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.
CoDA Nets improve interpretability in neural networks.
We study alignment in linear neural networks and its relation to gradient descent.
DFA trains deep networks by aligning weights then memorizing data.
In this paper, we develop a novel Backtrackless Aligned-Spatial Graph Convolutional Network (BASGCN) model to learn effective features for graph classification. Our idea is to transform arbitrary-sized graphs into fixed-sized backtrackless aligned grid structures and define a new spatial graph convolution operation ass…
Where dealing with temporal sequences it is fair to assume that the same kind of deformations that motivated the development of the Dynamic Time Warp algorithm could be relevant also in the calculation of the dot product ("convolution") in a 1-D convolution layer. In this work a method is proposed for aligning the conv…
We present an efficient approach for leveraging the knowledge from multiple modalities in training unimodal 3D convolutional neural networks (3D-CNNs) for the task of dynamic hand gesture recognition. Instead of explicitly combining multimodal information, which is commonplace in many state-of-the-art methods, we propo…
Guided warping augments time series data by aligning features with a teacher.
G-CREWE efficiently aligns large networks using node embeddings and compression.
In this paper, we develop a new aligned vertex convolutional network model to learn multi-scale local-level vertex features for graph classification. Our idea is to transform the graphs of arbitrary sizes into fixed-sized aligned vertex grid structures, and define a new vertex convolution operation by adopting a set of…
Time-continuous dimensional descriptions of emotions (e.g., arousal, valence) allow researchers to characterize short-time changes and to capture long-term trends in emotion expression. However, continuous emotion labels are generally not synchronized with the input speech signal due to delays caused by reaction-time, …
Online news recommender systems aim to address the information explosion of news and make personalized recommendation for users. In general, news language is highly condensed, full of knowledge entities and common sense. However, existing methods are unaware of such external knowledge and cannot fully discover latent k…
Network alignment is a critical task to a wide variety of fields. Many existing works leverage on representation learning to accomplish this task without eliminating domain representation bias induced by domain-dependent features, which yield inferior alignment performance. This paper proposes a unified deep architectu…
Convolutional neural networks (CNNs) are deep learning frameworks which are well-known for their notable performance in classification tasks. Hence, many skeleton-based action recognition and segmentation (SBARS) algorithms benefit from them in their designs. However, a shortcoming of such applications is the general l…
This paper proposes a new Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. Unlike state-of-the-art Graph Convolutional Neural Network (GCNN) models, the proposed QSGCNN model incorporates the process of identifying transit…
Graph Neural Networks align with dynamic programming, improving algorithmic reasoning.
The study explains how neural networks align their kernels to target functions during training.
We embed KKT points in neural networks of different sizes.
The paper improves DFA for CNN and RNN training to match BP accuracy.
Ongoing studies have identified similarities between neural representations in biological networks and in deep artificial neural networks. This has led to renewed interest in developing analogies between the backpropagation learning algorithm used to train artificial networks and the synaptic plasticity rules operative…
Paper proposes KE-GCN for better graph embedding.
This paper studies nonlinear representation learning dynamics beyond the NTK regime.
For a standard convolutional neural network, optimizing over the input pixels to maximize the score of some target class will generally produce a grainy-looking version of the original image. However, Santurkar et al. (2019) demonstrated that for adversarially-trained neural networks, this optimization produces images …
Recently, researchers have started applying convolutional neural networks (CNNs) with one-dimensional convolutions to clinical tasks involving time-series data. This is due, in part, to their computational efficiency, relative to recurrent neural networks and their ability to efficiently exploit certain temporal invari…
Recent advances in deep neural networks (DNNs) owe their success to training algorithms that use backpropagation and gradient-descent. Backpropagation, while highly effective on von Neumann architectures, becomes inefficient when scaling to large networks. Commonly referred to as the weight transport problem, each neur…
The backpropagation algorithm has long been the canonical training method for neural networks. Modern paradigms are implicitly optimized for it, and numerous guidelines exist to ensure its proper use. Recently, synthetic gradients methods -where the error gradient is only roughly approximated - have garnered interest. …
Training avoids edge of stability by aligning Jacobian matrices.
There were many algorithms to substitute the back-propagation (BP) in the deep neural network (DNN) training. However, they could not become popular because their training accuracy and the computational efficiency were worse than BP. One of them was direct feedback alignment (DFA), but it showed low training performanc…
NTW aligns multiple time-series data efficiently using neural networks.
SGD updates align with a low-rank subspace but do not lead to further loss reduction.
Graph neural network improves SOH estimation of lithium-ion batteries.
SGD's training dynamics align with Hessian and gradient spectra in high-dimensional classification tasks.
NTK-SAP improves neural network pruning by aligning training dynamics.
We show that the classification performance of graph convolutional networks (GCNs) is related to the alignment between features, graph, and ground truth, which we quantify using a subspace alignment measure (SAM) corresponding to the Frobenius norm of the matrix of pairwise chordal distances between three subspaces ass…
CTGCN learns dynamic graph embeddings preserving both local and global graph structure.
GrokAlign aligns Jacobians to accelerate grokking in deep networks.
Early alignment in neural networks leads to sparse representations but hinders convergence.
Coordinate-independent convolutions on manifolds avoid reference frame ambiguity.
Global pairwise network alignment (GPNA) aims to find a one-to-one node mapping between two networks that identifies conserved network regions. GPNA algorithms optimize node conservation (NC) and edge conservation (EC). NC quantifies topological similarity between nodes. Graphlet-based degree vectors (GDVs) are a state…
A new method to rescale ReLU neural networks based on path-lifting.
Deep learning improves chaotic dynamics filtering without ensemble.
TK-GCN forecasts spatiotemporal dynamics using Koopman-enhanced graph convolutional networks.
Neural networks learn patterns in random data, improving downstream performance.
Representational similarity analysis (RSA) has been shown to be an effective framework to characterize brain-activity profiles and deep neural network activations as representational geometry by computing the pairwise distances of the response patterns as a representational dissimilarity matrix (RDM). However, how to p…
CRITS improves time series classification with interpretable local explanations.
Photonic co-processor speeds up training of large neural networks.
Deep learning for object classification relies heavily on convolutional models. While effective, CNNs are rarely interpretable after the fact. An attention mechanism can be used to highlight the area of the image that the model focuses on thus offering a narrow view into the mechanism of classification. We expand on th…
Proposes dynamic channel pruning during neural network training.
In this paper, we propose a new differentiable neural network alignment mechanism for text-dependent speaker verification which uses alignment models to produce a supervector representation of an utterance. Unlike previous works with similar approaches, we do not extract the embedding of an utterance from the mean redu…