Real-time pruning during training reduces network size and training time.
problem Efficiently reducing neural network size without sacrificing accuracy.
method Activation density-based pruning during training.
result Up to 200x reduction in parameters and 60x reduction in inference compute operations.
Dynamic networks are a general language for describing time-evolving complex systems, and discrete time network models provide an emerging statistical technique for various applications. It is a fundamental research question to detect the community structure in time-evolving networks. However, due to significant comput…
New neural networks with variable time constants for better time-series prediction.
problem Improving neural network performance in time-series prediction.
method Constructing networks of linear dynamical systems modulated by nonlinear gates, using numerical differential equation solvers.
result Liquid Time-Constant Networks (LTCs) yield superior performance on time-series prediction tasks.
In this work, we develop a novel framework to measure the similarity between dynamic financial networks, i.e., time-varying financial networks. Particularly, we explore whether the proposed similarity measure can be employed to understand the structural evolution of the financial networks with time. For a set of time-v…
Survey of data augmentation techniques for time series classification with neural networks.
problem Small datasets in time series recognition.
method Four families of data augmentation: transformation-based, pattern mixing, generative models, and decomposition methods.
result Empirical evaluation of 12 data augmentation methods on 128 datasets.
Wavelet Networks learn from raw time-series data, outperforming conventional CNNs.
problem Learning from raw time-series data efficiently and effectively.
method Constructing scale-translation equivariant neural networks based on wavelet symmetries.
result Wavelet Networks outperform conventional CNNs on raw waveforms and spectrograms.
Stochastic networks are a plausible representation of the relational information among entities in dynamic systems such as living cells or social communities. While there is a rich literature in estimating a static or temporally invariant network from observation data, little has been done toward estimating time-varyin…
VSDN models sporadic time series with neural SDEs.
problem Modeling irregular and sparse time series data.
method Variational Bayesian method and neural SDEs.
result VSDNs outperform state-of-the-art models in prediction and interpolation.
A new method improves recommendation accuracy by learning from multiple networks and time-dependent user preferences.
problem Incomplete user profiles and dynamic user preferences degrade recommender quality.
method A cross-network time-aware recommender that learns from multiple source networks and develops current user models.
result The proposed solution achieves superior performance in accuracy, novelty, and diversity.
Proposes a neural network for handling multi-sensor time series with varying input dimensions.
problem Handling multi-sensor time series with varying input dimensions.
method Graph neural network conditioning vectors for zero-shot transfer learning.
result Better generalization in activity recognition and equipment prognostics datasets.
This paper advocates Riemannian multi-manifold modeling in the context of network-wide non-stationary time-series analysis. Time-series data, collected sequentially over time and across a network, yield features which are viewed as points in or close to a union of multiple submanifolds of a Riemannian manifold, and dis…
The paper analyzes a neural network two-sample test using kernel analysis.
problem Determining if two datasets come from the same distribution.
method Time-analysis on a neural tangent kernel (NTK) two-sample test, extending to realistic neural network dynamics.
result Training times needed to detect deviations are well-separated in null and alternative hypothesis scenarios.
Deep neural networks show great potential as solutions to many sensing application problems, but their excessive resource demand slows down execution time, pausing a serious impediment to deployment on low-end devices. To address this challenge, recent literature focused on compressing neural network size to improve pe…
The paper maps time-series onto networks to reveal hidden joint information.
problem Extract hidden joint information from uncorrelated time-series.
method Discretize time-series amplitudes, map onto networks, measure coupling deviations, and compare with Gaussian distributions.
result Markets may possess joint patterns even if initially uncorrelated.
ForecastNet uses a time-variant deep feed-forward neural network for better multi-step-ahead time series forecasting.
problem Time-invariant architectures limit multi-step-ahead forecasting.
method ForecastNet employs a deep feed-forward architecture with time-variant parameters and interleaved outputs.
result ForecastNet outperforms other models on multi-step-ahead time series forecasting tasks.
Guided warping augments time series data by aligning features with a teacher.
problem Small time series datasets limit neural network performance.
method Guided warping with a discriminative teacher to augment data deterministically.
result Significant improvement in performance on various time series datasets.
Time series are series of values ordered by time. This kind of data can be found in many real world settings. Classifying time series is a difficult task and an active area of research. This paper investigates the use of transfer learning in Deep Neural Networks and a 2D representation of time series known as Recurrenc…
New algorithm learns random neural networks efficiently.
problem Learning random constant-depth neural networks efficiently.
method Presented a PTAS (Polynomial-Time Approximation Scheme) for learning random Xavier networks of fixed depth.
result For any fixed ε and depth i, there is a poly-time algorithm that learns random Xavier networks up to an additive error of ε.
Study of deep neural networks using finite-time Lyapunov exponents.
problem Understanding the geometric structures in input space formed by deep neural networks.
method Analogy with dynamical systems, computing finite-time Lyapunov exponents.
result Ridges of large positive exponents divide input space into regions associated with different classes.
New method embeds correlation networks to reveal underlying time series patterns.
problem Analyzing correlation networks derived from time series data.
method Spectral embedding of noisy correlation networks, leveraging Fourier basis elements.
result Spectral embedding recovers true vertex-level latent representations under suitable assumptions.
This paper proposes a probabilistic neural network developed on the basis of time-series discriminant component analysis (TSDCA) that can be used to classify high-dimensional time-series patterns. TSDCA involves the compression of high-dimensional time series into a lower-dimensional space using a set of orthogonal tra…
KTVGL models tensor time series data for interpretable dynamic network estimation.
problem Estimating time-varying dependencies in multi-mode tensor time series data.
method Kronecker Time-Varying Graphical Lasso (KTVGL) for mode-specific dynamic network estimation.
result KTVGL produces interpretable modeling results and higher edge estimation accuracy than existing methods.
Hidden Markov Neural Networks balance adaptation and forgetting in time-series data.
problem Balancing adaptation to new data and forgetting outdated information in time-series forecasting.
method Modeling weights as hidden states of a Hidden Markov model, using a filtering algorithm for learning a variational approximation of the posterior distribution over weights, and employing sequential Bayes by Backprop with variational DropConnect for regularization.
result Achieves strong predictive performance and effective uncertainty quantification on various tasks.
In many fields observations are performed irregularly along time, due to either measurement limitations or lack of a constant immanent rate. While discrete-time Markov models (as Dynamic Bayesian Networks) introduce either inefficient computation or an information loss to reasoning about such processes, continuous-time…
Time series forecasting is difficult. It is difficult even for recurrent neural networks with their inherent ability to learn sequentiality. This article presents a recurrent neural network based time series forecasting framework covering feature engineering, feature importances, point and interval predictions, and for…
In many application settings involving networks, such as messages between users of an on-line social network or transactions between traders in financial markets, the observed data consist of timestamped relational events, which form a continuous-time network. We propose the Community Hawkes Independent Pairs (CHIP) ge…
Paper tackles hyper-gradient estimation in decentralized FL over time-varying networks.
problem Excessive communication costs and inability to use robust networks.
method Introduces an optimality condition and uses Push-Sum for averaging model parameters and gradients over time-varying directed networks.
result Derives a hyper-gradient estimator that operates over time-varying directed networks and converges to the true hyper-gradient.
This study uses persistent homology to analyze complex transitional networks from time series data.
problem Lack of effective tools to summarize complex topology in transitional networks.
method Persistent homology from topological data analysis applied to coarse-grained state-space networks (CGSSN).
result CGSSN improves dynamic state detection and noise robustness compared to other methods.
DAMNETS generates complex network dynamics models.
problem Generating flexible and scalable models for network time series is challenging.
method Deep autoregressive model for Markovian network time series.
result DAMNETS outperforms other methods in sample quality.
New method uses randomized sparse neural networks to solve time-dependent PDEs more accurately and efficiently.
problem Numerical challenges in training neural networks sequentially in time to solve time-dependent PDEs.
method Introduces Neural Galerkin schemes that update randomized sparse subsets of network parameters at each time step.
result Up to two orders of magnitude more accurate and two orders of magnitude faster than dense update schemes.
Oddnet detects anomalies in dynamic networks using time series methods.
problem Detecting anomalies in temporal networks (e.g., transport, social networks).
method Feature-based network anomaly detection using time series methods.
result Demonstrated effectiveness on synthetic and real-world datasets.
LAVARNET predicts multivariate time series by estimating causal variable relationships.
problem Forecasting multivariate time series requires understanding causal interrelationships among variables.
method LAVARNET is a neural network architecture that estimates causal effects and predicts future values.
result LAVARNET outperforms other models on various real-world data sets.
The paper analyzes deep neural networks using control theory to set a time limit for their convergence.
problem Understanding the finite-time convergence of deep neural networks.
method Lyapunov based analysis of the loss function, control theory framework, finite-time control of non-linear systems.
result A priori guarantees of finite-time convergence for deep neural networks are provided.
Finite singular times for symmetric network curvature flow.
problem Formation of singularities in network curvature flow.
method Curvature flow of networks with symmetric initial data and two triple junctions.
result The set of singular times is finite.
Generative Adversarial Graph Neural Network (Sig-Graph GAN) models financial time series data.
problem Challenges in generating synthetic data for non-stationary financial time series.
method Integrates time-series signature, LSTM, and GNNs with visibility graph algorithm.
result Sig-Graph GAN outperforms baseline methods in replicating time series data distributions.
Estimates time-varying network connections using multi-stage smoothing.
problem Estimating edge probabilities of time-varying networks.
method Multi-stage smoothing: temporal local smoothing followed by node-domain smoothing.
result Captures both smooth temporal evolution and structural patterns in connectivity.
Stacked LSTM networks improve traffic volume forecasting.
problem Accurate traffic volume prediction for better planning.
method Applying stacked Long Short-Term Memory (LSTM) networks for time series forecasting.
result Stacked LSTM networks enhance the accuracy of traffic volume predictions.
In this paper, we propose a technique for time series clustering using community detection in complex networks. Firstly, we present a method to transform a set of time series into a network using different distance functions, where each time series is represented by a vertex and the most similar ones are connected. The…
Proposes a new algorithm for learning continuous-time Bayesian network structures.
problem Lack of constraint-based algorithms for continuous-time Bayesian networks.
method Develops a constraint-based algorithm using statistical tests for conditional independence.
result The proposed algorithm is more accurate with variables having more than two values.
In this paper we use a time-evolving graph which consists of a sequence of graph snapshots over time to model many real-world networks. We study the path classification problem in a time-evolving graph, which has many applications in real-world scenarios, for example, predicting path failure in a telecommunication netw…
We show that the standard stochastic gradient decent (SGD) algorithm is guaranteed to learn, in polynomial time, a function that is competitive with the best function in the conjugate kernel space of the network, as defined in Daniely, Frostig and Singer. The result holds for log-depth networks from a rich family of ar…
Network structures in various backgrounds play important roles in social, technological, and biological systems. However, the observable network structures in real cases are often incomplete or unavailable due to measurement errors or private protection issues. Therefore, inferring the complete network structure is use…
Method selects the best deep learner for time-series prediction using Bayesian networks.
problem Selecting the most effective deep learning model for time-series prediction.
method Bayesian network selects deep learners based on input variables and cluster training data.
result Threshold value determines which deep learners predict time-series data robustly.
TAnoGan detects anomalies in time series data using GANs.
problem Anomaly detection in time series data.
method Generative Adversarial Networks (GAN) for unsupervised anomaly detection.
result TAnoGan outperforms traditional and neural network models in anomaly detection.
Time-varying neural network improves stock return prediction.
problem Predicting stock returns in a time-varying market.
method Online early stopping algorithm for neural network training.
result The proposed algorithm outperforms current methods in predicting monthly U.S. stock returns.
Improved anomaly detection in time series data using kervolutional neural networks.
problem Anomaly detection in time series data.
method Mixed kervolutional and convolutional layers in a temporal auto-encoder.
result The mixed model detects anomalies more sensitively in time series data.
Theoretical analysis of deep neural networks for time series data.
problem Theoretical development for deep neural networks on temporally dependent observations is lacking.
method Established non-asymptotic bounds for prediction error of deep neural networks under mixing-type assumptions.
result Deep neural networks can model non-linear time series data with additional logarithmic factors due to dependence.
The paper optimizes sensor selection for network time series data.
problem Optimizing sensor selection for network time series data with minimal error.
method Data-driven strategies to turn off sensors or select a sampling set of nodes.
result Proposes and compares various data-driven strategies for sensor selection.