arXiv research

Soft labeling impacts OOD detection in neural networks.

Improves deep neural networks using soft labels through alternating minimization.

MSLG generates soft labels to improve DNN performance on noisy datasets.

Rectified decision trees improve machine learning interpretability and effectiveness.

A framework learns dynamic soft labels to improve model generalization and accuracy.

Paper estimates optimal classification error with soft labels and calibration.

In Domain Adaptation (DA), the category-relevant losses usually occupy a dominant position, while they are usually built with hard or soft labels in existing models. We observed that hard labels are overconfident due to hard samples existed, and soft labels are ambiguous as too many small noisy probabilities involved, …

Method generates prototypes from small datasets for efficient learning.

Paper estimates FPR of Bayes classifier using soft labels.

The goal of semi-supervised learning is to improve supervised classifiers by using additional unlabeled training examples. In this work we study a simple self-learning approach to semi-supervised learning applied to the least squares classifier. We show that a soft-label and a hard-label variant of self-learning can be…

Less-than-one-shot learning tackles few-shot learning with minimal data.

Proposes a robust VIB approach using soft labels and mutual info estimation.

New PL method improves ASR accuracy without pseudo-labels.

The graph-based semi-supervised label propagation algorithm has delivered impressive classification results. However, the estimated soft labels typically contain mixed signs and noise, which cause inaccurate predictions due to the lack of suitable constraints. Moreover, available methods typically calculate the weights…

Proposes a new method for deep ensembles that improves accuracy and calibration.

Compressed Federated Distillation reduces communication in federated learning.

Study improves fair opinion aggregation by balancing voter attributes.

Improved KNN data valuation method with reduced computation time.

SBA improves neural network generalization by dynamically augmenting data.

Dataset distillation is a method for reducing dataset sizes by learning a small number of synthetic samples containing all the information of a large dataset. This has several benefits like speeding up model training, reducing energy consumption, and reducing required storage space. Currently, each synthetic sample is …

Inspired by recent interests of developing machine learning and data mining algorithms on hypergraphs, we investigate in this paper the semi-supervised learning algorithm of propagating "soft labels" (e.g. probability distributions, class membership scores) over hypergraphs, by means of optimal transportation. Borrowin…

Electron Cryo-Tomography (ECT) enables 3D visualization of macromolecule structure inside single cells. Macromolecule classification approaches based on convolutional neural networks (CNN) were developed to separate millions of macromolecules captured from ECT systematically. However, given the fast accumulation of ECT…

EXoN creates an explainable latent space for semi-supervised learning.

Learning using privileged information is an attractive problem setting that helps many learning scenarios in the real world. A state-of-the-art method of Gaussian process classification (GPC) with privileged information is GPC+, which incorporates privileged information into a noise term of the likelihood. A drawback o…

Heterogeneous domain adaptation (HDA) aims to facilitate the learning task in a target domain by borrowing knowledge from a heterogeneous source domain. In this paper, we propose a Soft Transfer Network (STN), which jointly learns a domain-shared classifier and a domain-invariant subspace in an end-to-end manner, for a…

How to obtain a model with good interpretability and performance has always been an important research topic. In this paper, we propose rectified decision trees (ReDT), a knowledge distillation based decision trees rectification with high interpretability, small model size, and empirical soundness. Specifically, we ext…

Improved self-distillation reduces label noise and enhances model accuracy.

SPEQ improves quantized neural networks by stochastic precision sharing and cosine similarity loss.

SelectMix improves deep learning robustness against noisy labels.

The paper analyzes knowledge distillation in wide neural networks, providing theoretical insights and practical implications.

This article describes an implementation of a nonparametric Bayesian approach to solving binary classification problems on graphs. We consider a hierarchical Bayesian approach with a prior that is constructed by truncating a series expansion of the soft label function using the graph Laplacian eigenfunctions as basis f…

Proposes a framework to improve domain adaptation without labeled data.

SoftCVI uses contrastive estimation to infer complex posteriors.

Logistic regression can handle noisy labels effectively when labels are imperfectly assigned by multiple experts.

A new method transfers adversarial robustness from teacher to student using feature distillation.

Improved segmentation model adaptation for new domains.

No regularization needed for InLDL, achieving efficient and effective model.

There is growing evidence that converting targets to soft targets in supervised learning can provide considerable gains in performance. Much of this work has considered classification, converting hard zero-one values to soft labels---such as by adding label noise, incorporating label ambiguity or using distillation. In…

IDS improves RLHF by smoothing reward data, enhancing model performance.

Unsupervised domain adaptation (UDA) amounts to assigning class labels to the unlabeled instances of a dataset from a target domain, using labeled instances of a dataset from a related source domain. In this paper, we propose to cast this problem in a game-theoretic setting as a non-cooperative game and introduce a ful…

Spanning attack improves black-box attacks with unlabeled data.

Uncertainty estimates help to identify ambiguous, novel, or anomalous inputs, but the reliable quantification of uncertainty has proven to be challenging for modern deep networks. In order to improve uncertainty estimation, we propose On-Manifold Adversarial Data Augmentation or OMADA, which specifically attempts to ge…

Proposes DFDG for robust domain generalization without source domain labels.

In this paper we propose a simple yet powerful method for learning representations in supervised learning scenarios where each original input datapoint is described by a set of vectors and their associated outputs may be given by soft labels indicating, for example, class probabilities. We represent an input datapoint …

Unsupervised domain adaptation is effective in leveraging the rich information from the source domain to the unsupervised target domain. Though deep learning and adversarial strategy make an important breakthrough in the adaptability of features, there are two issues to be further explored. First, the hard-assigned pse…

Estimates hybrid dynamical systems with polynomial expansions and Markovian switching.

New SGD covering technique yields dimension-independent generalization bounds.

Voting ensemble of robust models improves robustness.