Bayesian networks are simplified for categorical variables using staged trees and asymmetry-labeled DAGs.
problem Representing non-symmetric conditional independences in Bayesian networks.
method Formalized relationship between Bayesian networks and staged trees, introduced asymmetry-labeled DAGs, and developed an algorithm to learn staged trees.
result A novel algorithm for learning staged trees that captures non-symmetric independences.
We propose a streaming algorithm for the binary classification of data based on crowdsourcing. The algorithm learns the competence of each labeller by comparing her labels to those of other labellers on the same tasks and uses this information to minimize the prediction error rate on each task. We provide performance g…
The paper cleans label noise in supervised classification using Bernoulli sampling.
problem Label noise degrades supervised classifier performance.
method Proposes a label noise cleaning method based on Bernoulli random sampling.
result The method separates clean and noisy observations without prior label information.
Graph neural networks often assume vertex labels are independent, but we show this is rarely true and propose a method to improve predictions.
problem Graph neural networks often assume vertex labels are conditionally independent given their neighborhood features, which is rarely true.
method We model the joint distribution of residuals on vertices with a parameterized multivariate Gaussian and estimate parameters by maximizing the marginal likelihood of the observed labels.
result Our method achieves substantially higher accuracy than competing baselines and can be interpreted as the strength of correlation among connected vertices.
NURD improves model performance by distilling representations independent of nuisance variables.
problem Models trained under spurious correlations may fail on data with different nuisance-label relationships.
method Developed Nuisance-Randomized Distillation (NURD) to find representations independent of nuisance variables.
result NURD finds representations that perform better regardless of nuisance-label relationships.
New method improves LLM judge accuracy by accounting for dependencies in aggregated binary labels.
problem Classical label aggregation methods fail to account for dependencies among LLM judges, leading to miscalibrated predictions.
method Dependence-aware models based on Ising graphical models and latent factors.
result The proposed method outperforms classical methods on real-world datasets, reducing excess risk.
Tests for classifier independence without ground truth labels.
problem Validation of classifier independence without ground truth labels.
method Exact solution for independent binary classifiers using algebraic geometry.
result Self-consistent test for classifier independence without ground truth labels.
A method uses confidence scores to handle noisy labels for each instance.
problem Learning with noisy labels where each instance's label can randomly change.
method Introduces confidence-scored instance-dependent noise (CSIDN) to estimate transition distributions for each instance.
result Demonstrates the utility and effectiveness of CSIDN through experiments with synthetic and real-world noise.
SGD handles label noise with bounds improving over SGLD.
problem Label noise in non-convex optimization.
method Stochastic gradient descent with uniform dissipativity and smoothness conditions, using Wasserstein distance and algorithmic stability.
result Generalization error bounds with a rate of n−2/3, better than SGLD's n−1/2. Paper proposes a new PLL framework with a progressive identification algorithm.
problem Weakly supervised learning with partial labels.
method Flexible model and optimization algorithm for PLL, progressive identification algorithm.
result Established an estimation error bound and set new state of the art.
CORES2 removes noisy labels by sieving out corrupted examples.
problem Instance-dependent label noise degrades DNN performance.
method CORES2 (COnfidence REgularized Sample Sieve) progressively sieves out corrupted examples.
result CORES2 provides theoretical guarantees for filtering out corrupted examples.
New algorithms learn and interpret asymmetry-labeled DAGs for COVID-19 fear.
problem Bayesian networks' strict symmetric independence assumption limits their applicability in real-world scenarios.
method Developed novel structural learning algorithms for asymmetry-labeled DAGs.
result Efficient algorithms allow for straightforward interpretation of the underlying dependence structure.
SFB uses stable features to adapt unstable ones for better performance.
problem Improving classifier performance on out-of-distribution data by leveraging stable features.
method SFB learns a predictor that separates stable and unstable features, then adapts unstable predictions using stable predictions.
result SFB can learn an asymptotically-optimal predictor without test-domain labels.
New framework learns disentangled causal representations from observed labels.
problem Learning meaningful disentangled causal representations from observed data.
method ICM-VAE framework using flow-based diffeomorphic functions and causal disentanglement prior.
result Induces highly disentangled causal factors and improves robustness.
Active local learning uses fewer labels to predict near-optimal functions.
problem Efficiently predicting near-optimal functions with fewer labels.
method Active local learning algorithm for estimating functions with fewer labels.
result Algorithm makes significantly fewer label queries than traditional methods.
We investigate the use of a non-parametric independence measure, the Hilbert-Schmidt Independence Criterion (HSIC), as a loss-function for learning robust regression and classification models. This loss-function encourages learning models where the distribution of the residuals between the label and the model predictio…
Paper bridges ordinary-label and complementary-label learning frameworks.
problem Combining complementary-label learning with ordinary-label learning.
method Integrates loss functions for one-versus-all and pairwise classification.
result Derives classification risk and error bound for additivity and duality loss functions.
LFD method improves text classification by making features clearer and less label-leaking.
problem Creating interpretable text representations that are both predictive and understandable.
method LFD method: proposes lexical and semantic features from contrastive text pairs, screens candidates using κ, and selects features by residual gain. result LFD features achieve higher human-human and human-LLM agreement than baseline concepts and are less label-leaking.
The ability of learning from noisy labels is very useful in many visual recognition tasks, as a vast amount of data with noisy labels are relatively easy to obtain. Traditionally, the label noises have been treated as statistical outliers, and approaches such as importance re-weighting and bootstrap have been proposed …
Theory explains how AI models can predict unseen tasks without labeled data.
problem Understanding how AI models can generalize to unseen tasks.
method Developed a theoretical framework to analyze zero-shot prediction.
result Identified key quantities and independence relationships for generalization.
There has been a recent interest in understanding the power of local algorithms for optimization and inference problems on sparse graphs. Gamarnik and Sudan (2014) showed that local algorithms are weaker than global algorithms for finding large independent sets in sparse random regular graphs. Montanari (2015) showed t…
Self-training avoids spurious features in domain adaptation.
problem Domain shift with large differences between source and target domains.
method Entropy minimization on unlabeled target data, initialized with a source classifier.
result Entropy minimization avoids using spurious features in large domain shifts.
To reduce the label complexity in Agnostic Active Learning (A^2 algorithm), volume-splitting splits the hypothesis edges to reduce the Vapnik-Chervonenkis (VC) dimension in version space. However, the effectiveness of volume-splitting critically depends on the initial hypothesis and this problem is also known as target…
Multi-label classification is a type of supervised learning where an instance may belong to multiple labels simultaneously. Predicting each label independently has been criticized for not exploiting any correlation between labels. In this paper we propose a novel approach, Nearest Labelset using Double Distances (NLDD)…
Proposes a progressive label correction method for feature-dependent label noise.
problem Real-world large-scale datasets often suffer from heterogeneous, feature-dependent label noise.
method A progressive label correction algorithm that iteratively refines the model.
result A classifier trained with this strategy converges to be consistent with the Bayes classifier for various noise patterns.
In many supervised learning tasks, the entities to be labeled are related to each other in complex ways and their labels are not independent. For example, in hypertext classification, the labels of linked pages are highly correlated. A standard approach is to classify each entity independently, ignoring the correlation…
A new framework CL embeds features and labels for multi-label classification.
problem Exponential growth of output space in multi-label classification.
method Compact Learning (CL) framework that embeds features and labels simultaneously.
result CMLL maximizes label-feature dependency and minimizes label space loss.
Face recognition system trained with noisy labels.
problem Label noise in training deep learning classifiers.
method Review and apply recent methods to manage noisy annotations.
result Improved performance of face recognition system with noisy labels.
New methods identify concepts in trained embeddings reliably without human labels.
problem Identifying interpretable concepts in trained embedding spaces without human labels.
method Explicitly connecting concept discovery to PCA and ICA, proposing novel approaches for dependent concepts.
result Proven methods outperform competitors on a variety of experiments, achieving up to 29% better alignment with ground truth.
A new method for batch prediction sets in classification problems.
problem Constructing reliable prediction sets for multiple unlabeled examples.
method Proposes a uniformly more powerful approach to batch prediction sets using specific combinations of conformal p-values.
result The proposed method provides narrower prediction sets compared to the Bonferroni correction.
Conformal prediction uses past experience to determine precise levels of confidence in new predictions. Given an error probability ε, together with a method that makes a prediction y^ of a label y, it produces a set of labels, typically containing y^, that also contains y with probability 1−ε. Con…
The study examines the generalization of Macro-AUC in multi-label learning, identifying label imbalance as a critical factor.
problem Theoretical understanding of Macro-AUC in multi-label learning is lacking.
method Characterization of generalization properties of learning algorithms based on surrogate losses w.r.t. Macro-AUC, identification of label imbalance as a critical factor.
result The widely-used univariate loss-based algorithm is more sensitive to label imbalance than pairwise and reweighted loss-based ones, implying worse performance.
The problem of multilabel classification when the labels are related through a hierarchical categorization scheme occurs in many application domains such as computational biology. For example, this problem arises naturally when trying to automatically assign gene function using a controlled vocabularies like Gene Ontol…
Recent works have cast some light on the mystery of why deep nets fit any data and generalize despite being very overparametrized. This paper analyzes training and generalization for a simple 2-layer ReLU net with random initialization, and provides the following improvements over recent works: (i) Using a tighter char…
The paper studies how to use AI-generated labels in econometrics to avoid bias.
problem Small misclassification errors in AI-generated labels can lead to large biases in econometric estimators.
method The paper proposes a coupled-label bootstrap method to correct bias and deliver valid inference.
result The coupled-label bootstrap method is valid without the strong independence condition between true and imputed labels.
ICAL improves deep learning model accuracy and NLL with optimized batch labeling.
problem Deep Bayesian Active Learning for efficient model training.
method ICAL uses HSIC to measure dependency and optimizes batch size scaling.
result Significant improvements in model accuracy and NLL on image datasets.
Study efficient learning of robust halfspaces with noise.
problem Learning robust halfspaces in the presence of adversarial perturbations and random label noise.
method Provides conditions for robust learnability and a simple algorithm for any ℓ_p perturbation.
result Simple computationally efficient algorithm for robust learning with random label noise.
We propose Regularized Learning under Label shifts (RLLS), a principled and a practical domain-adaptation algorithm to correct for shifts in the label distribution between a source and a target domain. We first estimate importance weights using labeled source data and unlabeled target data, and then train a classifier …
We present a unified invariance framework for supervised neural networks that can induce independence to nuisance factors of data without using any nuisance annotations, but can additionally use labeled information about biasing factors to force their removal from the latent embedding for making fair predictions. Invar…
Many classification problems can be difficult to formulate directly in terms of the traditional supervised setting, where both training and test samples are individual feature vectors. There are cases in which samples are better described by sets of feature vectors, that labels are only available for sets rather than i…
In this paper, we study a classification problem in which sample labels are randomly corrupted. In this scenario, there is an unobservable sample with noise-free labels. However, before being observed, the true labels are independently flipped with a probability ρ∈[0,0.5), and the random label noise can be class-co…
The study analyzes how label noise affects deep learning feature learning.
problem The impact of label noise on deep learning feature learning.
method Theoretical analysis of a two-layer convolutional neural network under noisy label conditions.
result Two key stages identified: signal learning in Stage I and noise memorization in Stage II.
New method uses weak labels to create valid confidence sets for predictions.
problem Lack of labeled data in machine learning models.
method Developed a conformal prediction framework to provide valid predictive confidence sets using weakly labeled data.
result New coverage definition allows for tighter and more informative (but valid) confidence sets.
FreDF improves forecasting by learning in the frequency domain.
problem Label autocorrelation in future forecasts is often overlooked in time series modeling.
method FreDF learns to forecast in the frequency domain to mitigate label autocorrelation.
result FreDF significantly outperforms existing methods in forecasting accuracy.
New bound proves rationality helps generalization in self-supervised learning.
problem Proving generalization gap in self-supervised learning.
method Proving upper bound on generalization gap for classifiers using rationality and self-supervised representations.
result Generalization gap tends to zero if classifier complexity is low relative to number of samples.
Identifying statistical dependence between the features and the label is a fundamental problem in supervised learning. This paper presents a framework for estimating dependence between numerical features and a categorical label using generalized Gini distance, an energy distance in reproducing kernel Hilbert spaces (RK…
Unified surrogate loss framework for multi-label learning with strong consistency guarantees.
problem Improving consistency and accounting for label correlations in multi-label learning.
method Introducing multi-label logistic loss and extending it to comprehensive multi-label comp-sum losses, proving strong consistency guarantees for any multi-label loss.
result Unified surrogate loss framework benefiting from strong consistency guarantees for any multi-label loss.
This paper examines error bounds for deep learning classifiers with noisy labels.
problem Understanding the performance of classifiers trained on noisy data.
method Derives error bounds for excess risk, decomposing it into statistical and approximation errors. Uses independent block construction for statistical dependencies and vector-valued setting for approximation error.
result Established theoretical results for error bounds in deep learning with noisy labels, mitigating the impact of high-dimensional input spaces.