Improved saliency maps for deep neural networks with reduced noise.
problem Noisy explanations in Integrated Gradients for deep neural networks.
method SmoothTaylor, adaptive noising, and SmoothGrad techniques.
result SmoothTaylor and adaptive noising generate better quality saliency maps.
Efficiently learns halfspaces with malicious noise, near-optimal label complexity.
problem Learning s-sparse halfspaces under malicious label noise. method Active learning algorithm with instance reweighting and empirical risk minimization.
result Near-optimal label complexity of O(slog4d/ε) and noise tolerance Ω(ε). We consider the problem of learning linear classifiers when both features and labels are binary. In addition, the features are noisy, i.e., they could be flipped with an unknown probability. In Sy-De attribute noise model, where all features could be noisy together with same probability, we show that 0-1 loss ($l_{…
Users in various web and mobile applications are vulnerable to attribute inference attacks, in which an attacker leverages a machine learning classifier to infer a target user's private attributes (e.g., location, sexual orientation, political view) from its public data (e.g., rating scores, page likes). Existing defen…
PiNGDA learns beneficial noise for graph augmentation stability.
problem Challenges in generating effective and stable graph augmentations.
method PiNGDA uses positive-incentive noise to scientifically analyze and generate beneficial graph augmentations.
result PiNGDA improves GCL performance by learning beneficial noise on graph topology and attributes.
Framework for fair classification with noisy protected attributes and provable guarantees.
problem Fair classification with noisy protected attributes.
method Optimization framework for linear and linear-fractional fairness constraints, handling multiple non-binary attributes.
result Provably fair classifier with minimal accuracy loss, even with large noise.
PS-IG improves feature attribution by reducing noise and variance.
problem Improving feature attribution in machine learning models.
method Path-sampled integrated gradients (PS-IG) computes expected value over sampled baselines.
result PS-IG reduces attribution variance by a factor of 1/3 under uniform sampling.
New algorithm mitigates bias in subset selection with noisy protected attributes.
problem Mitigating bias in subset selection when protected attributes are noisy.
method Formulated a denoised selection problem and developed a linear-programming based approximation algorithm.
result The approach can produce fairer subsets despite noisy protected attributes.
Unified bounds for DP risks reduce noise and improve accuracy.
problem Difficult interpretation and calibration of DP mechanisms.
method Hypothesis-testing interpretation of DP (f-DP) and unified bounds. result Unified bounds are tighter and tunable for specific risks.
Study on list learning with noisy data, showing limits and some learnable cases.
problem Learning from noisy data in a list learning context.
method Inspired by coding theory, extends list learning model to study sparse conjunctions and parities/majors.
result Sparse conjunctions can be efficiently list learned under certain conditions, but parities and majors cannot be efficiently learned.
New algorithm learns PTFs with noisy data efficiently.
problem Learning low-degree PTFs with noisy data efficiently.
method Structural result and novel robust Chow vector estimation.
result PAC learns PTFs with nasty noise using efficient samples.
Paper develops methods for fair insurance pricing without direct access to sensitive attributes.
problem Fairness in insurance pricing with restricted access to sensitive attributes.
method Develops statistical methods for estimating discrimination-free premiums using privatized sensitive attributes.
result The proposed methods enable fair insurance pricing while respecting privacy and regulatory constraints.
Paper proposes MUCS for more reliable TDA in diffusion models.
problem Current TDA approaches lack reliability and robustness.
method Mirrored unlearning and noise-consistent skew (MUCS).
result MUCS outperforms existing methods on three datasets.
WassersteinGrad improves weather forecasting explanations by addressing geometric misalignment issues.
problem Improving explainability of autoregressive neural predictions on dynamic physical fields.
method WassersteinGrad, a geometric consensus method for averaged perturbed attribution maps.
result WassersteinGrad provides more accurate explanations for weather forecasting models.
Method identifies root causes of anomalies in causal processes.
problem Identifying root causes of anomalies in causal processes.
method Noisy functional causal model, Bayesian learning, gradient-based attribution.
result Proposes efficient method to compute anomaly attribution scores.
This paper explores BDL hyperparameters for robust polynomial mapping with noise.
problem Designing BDL hyperparameters for robust function mapping with uncertainty quantification.
method Mapping Bayesian connectionist representations to polynomials of varying orders and noise types.
result Optimal network depth and ensemble size for prediction and uncertainty quantification.
Feature attribution methods, which explain an individual prediction made by a model as a sum of attributions for each input feature, are an essential tool for understanding the behavior of complex deep learning models. However, ensuring that models produce meaningful explanations, rather than ones that rely on noise, i…
Density-based spatial clustering of applications with noise (DBSCAN) is a data clustering algorithm which has the high-performance rate for dataset where clusters have the constant density of data points. One of the significant attributes of this algorithm is noise cancellation. However, DBSCAN demonstrates reduced per…
Noise injection improves inference privacy in DNN models.
problem Malicious servers can infer sensitive attributes from input data.
method Adaptive Noise Injection (ANI) using a lightweight DNN on the client.
result Significant improvement in privacy (up to 48.5% degradation in sensitive-task accuracy with <1% degradation in primary accuracy).
Bayesian approach scores influential training examples for model predictions.
problem Enhance interpretability and safety of machine learning models.
method Formulate TDA as a Bayesian information-theoretic problem, scoring subsets by information loss.
result Method aligns with classical influence scores while promoting diversity for subsets.
New framework improves attribution of predictive uncertainties in classification models.
problem Improper attribution of predictive uncertainties in classification tasks.
method Combines path integrals, counterfactual explanations, and generative models.
result Framework outperforms existing alternatives in quantitative evaluations.
CARV reduces compute cost for downstream pipelines using diffusion models.
problem High variance in Monte Carlo estimators from diffusion models limits compute efficiency.
method CARV uses hierarchical MC estimation with amortized upstream computation and stratified-inverse-CDF.
result CARV delivers 2-3x effective compute multipliers without changing the objective.
Attribution methods provide insights into the decision-making of machine learning models like artificial neural networks. For a given input sample, they assign a relevance score to each individual input variable, such as the pixels of an image. In this work we adapt the information bottleneck concept for attribution. B…
BIND removes background noise from binary matrices, improving detection accuracy and fairness.
problem Real data often violates the i.i.d assumption for binary matrix entries, leading to inaccurate detection.
method BIND optimizes detection by estimating row- and column-wise mixture distributions and eliminating background noise.
result BIND effectively removes background noise and increases detection accuracy and fairness.
CAP adapts optimization to class attributes for better fairness.
problem Heterogeneities across classes impede classification performance.
method CAP generates class-specific learning strategies based on attributes.
result CAP improves over naive approach and is competitive with prior art.
We consider a query-based data acquisition problem for binary classification of unknown labels, which has diverse applications in communications, crowdsourcing, recommender systems and active learning. To ensure reliable recovery of unknown labels with as few number of queries as possible, we consider an effective quer…
GNNs robustness in community detection is studied with various perturbations.
problem Understanding GNNs robustness in community detection tasks.
method Systematic computational evaluation of six GNN architectures on synthetic and real-world networks.
result Supervised GNNs achieve higher baseline accuracy, while DMoN shows stronger resilience to perturbations.
Infer-AVAE infers missing user attributes from incomplete data using a novel adversarial approach.
problem Incomplete user attributes in social networks.
method Infer-AVAE combines MLP and GNNs with adversarial training to infer missing attributes.
result Infer-AVAE outperforms baselines by 7.0% in accuracy on real-world datasets.
Deep networks learn clean structure before memorizing corrupted labels, leaving a spectral signature in gradient centered scatter.
problem Deep networks' transition from learning clean structure to memorizing corrupted labels under label noise.
method Analysis of the centered scatter of per-example last-layer gradients to identify Fisher Rank Inflation.
result Fisher Rank Inflation is a spectral signature of memorization under label noise, with effective rank expanding during memorization.
The performance of standard learning procedures has been observed to differ widely across groups. Recent studies usually attribute this loss discrepancy to an information deficiency for one group (e.g., one group has less data). In this work, we point to a more subtle source of loss discrepancy---feature noise. Our mai…
SISR improves feature attribution in complex payoff schemes.
problem Distorted feature attributions due to non-additive payoff functions and high-dimensional feature spaces.
method Sparse Isotonic Shapley Regression (SISR) learns a monotonic transformation to restore additivity and enforces L0 sparsity.
result SISR achieves strong support recovery and stable attributions across various payoff schemes.
New research shows fairness in machine learning can sometimes make disadvantaged groups worse off.
problem The impact of fairness constraints in machine learning on different groups.
method Unified, population-level (Bayes) framework for binary classification under prevalent group fairness notions.
result Fairness in machine learning can lead to leveling down, making one or both groups worse off.
This research tackles image classification with noise, proposing committees of CNNs.
problem Image classification with concurrent feature and label noise.
method Committees of Convolutional Neural Networks (CNNs) for MNIST, CIFAR-10, and CIFAR-100 datasets.
result Committees outperform single models in noisy conditions, especially on difficult datasets.
We investigate the "compass rose" (Crack, T.F. and Ledoit, O. (1996), Journal of Finance, 51(2), pg. 751-762) patterns revealed in phase portraits (delay plots) of stock returns. The structures observed in these diagrams have been attributed mainly to price clustering and discreteness. Using wavelet based denoising, we…
This work reveals how label noise can cause a final ascent in neural network performance curves.
problem The impact of label noise on the performance of neural networks.
method Theoretical analysis and extensive experiments on various neural network architectures.
result Label noise can lead to a final ascent in the test loss curve, improving generalization at intermediate model widths.
AGE improves graph embedding by smoothing features and iteratively enhancing node embeddings.
problem Challenges in attributed graph embedding, especially in preserving optimal low-pass characteristics and robustness.
method AGE, a novel framework combining Laplacian smoothing and adaptive encoding, addresses these issues.
result AGE consistently outperforms state-of-the-art methods on node clustering and link prediction tasks.
Improved decision tree learning guarantees for complex functions.
problem Achieving provable guarantees for decision tree induction with complex target functions.
method Introduces a new splitting criterion that considers correlations between target function and subsets of attributes.
result Proves provable guarantees for all target functions with respect to the uniform distribution, circumventing previous impossibility results.
Regularization helps resolve ambiguity in mean-variance models, improving predictive uncertainty quantification.
problem Signal-to-noise ambiguity in overparameterized mean-variance models.
method Statistical field theory framework to explain phase transition.
result Regularization reduces variability and improves predictive uncertainty quantification.
The paper tackles noisy functional data by exploring a multivariate perspective.
problem Noisy functional data measured on discrete points.
method Factor model and principal components analysis.
result The latent signal can be accurately estimated using multivariate methods.
Graph embedding techniques have been increasingly deployed in a multitude of different applications that involve learning on non-Euclidean data. However, existing graph embedding models either fail to incorporate node attribute information during training or suffer from node attribute noise, which compromises the accur…
It is a common practice in the machine learning community to assume that the observed data are noise-free in the input attributes. Nevertheless, scenarios with input noise are common in real problems, as measurements are never perfectly accurate. If this input noise is not taken into account, a supervised machine learn…
New algorithm learns halfspaces with adversarial noise efficiently.
problem Learning halfspaces in the presence of adversarial noise.
method Polynomial-time Perceptron-like online active learning algorithm.
result Near-optimal label and sample complexity with isotropic log-concave marginal distribution.
Truncated SGD with heavy-tailed noise eliminates sharp local minima.
problem Avoiding sharp local minima in deep learning models.
method Truncated SGD with heavy-tailed gradient noise.
result Truncated SGD can eliminate sharp local minima entirely from its training trajectory.
Active learning improves ordering of items with contextual attributes.
problem Learning accurate item orderings from pairwise comparisons, especially when exhaustive comparisons are impractical.
method Proposes an active learning strategy that samples items to minimize expected ordering error, accounting for uncertainty in comparisons.
result Superior sample efficiency and generalization compared to non-contextual ranking approaches and active preference learning baselines.
Estimates intrinsic dimension of data sets robustly to noise.
problem Estimating intrinsic dimension of noisy data sets.
method Quantum Cognition Machine Learning for data representation and spectral gap detection.
result Robust estimation of intrinsic dimension in the presence of Gaussian noise.
This paper presents a Semantic Attribute Modulation (SAM) for language modeling and style variation. The semantic attribute modulation includes various document attributes, such as titles, authors, and document categories. We consider two types of attributes, (title attributes and category attributes), and a flexible a…
Classifier chains have recently been proposed as an appealing method for tackling the multi-label classification task. In addition to several empirical studies showing its state-of-the-art performance, especially when being used in its ensemble variant, there are also some first results on theoretical properties of cla…
Statistical test detects model degradations in optimized language models.
problem Detecting model degradations in optimized language models.
method Statistical hypothesis testing framework based on McNemar's test.
result Even small accuracy degradations (0.3%) can be attributed to actual degradations, not noise.