forgeNet uses a tree-based ensemble to learn feature graphs for deep learning in omics data.
problem Small sample size vs. large feature space in omics data.
method forgeNet integrates a forest feature graph extractor with a GEDFN architecture.
result ForgeNet achieves high classification accuracy on synthetic and real datasets.
New method uses graph-based interpolation for few-shot classification.
problem Learning models with limited labeled examples.
method Graph-based feature vector interpolation for transductive learning.
result Significant gains in few-shot classification compared to other methods.
Discriminators can be good feature extractors despite their task focus.
problem Discriminators' features are often considered useless for downstream tasks.
method Theoretical analysis and feature space examination to understand discriminator's role.
result Discriminator features are robust and can prevent mode collapse, making them useful for transfer learning.
FOCA method prevents co-adaptation between feature extractor and classifier.
problem Co-adaptation between feature extractor and classifier degrades neural network performance.
method FOCA method uses randomly-generated, weak classifiers to optimize feature extractor without explicit co-adaptation.
result FOCA features form a point-like distribution within the same class under special conditions.
Enhances CNN feature extractors' separation capacity analysis.
problem Understanding the separation capacity of CNNs.
method Extending Cover's function-counting theory, analyzing scattering networks.
result Identifies factors affecting scattering networks' separation capacity.
We introduce a method to provide vectorial representations of visual classification tasks which can be used to reason about the nature of those tasks and their relations. Given a dataset with ground-truth labels and a loss function defined over those labels, we process images through a "probe network" and compute an em…
Deep learning is still not a very common tool in speaker verification field. We study deep convolutional neural network performance in the text-prompted speaker verification task. The prompted passphrase is segmented into word states - i.e. digits -to test each digit utterance separately. We train a single high-level f…
In this paper, we use variational recurrent neural network to investigate the anomaly detection problem on graph time series. The temporal correlation is modeled by the combination of recurrent neural network (RNN) and variational inference (VI), while the spatial information is captured by the graph convolutional netw…
Predicting odor's pleasantness simplifies the evaluation of odors and has the potential to be applied in perfumes and environmental monitoring industry. Classical algorithms for predicting odor's pleasantness generally use a manual feature extractor and an independent classifier. Manual designing a good feature extract…
Enhances fault tolerance in neural networks with a novel multi-criteria objective function.
problem Faults in neural networks, especially in deep learning accelerators, reduce classification accuracy.
method Modelled as two networks: Feature Extractor and Classifier. Proposed a novel multi-criteria objective function combining unsupervised and supervised training.
result The proposed approach achieves high accuracy with superior fault tolerance compared to existing regularizers.
Privacy-preserving distributed deep learning method for multiple classification.
problem Privacy issues in training deep learning models for various fields.
method Split learning into common extractor, cloud model, and local classifier.
result Average performance improvement of 2.63% over existing local training models.
Spatial graph representation improves GNN performance.
problem GNNs struggle with distinguishing similar local structures in different graph locations.
method Proposes a spatial graph representation method to distinguish local structures and simplify graph downsampling.
result Proposed graph pooling method achieves competitive results.
Deep convolutional neural networks have led to breakthrough results in practical feature extraction applications. The mathematical analysis of these networks was pioneered by Mallat, 2012. Specifically, Mallat considered so-called scattering networks based on identical semi-discrete wavelet frames in each network layer…
We provide a methodology, resilient feature engineering, for creating adversarially resilient classifiers. According to existing work, adversarial attacks identify weakly correlated or non-predictive features learned by the classifier during training and design the adversarial noise to utilize these features. Therefore…
Improves deep learning training by matching mini-batch distributions.
problem Overfitting and noise in mini-batch training.
method ITDM, which matches the moments of mini-batch distributions to reduce overfitting.
result ITDM reduces overfitting and improves DNN training.
RTFE provides adversarial robustness to multiple models.
problem Adversarial examples can transfer to other models, compromising robustness.
method Proposes RTFE, a deep learning-based pre-processing mechanism.
result RTFE provides adversarial robustness to multiple independently trained classifiers.
Dealing with uncertainty in Bayesian Network structures using maximum a posteriori (MAP) estimation or Bayesian Model Averaging (BMA) is often intractable due to the superexponential number of possible directed, acyclic graphs. When the prior is decomposable, two classes of graphs where efficient learning can take plac…
Proves bounds on spanning two-forests and random cut sizes.
problem Counting spanning two-forests and estimating random cut sizes.
method Uses pairwise effective resistances and potential theory.
result Establishes bounds on the number of spanning two-forests and average cut size.
Meta-learning improves feature extraction for few-shot tasks.
problem Understanding why meta-learning models perform better on few-shot classification.
method Developed hypotheses and a regularizer to improve standard training routines.
result Meta-learned models outperform classical training routines in few-shot classification.
Bayesian learning for forests and trees improves graph detection and structure learning.
problem Learning graph structures in non-decomposable graphs.
method Adapted MCMC and SSS algorithms for forests and trees, using the Chow-Liu algorithm and Matrix Tree Theorem.
result SSS with trees or forests outperforms SSS with decomposable graphs in certain cases.
Proposes a framework for extracting consistent physiological features across users.
problem Variability of biosignals across different users and tasks.
method Adversarial feature extractor for disentangled universal representations.
result Up to 8.8% improvement in average accuracy of classification.
OCmst detects anomalies using CNN features and MSTs.
problem Novelty detection in data with no outliers.
method Uses CNN for feature extraction and MSTs for graph-based modeling.
result Achieved state-of-the-art results on CIFAR10 dataset.
Hyperparameter optimization aims to find the optimal hyperparameter configuration of a machine learning model, which provides the best performance on a validation dataset. Manual search usually leads to get stuck in a local hyperparameter configuration, and heavily depends on human intuition and experience. A simple al…
SHAKE-GNN scales GNNs for large graphs with multi-scale representations.
problem Scaling Graph Neural Networks (GNNs) to large graphs.
method SHAKE-GNN uses a hierarchy of Kirchhoff Forests for stochastic multi-resolution graph decompositions.
result SHAKE-GNN achieves competitive performance on large-scale graph classification benchmarks.
Transfer learning using deep neural networks as feature extractors has become increasingly popular over the past few years. It allows to obtain state-of-the-art accuracy on datasets too small to train a deep neural network on its own, and it provides cutting edge descriptors that, combined with nonparametric learning m…
Headless attacks bypass classification heads to fool transfer learning models.
problem Adversarial attacks against transfer learning models without access to the classification head.
method Label-blind adversarial attacks that do not require class-label information.
result Transfer attack lowers ResNet18 accuracy on CIFAR10 by over 40%.
Adversarially robust transfer learning improves model robustness with minimal data.
problem Data scarcity and computational limitations in adversarially robust transfer learning.
method Train classifiers on top of robust feature extractors from source models, or fine-tune end-to-end in target domain using lifelong learning strategies.
result Accurate and robust models can be produced with little data and without adversarial training.
This work introduces a novel nonparametric density index defined on graphs, the Sum-over-Forests (SoF) density index. It is based on a clear and intuitive idea: high-density regions in a graph are characterized by the fact that they contain a large amount of low-cost trees with high outdegrees while low-density regions…
MORF improves Forests' performance on manifold data by considering feature indices.
problem Forest methods struggle with structured data like images and text.
method MORF incorporates feature locality by sampling random matrices from manifold-aware distributions.
result MORF outperforms ConvNets and other methods on manifold data.
An unsupervised learning classification model is described. It achieves classification error probability competitive with that of popular supervised learning classifiers such as SVM or kNN. The model is based on the incremental execution of small step shift and rotation operations upon selected discriminative hyperplan…
New method improves feature importance assessment in random forests.
problem Improving feature importance measures for random forests.
method Hypothesis testing via self-normalized feature-residual correlation test (FACT).
result The method provides theoretically justified feature importance tests with controlled type I error and appealing power.
The paper models crime risk using Foursquare check-ins and mobility data.
problem Understanding and predicting crime risk in urban areas.
method Directed graph of aggregated movement data, region risk factor derivation, DIFFER features.
result Reliable correlations between DIFFER features and crime count observed.
Improves unsupervised domain adaptation by enforcing feature extractor to focus on task-relevant information.
problem Leveraging label information from source domain for accurate target domain models without labels.
method Variational Information Bottleneck (VBDA) method that explicitly enforces feature extractor to ignore irrelevant task factors.
result Significantly outperforms state-of-the-art methods across three domain adaptation benchmark datasets.
Improves speaker verification for variable-duration utterances using a feature pyramid module.
problem Improving robustness for variable-duration utterances in speaker verification.
method Integrates a feature pyramid module into multi-scale aggregation to enhance speaker-discriminative information from multiple layers.
result Improves performance for both short and long utterances compared to state-of-the-art approaches.
Enhances random forest performance with exogenous randomness.
problem Improving random forest performance through exogenous randomness.
method Developed non-asymptotic MSE expansions for individual trees and forests, identified two types of randomness, and conducted simulations.
result Exogenous randomness, particularly feature subsampling, reduces both bias and variance of random forests.
This paper improves cross-domain learning using random forests for manifold alignment.
problem Improving cross-domain learning and feature integration.
method Semi-supervised manifold alignment using random forest proximities.
result Random forest proximities enhance downstream classification accuracy.
Random forests are a type of ensemble method which makes predictions by combining the results of several independent trees. However, the theory of random forests has long been outpaced by their application. In this paper, we propose a novel random forests algorithm based on cooperative game theory. Banzhaf power index …
A novel fact-checking method using debate dynamics on knowledge graphs.
problem Fact-checking on knowledge graphs with user comprehension and interactive reasoning.
method Reinforcement learning agents debate on paths in the graph to classify facts as true or false.
result Interactive reasoning and user understanding of AI decisions on knowledge graphs.
Two approaches use TDA and graph theory for tennis match prediction.
problem Predicting tennis match outcomes using network features.
method Lower-star filtration on player competitive networks, Random Forest model, modified Katz similarity index.
result TDA features alone can achieve above-chance prediction in tennis match outcomes.
The computational demands of computer vision tasks based on state-of-the-art Convolutional Neural Network (CNN) image classification far exceed the energy budgets of mobile devices. This paper proposes FixyNN, which consists of a fixed-weight feature extractor that generates ubiquitous CNN features, and a conventional …
A new model improves uncertainty estimation in deep learning.
problem Deep Kernel Learning (DKL) produces unreliable uncertainty estimates.
method Proposed a bi-Lipschitz constraint to preserve distances in feature space.
result DUE model outperforms previous DKL and other methods in uncertainty quality.
Fuzzy Forests reduces feature space in high-dimensional survey data.
problem High-dimensional and highly correlated datasets in social science.
method Fuzzy Forests algorithm, a variant of Random Forests.
result Partisan polarization was the strongest factor in the 2020 presidential election.
Graph Neural Network identifies ASD biomarkers from fMRI data.
problem Finding biomarkers for Autism Spectrum Disorder (ASD).
method Graph Neural Network (GNN) for analyzing task-fMRI brain networks, 2-stage pipeline to interpret feature importance.
result GNN achieves high accuracy in identifying ASD biomarkers and reveals their association with social behaviors.
ADNN uses prior knowledge to construct financial features.
problem Feature construction in financial trading.
method Tailored neural network structure with domain knowledge.
result ADNN constructs more informative features than genetic programming.
Decision forests learn to model text by evaluating categorical-set conditions.
problem Decision forests cannot directly model text features.
method Defined and learned conditions for categorical-set features, enabling efficient text modeling.
result Decision forests can now directly model text features.
New method initializes MLPs for tabular data with tree-based feature interactions.
problem No dedicated neural network architecture for tabular data.
method Sparse tree-based initialization for MLPs.
result New method outperforms default MLP initialization and gradient boosting.
We define and calculate the HOMFLY polynomial for a specific type of quiver.
problem Calculating the HOMFLY polynomial for forest quivers.
method Recursive definition and closed-form expression for forest quivers.
result Closed-form expression for the HOMFLY polynomial of a forest quiver.
We study graph estimation and density estimation in high dimensions, using a family of density estimators based on forest structured undirected graphical models. For density estimation, we do not assume the true distribution corresponds to a forest; rather, we form kernel density estimates of the bivariate and univaria…