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.
ADEC addresses feature randomness and drift in autoencoder-based clustering.
MadNet uses MAD optimization to enhance deep model robustness against adversarial attacks.
New method interprets deep embeddings for diabetes patient clustering.
A new deep clustering model learns both clustering and embedding simultaneously.
This paper tackles deep clustering evaluation challenges in high-dimensional data.
Deep clustering has increasingly been demonstrating superiority over conventional shallow clustering algorithms. Deep clustering algorithms usually combine representation learning with deep neural networks to achieve this performance, typically optimizing a clustering and non-clustering loss. In such cases, an autoenco…
Improves deep learning robustness by enforcing local and global compactness.
ARMED models improve deep learning interpretability and generalize better on clustered data.
AutoEmbedder clusters unlabeled data using semi-supervised DNN embedding.
Graph embedding aims to transfer a graph into vectors to facilitate subsequent graph analytics tasks like link prediction and graph clustering. Most approaches on graph embedding focus on preserving the graph structure or minimizing the reconstruction errors for graph data. They have mostly overlooked the embedding dis…
DEMVC improves multi-view clustering with collaborative training and deep autoencoders.
New algorithm B++&C improves hierarchical clustering on large deep embedding datasets.
ClusTR improves clustering-based models' robustness without adversarial training.
Graph clustering is a fundamental task which discovers communities or groups in networks. Recent studies have mostly focused on developing deep learning approaches to learn a compact graph embedding, upon which classic clustering methods like k-means or spectral clustering algorithms are applied. These two-step framewo…
The clustering methods have recently absorbed even-increasing attention in learning and vision. Deep clustering combines embedding and clustering together to obtain optimal embedding subspace for clustering, which can be more effective compared with conventional clustering methods. In this paper, we propose a joint lea…
Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the laten…
Machine Learning (ML) and Deep Learning (DL) models have achieved state-of-the-art performance on multiple learning tasks, from vision to natural language modelling. With the growing adoption of ML and DL to many areas of computer science, recent research has also started focusing on the security properties of these mo…
A new clustering method using deep neural networks with size constraints.
Adversarial training improves graph autoencoder generalization.
We propose a deep learning approach for discovering kernels tailored to identifying clusters over sample data. Our neural network produces sample embeddings that are motivated by--and are at least as expressive as--spectral clustering. Our training objective, based on the Hilbert Schmidt Information Criterion, can be o…
Unsupervised domain adaptation techniques have been successful for a wide range of problems where supervised labels are limited. The task is to classify an unlabeled `target' dataset by leveraging a labeled `source' dataset that comes from a slightly similar distribution. We propose metric-based adversarial discriminat…
Advances AT with HE to improve model robustness.
Root Laplacian Eigenmaps help in spectral embedding of graphs.
Deep clustering is the first method to handle general audio separation scenarios with multiple sources of the same type and an arbitrary number of sources, performing impressively in speaker-independent speech separation tasks. However, little is known about its effectiveness in other challenging situations such as mus…
Adaptive framework generates challenging adversarial scenarios for autonomous vehicles.
The joint optimization of representation learning and clustering in the embedding space has experienced a breakthrough in recent years. In spite of the advance, clustering with representation learning has been limited to flat-level categories, which often involves cohesive clustering with a focus on instance relations.…
Network embedding has become a hot research topic recently which can provide low-dimensional feature representations for many machine learning applications. Current work focuses on either (1) whether the embedding is designed as an unsupervised learning task by explicitly preserving the structural connectivity in the n…
RECODE uses clustering and embedding to track state visitation counts in RL.
Proposes Group Loss for deep metric learning to improve clustering and image retrieval.
We address the problem of acoustic source separation in a deep learning framework we call "deep clustering." Rather than directly estimating signals or masking functions, we train a deep network to produce spectrogram embeddings that are discriminative for partition labels given in training data. Previous deep network …
Improves hierarchical clustering in Euclidean space using autoencoders.
DETECT clusters mobility behaviors from trajectories using deep learning.
Recently, deep clustering, which is able to perform feature learning that favors clustering tasks via deep neural networks, has achieved remarkable performance in image clustering applications. However, the existing deep clustering algorithms generally need the number of clusters in advance, which is usually unknown in…
Our work improves VAE latent space clustering by enforcing invariant and equivariant learning.
In spite of achieving revolutionary successes in machine learning, deep convolutional neural networks have been recently found to be vulnerable to adversarial attacks and difficult to generalize to novel test images with reasonably large geometric transformations. Inspired by a recent neuroscience discovery revealing t…
Despite significant progress made over the past twenty five years, unconstrained face verification remains a challenging problem. This paper proposes an approach that couples a deep CNN-based approach with a low-dimensional discriminative embedding learned using triplet probability constraints to solve the unconstraine…
The use of deep networks to extract embeddings for speaker recognition has proven successfully. However, such embeddings are susceptible to performance degradation due to the mismatches among the training, enrollment, and test conditions. In this work, we propose an adversarial speaker verification (ASV) scheme to lear…
Detects physiological patterns to hemodynamic stress using unsupervised deep learning.
Adversarial CCA improves representation learning by allowing more flexible priors.
A framework clusters vehicle motion trajectories efficiently.
MetalGAN uses meta-learning and clustering to colorize images with little data.
Private training and synthetic data generation using DP clustering.
NewsNet-SDF uses deep learning to integrate financial news with financial data for better asset pricing.
In this paper, we consider a generic probabilistic discriminative learner from the functional viewpoint and argue that, to make it learn well, it is necessary to constrain its hypothesis space to a set of non-trivial piecewise constant functions. To achieve this goal, we present a scalable unsupervised regularization f…
Survey of graph adversarial learning tasks and their attacks and defenses.
AVDA transfers knowledge from source to target domains using embeddings.
Deep generative architectures provide a way to model not only images but also complex, 3-dimensional objects, such as point clouds. In this work, we present a novel method to obtain meaningful representations of 3D shapes that can be used for challenging tasks including 3D points generation, reconstruction, compression…
DIP-FAT improves adversarial training by diversifying perturbations.