Paper shows adversarial training can be fooled by new type of noise.
problem Adversarial training can be fooled by new types of noise.
method Designing ADVIN, a new type of inducing noise.
result ADVIN can degrade adversarial training robustness by 99.9%.
TUDataset provides benchmark datasets for graph learning.
problem Lack of meaningful benchmark datasets and standardized evaluation procedures for graph learning.
method Collection and standardization of 120 graph datasets from various applications.
result Standardized evaluation procedures and baseline experiments provided.
Study reveals statistical bias in dataset replication, reducing accuracy drop from 11-14% to 3.6%.
problem Statistical bias in dataset replication affects model generalization accuracy.
method Analyzed ImageNet-v2, identified and corrected for bias, and compared results.
result Correcting bias reduces accuracy drop from 11-14% to 3.6%.
Torchmeta simplifies meta-learning evaluation across multiple datasets.
problem Inconsistent evaluation of meta-learning algorithms across different datasets.
method Introduces a library that provides data-loaders for standard benchmarks and simplifies model compatibility.
result Seamless and consistent evaluation of meta-learning algorithms on multiple datasets.
Meta-learning model clusters data better than standard methods.
problem Challenges in clustering due to custom loss functions and small datasets.
method Trains a recurrent model to learn clustering from various datasets.
result Meta clustering model outperforms standard clustering techniques on unseen datasets.
We present a new technique called contrastive principal component analysis (cPCA) that is designed to discover low-dimensional structure that is unique to a dataset, or enriched in one dataset relative to other data. The technique is a generalization of standard PCA, for the setting where multiple datasets are availabl…
New method for initializing RBM weights without datasets.
problem No dataset-free weight-initialization for RBMs.
method Statistical mechanical analysis to derive Gaussian distribution with optimized standard deviation.
result Optimal weight initialization improves learning efficiency in RBMs.
This paper presents the recently published Cerema AWP (Adverse Weather Pedestrian) dataset for various machine learning tasks and its exports in machine learning friendly format. We explain why this dataset can be interesting (mainly because it is a greatly controlled and fully annotated image dataset) and present base…
Machine learning methods tend to outperform traditional statistical models at prediction. In the prediction of academic achievement, ML models have not shown substantial improvement over logistic regression. So far, these results have almost entirely focused on college achievement, due to the availability of administra…
New hierarchical model improves on standard practice for high-dimensional data.
problem Poor statistical performance in high-dimensional hierarchical models.
method Model effects as exchangeable across covariates and correlated across datasets.
result Empirical Bayes estimator outperforms classic approach in high-dimensional settings.
Paper tightens variational GP approximations for large datasets.
problem Scaling Gaussian processes to large datasets.
method Relaxing the standard assumption about inducing points' posterior matching the prior, leading to a tighter variational approximation.
result The proposed approximation consistently matches or outperforms standard sparse variational GPs while maintaining computational cost.
Research shows continual learning challenges in confounded datasets.
problem Challenges in mitigating confounders in continual learning settings.
method Formal description of continual confounders, construction of ConCon dataset.
result Standard continual learning methods fail to ignore confounders.
This paper extracts topic-specific subgraphs from Wikidata for easier research.
problem Time-consuming and task-specific tuning in using Wikidata for graph processing.
method Unified framework to extract topic-specific subgraphs from Wikidata.
result Standardized sub-graphs for easier evaluation of graph processing algorithms.
A comparative study of the application of Gaussian Mixture Model (GMM) and Radial Basis Function (RBF) in biometric recognition of voice has been carried out and presented. The application of machine learning techniques to biometric authentication and recognition problems has gained a widespread acceptance. In this res…
New method balances multivariate model fitting for mixed likelihoods.
problem Multivariate models often fit only a subset of observed variables.
method Lipschitz standardization for data preprocessing.
result Lipschitz standardization leads to more accurate multivariate models.
Tree-based models outperform deep learning on tabular data, especially for medium-sized datasets.
problem Understanding why tree-based models outperform deep learning on tabular data.
method Extensive benchmarks of tree-based and deep learning models on 45 datasets, accounting for hyperparameters.
result Tree-based models remain state-of-the-art on medium-sized tabular data, even without hyperparameter optimization.
Paper introduces a fraud detection dataset benchmark.
problem Unique challenges in fraud detection datasets.
method Compilation of publicly available fraud datasets.
result Demonstrates applications of the Fraud Dataset Benchmark.
Datasets often contain biases which unfairly disadvantage certain groups, and classifiers trained on such datasets can inherit these biases. In this paper, we provide a mathematical formulation of how this bias can arise. We do so by assuming the existence of underlying, unknown, and unbiased labels which are overwritt…
Given the success of the gated recurrent unit, a natural question is whether all the gates of the long short-term memory (LSTM) network are necessary. Previous research has shown that the forget gate is one of the most important gates in the LSTM. Here we show that a forget-gate-only version of the LSTM with chrono-ini…
Standardized fairness measures for continuous risk scores using Wasserstein distance.
problem Quantifying and interpreting group disparities in continuous risk scores.
method Proposes standardized fairness measures based on Wasserstein distance for continuous scores.
result Proposed measures outperform ROC-based fairness measures by being more explicit and quantifying significant biases.
Optimal ensemble construction improves prediction accuracy for multi-study tasks, especially in pandemic scenarios.
problem Poor out-of-study prediction performance due to heterogeneous datasets.
method Optimal ensemble construction using a two-stage stacking strategy that jointly estimates ensemble weights and study-specific model parameters.
result Our method outperforms multi-study stacking and other standard methods in predicting excess mortality during the pandemic.
New method creates universal perturbations to fool neural network interpretations.
problem Vulnerability of gradient-based saliency maps to adversarial perturbations.
method Gradient-based optimization and PCA-based approach to create UPI.
result Existence and successful application of Universal Perturbation for Interpretation (UPI).
We provide a method to prepare covariance matrices for quantum datasets.
problem No concrete protocol for preparing covariance matrices for quantum datasets.
method Amplitude encoding of data, exploiting global phase symmetry to center the dataset.
result Covariance matrix can be prepared for arbitrary quantum datasets or centered classical datasets.
Self-regulating annealing improves sampling from heavy-tailed datasets.
problem Sampling from heavy-tailed distributions using diffusion models.
method Proposed an SDE-based sampler with a state-dependent diffusion coefficient.
result State dependence induces a self-regulating annealing mechanism.
The standard LSTM recurrent neural networks while very powerful in long-range dependency sequence applications have highly complex structure and relatively large (adaptive) parameters. In this work, we present empirical comparison between the standard LSTM recurrent neural network architecture and three new parameter-r…
The Resilient Propagation (Rprop) algorithm has been very popular for backpropagation training of multilayer feed-forward neural networks in various applications. The standard Rprop however encounters difficulties in the context of deep neural networks as typically happens with gradient-based learning algorithms. In th…
Simplifies risk minimization combining mean and standard deviation.
problem Minimizing mean and standard deviation under heavy-tailed losses.
method Adapting robust mean estimation technique to include standard deviation.
result Simple approach performs as well or better than alternative risk criteria.
Baseline for few-shot image classification outperforms state-of-the-art.
problem Few-shot image classification challenges.
method Fine-tuning deep networks trained with cross-entropy loss, transductively.
result Outperforms state-of-the-art on various datasets.
Shifts dataset evaluates uncertainty in real-world tasks across modalities.
problem Lack of standard datasets for evaluating uncertainty estimation and robustness to distributional shift.
method Proposes Shifts Dataset for evaluation of uncertainty estimates and robustness to distributional shift across tabular, audio, text, and sensor data.
result Baseline results for tabular weather prediction, machine translation, and SDC vehicle motion prediction.
Paper tackles offline RL from mixed datasets with adaptive KL regularizer.
problem Challenges in optimizing RL and BC signals with varying action coverage and multiple action modes.
method Adaptively weighted reverse KL divergence regularizer based on TD3 algorithm.
result Empirically outperforms existing offline RL algorithms in MuJoCo locomotion tasks.
New topic modeling method scales to large datasets.
problem Large-scale topic modeling with high co-occurrence data.
method Introduced Full Dependence Mixture (FDM) model for direct topic learning.
result FDM model performs comparably or better than benchmarks on large datasets.
We present two online causal structure learning algorithms which can track changes in a causal structure and process data in a dynamic real-time manner. Standard causal structure learning algorithms assume that causal structure does not change during the data collection process, but in real-world scenarios, it does oft…
The recent framework of compressive statistical learning aims at designing tractable learning algorithms that use only a heavily compressed representation-or sketch-of massive datasets. Compressive K-Means (CKM) is such a method: it estimates the centroids of data clusters from pooled, non-linear, random signatures of …
Enhances speech emotion recognition by adapting to varying time scales.
problem Robust emotion recognition from speech audio with temporal variations.
method Introduces multi-time-scale (MTS) convolutional layers to CNNs.
result MTS layers improve generalization, especially on smaller datasets.
In the classical Gaussian SVM classification we use the feature space projection transforming points to normal distributions with fixed covariance matrices (identity in the standard RBF and the covariance of the whole dataset in Mahalanobis RBF). In this paper we add additional information to Gaussian SVM by considerin…
GANs improve missing data imputation for ranking tasks.
problem Missing data in ranking datasets violates standard assumptions.
method Conditional Imputation GAN for Extended Missing At Random and Extended Always Missing At Random mechanisms.
result Optimal GAN imputation for EMAR and EAMAR mechanisms.
Study tests if input gradients highlight discriminative features, finds they often fail.
problem Validity of assumption that input gradients highlight discriminative features in model predictions.
method Developed DiffROAR framework and BlockMNIST dataset to test assumption on four benchmarks.
result Input gradients of standard models often fail to highlight discriminative features, while robust models do.
New method denoises and fills in missing image data without clean training data.
problem Denoising and inpainting images with noisy, incomplete data.
method Robust Hadamard Autoencoders trained on noisy, incomplete data.
result Autoencoders can perform denoising and inpainting simultaneously.
Proposes a method to learn conditional VAEs from datasets with missing covariates.
problem Learning conditional VAEs from datasets with missing covariates.
method Augments conditional VAEs with a prior distribution for missing covariates and estimates their posterior using amortised variational inference.
result The proposed method outperforms previous methods in learning conditional VAEs from non-temporal, temporal, and longitudinal datasets.
Paper proposes a dataset quality process for ML systems.
problem Inadequate standards for ML datasets in safety-critical systems.
method Proposes a dataset specification and verification process.
result Demonstrates the process on a railway signal recognition system.
DsDm selects data to improve model performance, avoiding handpicked notions of quality.
problem Selecting data for model training can lead to worse performance than random selection.
method Formulates dataset selection as an optimization problem, maximizing model performance.
result Selected datasets improve language model performance by 2x over baseline methods.
Paper proposes a new autoencoder metric for balanced learning in imbalanced tabular datasets.
problem Challenges of imbalanced self-supervised learning in tabular data.
method Developed a Multi-Supervised Balanced MSE metric to balance learning.
result The new metric outperforms standard MSE in imbalanced datasets.
PerturBench benchmarks ML models for cellular perturbation analysis.
problem Standardizing benchmarking in modeling single cell transcriptomic responses to perturbations.
method Modular platform, diverse datasets, metrics, extensive evaluation, rank metrics.
result Simpler models are competitive and scale well with larger datasets.
WRENCH benchmarks weak supervision datasets for machine learning.
problem Lack of standardized evaluation for weak supervision datasets.
method Developed a comprehensive benchmark platform WRENCH.
result Demonstrated the efficacy of WRENCH as a benchmark platform.
CbMLC improves multi-label classification with noisy labels.
problem Evaluating multi-label classifiers with noisy labels.
method Context-Based Multi-Label Classifier (CbMLC) that handles noisy labels without additional supervision.
result CbMLC yields substantial improvements over previous methods in noisy label settings.
Researchers compute Bayes error for classification models using normalizing flows.
problem Evaluating the inherent difficulty of classification problems.
method Invertible transformations and Gaussian base distributions to compute Bayes error.
result State-of-the-art models can achieve near-optimal accuracy but not always.
Study aggregation of statistical evidence under unknown dependence using group-invariance.
problem Aggregating statistical evidence under unknown and complex dependence structures.
method Develops a framework using group-invariance and permutation-based constructions to aggregate evidence across transformed datasets.
result Shows uniform improvement in critical values for single-batch aggregation over deterministic calibrations, adapting to unknown dependence structures.
Deep learning methods such as multitask neural networks have recently been applied to ligand-based virtual screening and other drug discovery applications. Using a set of industrial ADMET datasets, we compare neural networks to standard baseline models and analyze multitask learning effects with both random cross-valid…