A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
IVFS simplifies feature selection for high-dimensional data preservation.
FLFE improves machine learning by efficiently and securely transforming features.
Reproduces IVFS for high-dimensional data structure preservation.
Eigen-GNN enhances GNNs by preserving graph structures.
Cloak identifies essential features to preserve prediction privacy without provider collaboration.
Two new algorithms reduce feature space while preserving non-linear relationships.
Slow feature analysis (SFA) is an unsupervised-learning algorithm that extracts slowly varying features from a multi-dimensional time series. A supervised extension to SFA for classification and regression is graph-based SFA (GSFA). GSFA is based on the preservation of similarities, which are specified by a graph struc…
Bispectral OT improves dataset comparison by preserving intrinsic coherence.
Network embedding is the process of learning low-dimensional representations for nodes in a network, while preserving node features. Existing studies only leverage network structure information and focus on preserving structural features. However, nodes in real-world networks often have a rich set of attributes providi…
New method learns disentangled representations using Gromov-Monge maps.
AAT separates robust and non-robust features without supervision.
VFGNN tackles privacy-preserving node classification with federated GNN.
Feature selection, which searches for the most representative features in observed data, is critical for health data analysis. Unlike feature extraction, such as PCA and autoencoder based methods, feature selection preserves interpretability, meaning that the selected features provide direct information about certain h…
Empower efficient representation of distributions through moment-preserving methods.
Reservoir subspace injection improves online ICA by preserving injected features.
Paper introduces privacy-preserving inventory policy learning for feature-based newsvendor with unknown demand.
Powered by machine learning services in the cloud, numerous learning-driven mobile applications are gaining popularity in the market. As deep learning tasks are mostly computation-intensive, it has become a trend to process raw data on devices and send the deep neural network (DNN) features to the cloud, where the feat…
Automates feature selection and weighting in molecular systems.
Feature selection is a dimensionality reduction technique that selects a subset of representative features from high dimensional data by eliminating irrelevant and redundant features. Recently, feature selection combined with sparse learning has attracted significant attention due to its outstanding performance compare…
This paper compresses large datasets for efficient machine learning.
An algorithm preserves topological features in dimensionality reduction.
New Lie-group methods preserve geometric divergence-free features on manifolds.
In this paper, we investigate the unsupervised deep representation learning issue and technically propose a novel framework called Deep Self-representative Concept Factorization Network (DSCF-Net), for clustering deep features. To improve the representation and clustering abilities, DSCF-Net explicitly considers discov…
Paper proposes a privacy-preserving method for estimating complex models.
A new method for privacy-preserving data distillation using wavelet features from ScatterNet.
CDOT optimizes transport between domains preserving both feature and geometric structure.
Feature selection methods are widely used in order to solve the 'curse of dimensionality' problem. Many proposed feature selection frameworks, treat all data points equally; neglecting their different representation power and importance. In this paper, we propose an unsupervised hypergraph feature selection method via …
Effective feature representation is key to the predictive performance of any algorithm. This paper introduces a meta-procedure, called Non-Euclidean Upgrading (NEU), which learns feature maps that are expressive enough to embed the universal approximation property (UAP) into most model classes while only outputting fea…
Feature hashing and other random projection schemes are commonly used to reduce the dimensionality of feature vectors. The goal is to efficiently project a high-dimensional feature vector living in into a much lower-dimensional space , while approximately preserving Euclidean norm. These sc…
Domain adaptation aims to assist the modeling tasks of the target domain with knowledge of the source domain. The two domains often lie in different feature spaces due to diverse data collection methods, which leads to the more challenging task of heterogeneous domain adaptation (HDA). A core issue of HDA is how to pre…
New method distinguishes feature relevance in non-linear contexts.
LP-FT improves personalized model training in FL by balancing generalization and personalization.
Study shows how a strong model can learn a task's feature while retaining other capabilities.
Over the past few decades, we have witnessed a large family of algorithms that have been designed to provide different solutions to the problem of dimensionality reduction (DR). The DR is an essential tool to excavate the important information from the high-dimensional data by mapping the data to a low-dimensional subs…
New deep learning method preserves orientation in shape matching.
CDSPP learns domain-specific projections for heterogeneous domain adaptation.
We propose a probabilistic model to infer supervised latent variables in the Hamming space from observed data. Our model allows simultaneous inference of the number of binary latent variables, and their values. The latent variables preserve neighbourhood structure of the data in a sense that objects in the same semanti…
This paper is first-line research expanding GANs into graph topology analysis. By leveraging the hierarchical connectivity structure of a graph, we have demonstrated that generative adversarial networks (GANs) can successfully capture topological features of any arbitrary graph, and rank edge sets by different stages a…
We present a numerical approach for approximating unknown Hamiltonian systems using observation data. A distinct feature of the proposed method is that it is structure-preserving, in the sense that it enforces conservation of the reconstructed Hamiltonian. This is achieved by directly approximating the underlying unkno…
Method preserves correlations in synthetic data.
This paper tackles spatio-temporal information preservation in machine learning.
SNAM improves NAM's accuracy and feature selection via group sparsity.
We detail a new framework for privacy preserving deep learning and discuss its assets. The framework puts a premium on ownership and secure processing of data and introduces a valuable representation based on chains of commands and tensors. This abstraction allows one to implement complex privacy preserving constructs …
Privacy-preserving distributed deep learning method for multiple classification.
Graph neural networks (GNNs) are shown to be successful in modeling applications with graph structures. However, training an accurate GNN model requires a large collection of labeled data and expressive features, which might be inaccessible for some applications. To tackle this problem, we propose a pre-training framew…
Method transfers feature representation from large to small models using perception coherence.
We present Graph Random Neural Features (GRNF), a novel embedding method from graph-structured data to real vectors based on a family of graph neural networks. The embedding naturally deals with graph isomorphism and preserves the metric structure of the graph domain, in probability. In addition to being an explicit em…
Graph neural networks (GNNs) have shown great power in learning on attributed graphs. However, it is still a challenge for GNNs to utilize information faraway from the source node. Moreover, general GNNs require graph attributes as input, so they cannot be appled to plain graphs. In the paper, we propose new models nam…