Transactions on machine learning research最新文献

{"title":"Knockout: A simple way to handle missing inputs.","authors":"Minh Nguyen, Batuhan K Karaman, Heejong Kim, Alan Q Wang, Fengbei Liu, Mert R Sabuncu","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Deep learning models benefit from rich (e.g., multi-modal) input features. However, multimodal models might be challenging to deploy, because some inputs may be missing at inference. Current popular solutions include marginalization, imputation, and training multiple models. Marginalization achieves calibrated predictions, but it is computationally expensive and only feasible for low dimensional inputs. Imputation may result in inaccurate predictions, particularly when high-dimensional data, such as images, are missing. Training multiple models, where each model is designed to handle different subsets of inputs, can work well but requires prior knowledge of missing input patterns. Furthermore, training and retaining multiple models can be costly. We propose an efficient method to learn both the conditional distribution using full inputs and the marginal distributions. Our method, Knockout, randomly replaces input features with appropriate placeholder values during training. We provide a theoretical justification for Knockout and show that it can be interpreted as an implicit marginalization strategy. We evaluate Knockout across a wide range of simulations and real-world datasets and show that it offers strong empirical performance.</p>","PeriodicalId":75238,"journal":{"name":"Transactions on machine learning research","volume":"2025 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12809338/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145999975","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}

{"title":"A Baseline Method for Removing Invisible Image Watermarks using Deep Image Prior.","authors":"Hengyue Liang, Taihui Li, Ju Sun","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Image watermarks have been considered a promising technique to help detect AI-generated content, which can be used to protect copyright or prevent fake image abuse. In this work, we present a black-box method for removing <i>invisible</i> image watermarks, without the need of any dataset of watermarked images or any knowledge about the watermark system. Our approach is simple to implement: given a <i>single</i> watermarked image, we regress it by deep image prior (DIP). We show that from the intermediate steps of DIP one can reliably find an evasion image that can remove invisible watermarks while preserving high image quality. Due to its unique working mechanism and practical effectiveness, we advocate including DIP as a baseline invasion method for benchmarking the robustness of watermarking systems. Finally, by showing the limited ability of DIP and other existing black-box methods in evading training-based <i>visible</i> watermarks, we discuss the positive implications on the practical use of training-based <i>visible</i> watermarks to prevent misinformation abuse. Our code is publicly available at https://github.com/HengyueL/DIP_Watermark_Evasion.</p>","PeriodicalId":75238,"journal":{"name":"Transactions on machine learning research","volume":"2025 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12975117/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147438247","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}

{"title":"Bayesian Neighborhood Adaptation for Graph Neural Networks.","authors":"Paribesh Regmi, Rui Li, Kishan Kc","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>The neighborhood scope (i.e., number of hops) where graph neural networks (GNNs) aggregate information to characterize a node's statistical property is critical to GNNs' performance. Two-stage approaches, training and validating GNNs for every pre-specified neighborhood scope to search for the best setting, is a time-consuming task and tends to be biased due to the search space design. How to adaptively determine proper neighborhood scopes for the aggregation process for both homophilic and heterophilic graphs remains largely unexplored. We thus propose to model the GNNs' message-passing behavior on a graph as a stochastic process by treating the number of hops as a beta process. This Bayesian framework allows us to infer the most plausible neighborhood scope for message aggregation simultaneously with the optimization of GNN parameters. Our theoretical analysis shows that the scope inference improves the expressivity of a GNN. Experiments on benchmark homophilic and heterophilic datasets show that the proposed method is compatible with state-of-the-art GNN variants, achieving competitive or superior performance on the node classification task, and providing well-calibrated predictions.</p>","PeriodicalId":75238,"journal":{"name":"Transactions on machine learning research","volume":"2025 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13038280/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147596764","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}

{"title":"TapWeight: Reweighting Pretraining Objectives for Task-Adaptive Pretraining.","authors":"Ruiyi Zhang, Sai Ashish Somayajula, Pengtao Xie","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Large-scale general domain pretraining followed by downstream-specific finetuning has become a predominant paradigm in machine learning. However, discrepancies between the pretraining and target domains can still lead to performance degradation in certain cases, underscoring the need for task-adaptive continued pretraining (TAP). TAP methods typically involve continued pretraining on task-specific unlabeled datasets or introducing additional unsupervised learning objectives to enhance model capabilities. While many TAP methods perform continued pretraining with multiple pretraining objectives, they often determine the tradeoff parameters between objectives manually, resulting in suboptimal outcomes and higher computational costs. In this paper, we propose TapWeight, a task-adaptive pretraining framework which automatically determines the optimal importance of each pretraining objective based on downstream feedback. TapWeight reweights each pretraining objective by solving a multi-level optimization problem. We applied TapWeight to both molecular property prediction and natural language processing tasks, significantly surpassing baseline methods. Experimental results validate the effectiveness and generalizability of TapWeight. Our code is available at https://github.com/ruz048/TapWeight.</p>","PeriodicalId":75238,"journal":{"name":"Transactions on machine learning research","volume":"2025 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12377235/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144982041","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}

{"title":"AttentionSmithy: A Modular Framework for Rapid Transformer Development.","authors":"Caleb Cranney, Jesse G Meyer","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Transformer architectures have revolutionized a broad spectrum of AI applications by leveraging attention mechanisms for parallelized and long-range sequence processing. Despite their remarkable success, building and customizing transformers remains prohibitively complex for many domain experts who lack deep knowledge of low-level implementations. We introduce AttentionSmithy, a modular software package that lowers the barrier to transformer innovation by decomposing key components-attention modules, feed-forward networks, normalization layers, and positional encodings-into reusable building blocks. By disentangling architectural elements into well-defined interfaces, users can rapidly prototype, adapt, and evaluate transformer variants without extensive coding overhead. Our framework currently supports four distinct positional encoding strategies (sinusoidal, learned, rotary, and ALiBi), offers modular integration of multiple attention methods (including standard attention, Longformer, and Linformer), and integrates seamlessly with neural architecture search (NAS) for automated design exploration. The system is designed to support future extensions with minimal overhead. We validate AttentionSmithy by replicating the original \"Attention Is All You Need\" transformer under resource constraints, demonstrating robust performance on a machine translation task. Leveraging the package's integrated NAS capability, we identified an optimized model configuration that outperformed our baseline, demonstrating the framework's effectiveness for automated architecture search and model improvement. We further illustrate AttentionSmithy's adaptability through gene-specific modeling, where a variant of a BERT-style architecture achieves over 95% accuracy on downstream cell type classification tasks using ranked transcriptomic data. These case studies underscore AttentionSmithy's core advantage: enabling specialized experimentation across diverse application domains-from natural language processing to genomic analysis-by obviating the need for labor-intensive, low-level framework manipulation. We anticipate that AttentionSmithy will serve as a foundation for creative transformer-based solutions, expediting research and development in numerous scientific and industrial fields.</p>","PeriodicalId":75238,"journal":{"name":"Transactions on machine learning research","volume":"2025 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12987691/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147470551","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}

{"title":"Conformal Bounds on Full-Reference Image Quality for Imaging Inverse Problems.","authors":"Jeffrey Wen, Rizwan Ahmad, Philip Schniter","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>In imaging inverse problems, we would like to know how close the recovered image is to the true image in terms of full-reference image quality (FRIQ) metrics like PSNR, SSIM, LPIPS, etc. This is especially important in safety-critical applications like medical imaging, where knowing that, say, the SSIM was poor could potentially avoid a costly misdiagnosis. But since we don't know the true image, computing FRIQ is non-trivial. In this work, we combine conformal prediction with approximate posterior sampling to construct bounds on FRIQ that are guaranteed to hold up to a user-specified error probability. We demonstrate our approach on image denoising and accelerated magnetic resonance imaging (MRI) problems. Code is available at https://github.com/jwen307/quality_uq.</p>","PeriodicalId":75238,"journal":{"name":"Transactions on machine learning research","volume":"2025 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12956293/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147357946","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}

{"title":"Downstream Task Guided Masking Learning in Masked Autoencoders Using Multi-Level Optimization.","authors":"Han Guo, Ramtin Hosseini, Ruiyi Zhang, Sai Ashish Somayajula, Ranak Roy Chowdhury, Rajesh K Gupta, Pengtao Xie","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Masked Autoencoder (MAE) is a notable method for self-supervised pretraining in visual representation learning. It operates by randomly masking image patches and reconstructing these masked patches using the unmasked ones. A key limitation of MAE lies in its disregard for the varying informativeness of different patches, as it uniformly selects patches to mask. To overcome this, some approaches propose masking based on patch informativeness. However, these methods often do not consider the specific requirements of downstream tasks, potentially leading to suboptimal representations for these tasks. In response, we introduce the Multi-level Optimized Mask Autoencoder (MLO-MAE), a novel framework that leverages end-to-end feedback from downstream tasks to learn an optimal masking strategy during pretraining. Our experimental findings highlight MLO-MAE's significant advancements in visual representation learning. Compared to existing methods, it demonstrates remarkable improvements across diverse datasets and tasks, showcasing its adaptability and efficiency. Our code is available at https://github.com/Alexiland/MLO-MAE.</p>","PeriodicalId":75238,"journal":{"name":"Transactions on machine learning research","volume":"2025 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12356090/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144877138","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}

{"title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics.","authors":"Yichi Zhang, Zhihao Duan, Yuning Huang, Fengqing Zhu","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>As learned image compression (LIC) methods become increasingly computationally demanding, enhancing their training efficiency is crucial. This paper takes a step forward in accelerating the training of LIC methods by modeling the neural training dynamics. We first propose a Sensitivity-aware True and Dummy Embedding Training mechanism (STDET) that clusters LIC model parameters into few separate modes where parameters are expressed as affine transformations of reference parameters within the same mode. By further utilizing the stable intra-mode correlations throughout training and parameter sensitivities, we gradually embed non-reference parameters, reducing the number of trainable parameters. Additionally, we incorporate a Sampling-then-Moving Average (SMA) technique, interpolating sampled weights from stochastic gradient descent (SGD) training to obtain the moving average weights, ensuring smooth temporal behavior and minimizing training state variances. Overall, our method significantly reduces training space dimensions and the number of trainable parameters without sacrificing model performance, thus accelerating model convergence. We also provide a theoretical analysis on the Noisy quadratic model, showing that the proposed method achieves a lower training variance than standard SGD. Our approach offers valuable insights for further developing efficient training methods for LICs.</p>","PeriodicalId":75238,"journal":{"name":"Transactions on machine learning research","volume":"2025 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12129407/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144210455","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}

{"title":"A Theoretical Study of Neural Network Expressive Power via Manifold Topology.","authors":"Jiachen Yao, Lingjie Yi, Mayank Goswami, Chao Chen","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>A prevalent assumption regarding real-world data is that it lies on or close to a low-dimensional manifold. When deploying a neural network on data manifolds, the required size, i.e., the number of neurons of the network, heavily depends on the intricacy of the underlying latent manifold. While significant advancements have been made in understanding the geometric attributes of manifolds, it's essential to recognize that topology, too, is a fundamental characteristic of manifolds. In this study, we investigate network expressive power in terms of the latent data manifold. Integrating both topological and geometric facets of the data manifold, we present a size upper bound of ReLU neural networks.</p>","PeriodicalId":75238,"journal":{"name":"Transactions on machine learning research","volume":"2025 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12974905/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147438312","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}

{"title":"Lower Ricci Curvature for Efficient Community Detection.","authors":"Yun Jin Park, Didong Li","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>This study introduces the Lower Ricci Curvature (LRC), a novel, scalable, and scale-free discrete curvature designed to enhance community detection in networks. Addressing the computational challenges posed by existing curvature-based methods, LRC offers a streamlined approach with linear computational complexity, which makes it well suited for large-scale network analysis. We further develop an LRC-based preprocessing method that effectively augments popular community detection algorithms. Through applications on multiple real-world datasets, including the NCAA football league network, the DBLP collaboration network, the Amazon product co-purchasing network, and the YouTube social network, we demonstrate the efficacy of our method in significantly improving the performance of various community detection algorithms.</p>","PeriodicalId":75238,"journal":{"name":"Transactions on machine learning research","volume":"2025 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13021251/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147576784","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}