FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification

Importance sampling is a technique utilized to enhance the efficiency of deep neural network (DNN) training by minimizing the variance of gradient estimators. This paper introduces a method for estimating variance reduction during DNN training using only minibatches sampled through importance sampling. Additionally, it suggests an optimal minibatch size for automatic learning rate adjustment and presents a metric to quantify the efficiency of importance sampling, supported by theoretical analysis and experiments demonstrating improved training efficiency and model accuracy.

The paper presents a self-training framework for detecting offensive content on social media, addressing the challenge of limited labeled data. It utilizes Multi-Agent Vision-Language Models (MA-VLMs) to collaboratively assign pseudo-labels to unlabeled data. The framework distinguishes between Agreed-Unknown and Disagreed-Unknown sets based on classifier and MA-VLM agreement. By simulating dual perspectives, it enhances label reliability and employs a Positive-Negative-Unlabeled (PNU) loss for optimization, aiming to improve detection accuracy in low-resource settings.

The paper discusses the challenges of test-time prompt tuning for vision-language models, highlighting the issue of prompt optimization bias that can lead to suboptimal performance in downstream tasks. It identifies two main causes: the model's focus on entropy minimization, which may overlook prediction accuracy, and data misalignment between visual and textual modalities. To address these issues, the authors propose a new method called Doubly Debiased Test-Time Prompt Tuning, aimed at improving model performance in zero-shot settings.

The paper titled 'Laplace Learning in Wasserstein Space' explores the manifold hypothesis, which suggests that high-dimensional data typically exists within low-dimensional subspaces. The authors investigate graph-based semi-supervised learning methods, particularly focusing on Laplace Learning in the Wasserstein space. This research extends classical graph-based learning algorithms from finite-dimensional Euclidean spaces to infinite-dimensional contexts. The study proves the variational convergence of discrete graph p-Dirichlet energy to its continuum counterpart and characterizes the Laplac…

The article presents a novel approach to volumetric medical image segmentation called Coordinative Ordinal-Relational Anatomical Learning (CORAL). This method addresses challenges in segmenting medical images by utilizing continuous anatomical similarity instead of relying on hard binary thresholds. CORAL aims to improve the accuracy of segmentation by capturing both local and global anatomical structures, thereby enhancing the understanding of anatomical progression across different patients.

Label smoothing is a regularization technique in machine learning that has not been extensively applied to node classification in graph-structured data. This study introduces posterior label smoothing, a method that generates soft labels based on neighborhood labels. The approach adapts to various graph properties and has been tested on 10 benchmark datasets, showing consistent improvements in classification accuracy and reduced overfitting during training.