message passing 半跳：一种降低消息传递速度的图形上采样方法

Proceedings of machine learning research Pub Date : 2023-07-01 DOI: 10.48550/arXiv.2308.09198

Mehdi Azabou, Venkataraman Ganesh, Shantanu Thakoor, Chi-Heng Lin, Lakshmi Sathidevi, Ran Liu, M. Vaĺko, Petar Velickovic, Eva L. Dyer

{"title":"Half-Hop: A graph upsampling approach for slowing down message passing","authors":"Mehdi Azabou, Venkataraman Ganesh, Shantanu Thakoor, Chi-Heng Lin, Lakshmi Sathidevi, Ran Liu, M. Vaĺko, Petar Velickovic, Eva L. Dyer","doi":"10.48550/arXiv.2308.09198","DOIUrl":"https://doi.org/10.48550/arXiv.2308.09198","url":null,"abstract":"Message passing neural networks have shown a lot of success on graph-structured data. However, there are many instances where message passing can lead to over-smoothing or fail when neighboring nodes belong to different classes. In this work, we introduce a simple yet general framework for improving learning in message passing neural networks. Our approach essentially upsamples edges in the original graph by adding \"slow nodes\" at each edge that can mediate communication between a source and a target node. Our method only modifies the input graph, making it plug-and-play and easy to use with existing models. To understand the benefits of slowing down message passing, we provide theoretical and empirical analyses. We report results on several supervised and self-supervised benchmarks, and show improvements across the board, notably in heterophilic conditions where adjacent nodes are more likely to have different labels. Finally, we show how our approach can be used to generate augmentations for self-supervised learning, where slow nodes are randomly introduced into different edges in the graph to generate multi-scale views with variable path lengths.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"202 1","pages":"1341-1360"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45894268","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

A Conditional Normalizing Flow for Accelerated Multi-Coil MR Imaging. 用于加速多线圈磁共振成像的条件归一化流程

Proceedings of machine learning research Pub Date : 2023-07-01

Jeffrey Wen, Rizwan Ahmad, Philip Schniter

引用次数: 0

Radiology Reports Improve Visual Representations Learned from Radiographs. 放射学报告改进了从射线照片中学到的可视化表达。

Proceedings of machine learning research Pub Date : 2023-07-01

Haoxu Huang, Samyak Rawlekar, Sumit Chopra, Cem M Deniz

{"title":"Radiology Reports Improve Visual Representations Learned from Radiographs.","authors":"Haoxu Huang, Samyak Rawlekar, Sumit Chopra, Cem M Deniz","doi":"","DOIUrl":"","url":null,"abstract":"Although human's ability to visually understand the structure of the World plays a crucial role in perceiving the World and making appropriate decisions, human perception does not solely rely on vision but amalgamates the information from acoustic, verbal, and visual stimuli. An active area of research has been revolving around designing an efficient framework that adapts to multiple modalities and ideally improves the performance of existing tasks. While numerous frameworks have proved effective on natural datasets like ImageNet, a limited number of studies have been carried out in the biomedical domain. In this work, we extend the available frameworks for natural data to biomedical data by leveraging the abundant, unstructured multi-modal data available as radiology images and reports. We attempt to answer the question, \"For multi-modal learning, self-supervised learning and joint learning using both learning strategies, which one improves the visual representation for downstream chest radiographs classification tasks the most?\". Our experiments indicated that in limited labeled data settings with 1% and 10% labeled data, the joint learning with multi-modal and self-supervised models outperforms self-supervised learning and is at par with multi-modal learning. Additionally, we found that multi-modal learning is generally more robust on out-of-distribution datasets. The code is publicly available online.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"227 ","pages":"1385-1405"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11234265/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141581782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes. 具有潜在稀疏高斯过程的完全贝叶斯自动编码器。

Proceedings of machine learning research Pub Date : 2023-07-01

Ba-Hien Tran, Babak Shahbaba, Stephan Mandt, Maurizio Filippone

引用次数: 0

Half-Hop: A graph upsampling approach for slowing down message passing. 半跳：一种用于减慢消息传递速度的图形上采样方法。

Proceedings of machine learning research Pub Date : 2023-07-01

Mehdi Azabou, Venkataramana Ganesh, Shantanu Thakoor, Chi-Heng Lin, Lakshmi Sathidevi, Ran Liu, Michal Valko, Petar Veličković, Eva L Dyer

{"title":"Half-Hop: A graph upsampling approach for slowing down message passing.","authors":"Mehdi Azabou, Venkataramana Ganesh, Shantanu Thakoor, Chi-Heng Lin, Lakshmi Sathidevi, Ran Liu, Michal Valko, Petar Veličković, Eva L Dyer","doi":"","DOIUrl":"","url":null,"abstract":"Message passing neural networks have shown a lot of success on graph-structured data. However, there are many instances where message passing can lead to over-smoothing or fail when neighboring nodes belong to different classes. In this work, we introduce a simple yet general framework for improving learning in message passing neural networks. Our approach essentially upsamples edges in the original graph by adding \"slow nodes\" at each edge that can mediate communication between a source and a target node. Our method only modifies the input graph, making it plug-and-play and easy to use with existing models. To understand the benefits of slowing down message passing, we provide theoretical and empirical analyses. We report results on several supervised and self-supervised benchmarks, and show improvements across the board, notably in heterophilic conditions where adjacent nodes are more likely to have different labels. Finally, we show how our approach can be used to generate augmentations for self-supervised learning, where slow nodes are randomly introduced into different edges in the graph to generate multi-scale views with variable path lengths.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"202 ","pages":"1341-1360"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10559225/pdf/nihms-1931959.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41184447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Controlled Differential Equations on Long Sequences via Non-standard Wavelets. 通过非标准小波控制长序列上的微分方程

Proceedings of machine learning research Pub Date : 2023-07-01

Sourav Pal, Zhanpeng Zeng, Sathya N Ravi, Vikas Singh

{"title":"Controlled Differential Equations on Long Sequences via Non-standard Wavelets.","authors":"Sourav Pal, Zhanpeng Zeng, Sathya N Ravi, Vikas Singh","doi":"","DOIUrl":"","url":null,"abstract":"Neural Controlled Differential equations (NCDE) are a powerful mechanism to model the dynamics in temporal sequences, e.g., applications involving physiological measures, where apart from the initial condition, the dynamics also depend on subsequent measures or even a different \"control\" sequence. But NCDEs do not scale well to longer sequences. Existing strategies adapt rough path theory, and instead model the dynamics over summaries known as log signatures. While rigorous and elegant, invertibility of these summaries is difficult, and limits the scope of problems where these ideas can offer strong benefits (reconstruction, generative modeling). For tasks where it is sensible to assume that the (long) sequences in the training data are a fixed length of temporal measurements - this assumption holds in most experiments tackled in the literature - we describe an efficient simplification. First, we recast the regression/classification task as an integral transform. We then show how restricting the class of operators (permissible in the integral transform), allows the use of a known algorithm that leverages non-standard Wavelets to decompose the operator. Thereby, our task (learning the operator) radically simplifies. A neural variant of this idea yields consistent improvements across a wide gamut of use cases tackled in existing works. We also describe a novel application on modeling tasks involving coupled differential equations.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"202 ","pages":"26820-26836"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11178150/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141332696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning. 折扣正则化的意外后果：改进确定性等价强化学习中的正则化。

Proceedings of machine learning research Pub Date : 2023-07-01

Sarah Rathnam, Sonali Parbhoo, Weiwei Pan, Susan A Murphy, Finale Doshi-Velez

{"title":"The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning.","authors":"Sarah Rathnam, Sonali Parbhoo, Weiwei Pan, Susan A Murphy, Finale Doshi-Velez","doi":"","DOIUrl":"","url":null,"abstract":"Discount regularization, using a shorter planning horizon when calculating the optimal policy, is a popular choice to restrict planning to a less complex set of policies when estimating an MDP from sparse or noisy data (Jiang et al., 2015). It is commonly understood that discount regularization functions by de-emphasizing or ignoring delayed effects. In this paper, we reveal an alternate view of discount regularization that exposes unintended consequences. We demonstrate that planning under a lower discount factor produces an identical optimal policy to planning using any prior on the transition matrix that has the same distribution for all states and actions. In fact, it functions like a prior with stronger regularization on state-action pairs with more transition data. This leads to poor performance when the transition matrix is estimated from data sets with uneven amounts of data across state-action pairs. Our equivalence theorem leads to an explicit formula to set regularization parameters locally for individual state-action pairs rather than globally. We demonstrate the failures of discount regularization and how we remedy them using our state-action-specific method across simple empirical examples as well as a medical cancer simulator.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"202 ","pages":"28746-28767"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10472113/pdf/nihms-1926341.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10151971","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improved Algorithms for White-Box Adversarial Streams. 白箱对抗流的改进算法。

Proceedings of machine learning research Pub Date : 2023-07-01

Ying Feng, David P Woodruff

{"title":"Improved Algorithms for White-Box Adversarial Streams.","authors":"Ying Feng, David P Woodruff","doi":"","DOIUrl":"","url":null,"abstract":"We study streaming algorithms in the white-box adversarial stream model, where the internal state of the streaming algorithm is revealed to an adversary who adaptively generates the stream updates, but the algorithm obtains fresh randomness unknown to the adversary at each time step. We incorporate cryptographic assumptions to construct robust algorithms against such adversaries. We propose efficient algorithms for sparse recovery of vectors, low rank recovery of matrices and tensors, as well as low rank plus sparse recovery of matrices, i.e., robust PCA. Unlike deterministic algorithms, our algorithms can report when the input is not sparse or low rank even in the presence of such an adversary. We use these recovery algorithms to improve upon and solve new problems in numerical linear algebra and combinatorial optimization on white-box adversarial streams. For example, we give the first efficient algorithm for outputting a matching in a graph with insertions and deletions to its edges provided the matching size is small, and otherwise we declare the matching size is large. We also improve the approximation versus memory tradeoff of previous work for estimating the number of non-zero elements in a vector and computing the matrix rank.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"202 ","pages":"9962-9975"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11576266/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142683833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Causal isotonic calibration for heterogeneous treatment effects. 非均匀处理效果的因果等压校准。

Proceedings of machine learning research Pub Date : 2023-07-01

Lars van der Laan, Ernesto Ulloa-Pérez, Marco Carone, Alex Luedtke

引用次数: 0

Unsupervised Stain Decomposition via Inversion Regulation for Multiplex Immunohistochemistry Images. 通过反转调节对多重免疫组化图像进行无监督污点分解

Proceedings of machine learning research Pub Date : 2023-07-01

Shahira Abousamra, Danielle Fassler, Jiachen Yao, Rajarsi Gupta, Tahsin Kurc, Luisa Escobar-Hoyos, Dimitris Samaras, Kenneth Shroyer, Joel Saltz, Chao Chen

{"title":"Unsupervised Stain Decomposition via Inversion Regulation for Multiplex Immunohistochemistry Images.","authors":"Shahira Abousamra, Danielle Fassler, Jiachen Yao, Rajarsi Gupta, Tahsin Kurc, Luisa Escobar-Hoyos, Dimitris Samaras, Kenneth Shroyer, Joel Saltz, Chao Chen","doi":"","DOIUrl":"","url":null,"abstract":"Multiplex Immunohistochemistry (mIHC) is a cost-effective and accessible method for in situ labeling of multiple protein biomarkers in a tissue sample. By assigning a different stain to each biomarker, it allows the visualization of different types of cells within the tumor vicinity for downstream analysis. However, to detect different types of stains in a given mIHC image is a challenging problem, especially when the number of stains is high. Previous deep-learning-based methods mostly assume full supervision; yet the annotation can be costly. In this paper, we propose a novel unsupervised stain decomposition method to detect different stains simultaneously. Our method does not require any supervision, except for color samples of different stains. A main technical challenge is that the problem is underdetermined and can have multiple solutions. To conquer this issue, we propose a novel inversion regulation technique, which eliminates most undesirable solutions. On a 7-plexed IHC images dataset, the proposed method achieves high quality stain decomposition results without human annotation.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"227 ","pages":"74-94"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11138139/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141181231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0