GoT-WAVE improves temporal network alignment by 25% accuracy and 64% speed.
problem Finding conserved network regions in temporal networks.
method Using graphlet-orbit transitions (GoTs) as a dynamic node similarity measure within DynaWAVE.
result GoT-WAVE outperforms DynaWAVE in accuracy and speed on synthetic networks.
Geometric method captures rare topics and temporal alignment in co-author networks.
problem Missing rare topics and smooth temporal alignment in topic modeling.
method Integrates multimodal text and co-author network data using Hellinger distances and Ward's linkage.
result Effective identification of rare topics and visualization of topic drift over time.
Geometric approach improves motion alignment accuracy and efficiency.
problem Temporal alignment of human motion data for various applications.
method Geometric point of view, principal fiber bundle, reparameterization invariant projection, dynamic programming, keyframe correspondences.
result Temporal alignment procedures are more accurate and computationally efficient.
A new method aligns spatial and temporal data, improving on Dynamic Time Warping.
problem Comparing data over space and time, accounting for both spatial and temporal variability.
method Spatio-Temporal Alignments (STA) using regularized optimal transport (OT) and soft-DTW.
result Soft-DTW increases quadratically with time shifts, effectively handling spatio-temporal data.
A new method aligns convolution filters for temporal sequences using Dynamic Time Warp.
problem Improving deep learning models' ability to handle temporal sequence data.
method Integrates Dynamic Time Warp algorithm into 1-D convolution layers for better alignment of input and filter.
result Exceeds or matches standard 1-D convolution layers in time series classification tasks.
MLAT improves kNN performance in time series by learning metrics that align and capture temporal dependencies.
problem Improving kNN performance in time series by learning metrics that effectively handle variations and temporal dependencies.
method MLAT uses a sliding window to augment time series data and applies time-invariant metric learning to derive the most appropriate distance measure.
result MLAT outperforms other existing algorithms in various real-world data sets.
Proposes a new neural network for text-dependent speaker verification.
problem Improves speaker verification by encoding phrase and speaker information.
method Uses differentiable alignment models to produce supervectors from utterances.
result Achieves competitive performance in text-dependent speaker verification tasks.
HawkesLLM models text generation with temporal influence, improving semantic alignment under limited memory.
problem Path-dependent uncertainty in agentic text-simulation systems.
method HawkesLLM framework separates temporal influence modeling from text generation, using a multivariate Hawkes process and a language model.
result HawkesLLM improves late-stage semantic alignment under a compact prompt-memory budget.
The goal of temporal alignment is to establish time correspondence between two sequences, which has many applications in a variety of areas such as speech processing, bioinformatics, computer vision, and computer graphics. In this paper, we propose a novel temporal alignment method called least-squares dynamic time war…
A graph-based model aligns unaligned fMRI data across subjects efficiently.
problem Aligning fMRI data from different subjects with varying responses to stimuli.
method Develops a graph-based model to represent similarities between fMRI samples, regularizes the framework for efficient optimization, and uses kernel-based feature extraction.
result The method outperforms state-of-the-art techniques on both temporally-aligned and unaligned fMRI data.
DACNN improves skeleton-based action recognition and segmentation.
problem Lack of spatial relationships and non-uniform temporal scalings in skeleton-based data.
method Introduces deep-aligned convolutional neural network (DACNN) with new filters trained on local subsequences.
result DACNN achieves competitive performance compared to state-of-the-art models.
TD learning reduces interference, leading to better generalization.
problem Understanding and reducing interference in TD learning for better generalization.
method Analyzing the inner product of gradients as interference, comparing TD and supervised learning, and examining the dynamics of interference and bootstrapping.
result TD learning leads to low-interference, under-generalizing parameters, while supervised learning does the opposite.
Framework improves clinical timeline reconstruction from text and tables.
problem Temporal precision and event timing in clinical narratives and EHRs.
method Retrieval-augmented multimodal alignment framework.
result Consistently improves absolute timestamp accuracy and temporal concordance.
A novel distance measure aligns time series with feature and temporal variability.
problem Measuring similarity between time series with different features and dynamics.
method Learn a latent global transformation and temporal alignment in a joint optimization problem.
result Framework robustly aligns time series across various invariance classes.
New insights into how encoder-decoder networks generate attention matrices.
problem Understanding how encoder-decoder networks use attention matrices.
method Decomposing hidden states into temporal and input-driven components.
result Attention matrices are formed based on task requirements, not architecture type.
The paper tackles temporal coverage bias in financial panel data, proposing a structuring framework to correct for incomplete histories.
problem Incomplete histories of financial instruments lead to biased panel data.
method Formalizes the problem and proposes a coverage-aware structuring framework using structured metadata and an availability matrix.
result The framework reveals substantial distortions in return dynamics and volatility when naive temporal alignment is used.
Develops a model to detect shared communities in non-aligned graphs.
problem Clustering and community detection in non-aligned graphs with heterogeneous populations.
method Joint Stochastic Blockmodel (Joint SBM) and efficient spectral clustering.
result The joint model better estimates communities compared to separate SBMs on individual graphs.
A new framework for averaging spatio-temporal signals using optimal transport and soft alignments.
problem Averaging complex datasets with time and spatial components.
method Inspired by DTW, OT, and UOT, a new loss function is proposed to address shifts in time, space, and population size.
result The proposed loss function can be used to compute spatio-temporal barycenters efficiently.
A new framework improves ASR alignment accuracy via optimal transport.
problem Peaky behavior and alignment inaccuracies in E2E ASR models.
method Differentiable alignment framework based on 1D optimal transport.
result Significant improvement in ASR alignment performance compared to CTC.
RFN models urban mobility demand by separating temporal and spatial variability.
problem Aligning supply and demand in MoD systems for efficient transportation.
method Recurrent flow networks with latent variables and normalizing flows.
result RFN models explicitly disentangle temporal and spatial variability in urban mobility.
Unified model improves multi-task learning by accounting for temporal misalignment.
problem Poor predictive performance and uncertainty quantification due to temporal misalignment in multi-task learning.
method Uses Gaussian processes to model correlations and includes a monotonic warp of the input data to account for temporal misalignment.
result Improves predictive performance and uncertainty quantification in multi-task learning.
A new method for automatically aligning and clustering time series data.
problem Challenges in aligning and clustering time series data, especially without a template signal.
method TROUT (Temporal Registration using Optimal Unitary Transformations) method based on a novel dissimilarity measure.
result TROUT outperforms competitors in clustering time series data.
Meta-learning framework for credit risk assessment of SMEs, aligning financial statement dates with evaluation dates.
problem Temporal misalignment of credit scoring models leading to bias and inconsistent predictions.
method Two-step temporal decomposition: static model for annual PDs, dynamic model for monthly PDs; stacking architecture to aggregate multiple models.
result Framework effectively captures credit risk evolution over time, improving temporal consistency and predictive stability.
A new model for imputing missing values in time series data across domains.
problem Imputing missing values in time series data across domains with domain shifts and high missing rates.
method A diffusion-based imputation model that integrates shared spectral components and domain-specific temporal structures, with cross-domain consistency alignment.
result Our model effectively handles missing values and domain shifts, outperforming existing methods.
The structure of return spillovers is examined by constructing Granger causality networks using daily closing prices of 20 developed markets from 2nd January 2006 to 31st December 2013. The data is properly aligned to take into account non-synchronous trading effects. The study of the resulting networks of over 94 sub-…
NADPEx uses dropout to enable temporally consistent exploration in reinforcement learning.
problem Achieving temporally consistent exploration in reinforcement learning agents.
method Integrates dropout into reinforcement learning policies to ensure temporal consistency.
result NADPEx outperforms naive exploration and parameter noise in tasks with sparse rewards.
Neural TPPs improve EHR modelling efficiency.
problem Challenges in modelling irregularly timed, noisy EHRs.
method Proposed neural network parameterizations of Temporal Point Processes (TPPs) for EHRs.
result Neural TPPs outperform non-TPP models on EHRs.
Two-stream model recognizes affect from audio and video.
problem Human affect recognition in real-world settings.
method Two-stream aural-visual analysis model with separate audio and visual processing.
result Model achieves promising results on Aff-Wild2 database.
Aligns text representations over time for better performance in sequential tasks.
problem Language evolution causes data drift in sequential tasks.
method Sequentially aligns learned representations to combat data drift.
result Sequential alignment outperforms strong baselines on various tasks.
Novel flows generate molecules without post-processing.
problem Generating new molecules efficiently and without post-processing issues.
method Continuous normalizing E(3)-equivariant flows based on node ODEs coupled as a graph PDE.
result Generated samples achieve state-of-the-art performance on QM9 and ZINC250K benchmarks.
Improves text-dependent speaker verification using neural network supervectors and AUC optimization.
problem Enhance performance in text-dependent speaker verification systems.
method Proposes a supervector generation method and AUC optimization for neural networks.
result Improves system performance through novel alignment techniques and AUC optimization.
M2VN forecasts financial volatility by fusing time series data with news embeddings.
problem Forecasting financial volatility with unstructured news data.
method Combines deep neural networks with open-source market features and news embeddings.
result M2VN outperforms existing models in financial volatility forecasting.
A new model aligns sequences using DPMM, outperforming GP-LVM.
problem Aligning high-dimensional time-warped sequences without supervision.
method Dirichlet Process Mixture Model (DPMM) with Gaussian Processes (GPs).
result DPMM achieves competitive results compared to GP-LVM on synthetic and real-world data.
New method generates plausible counterfactuals for time series classification.
problem Generating realistic counterfactuals for time series data.
method Gradient-based optimization with soft-DTW alignment and multi-faceted loss function.
result Our method outperforms existing approaches in temporal realism and distributional alignment.
Using a rolling windows analysis of filtered and aligned stock index returns from 40 countries during the period 2006-2014, we construct Granger causality networks and investigate the ensuing structure of the relationships by studying network properties and fitting spatial probit models. We provide evidence that stock …
FreST Loss decorrelates spatio-temporal dependencies in graph signals.
problem Complex spatio-temporal dependencies in graph-structured signals are not well captured by standard forecasting models.
method FreST Loss extends supervision to the joint spatio-temporal spectrum using Joint Fourier Transform (JFT).
result FreST Loss reduces estimation bias and improves forecasting accuracy on real-world datasets.
This paper improves ASR performance by aligning frames more accurately.
problem Disagreement between teacher-student models in frame-level alignment.
method Introduces self-knowledge distillation (SKD) to guide frame-level alignment.
result Improves both resource efficiency and performance in ASR.
TeLeS improves ASR confidence estimation by considering temporal alignment and lexical errors.
problem Inaccurate confidence scores from E2E ASR models, especially for overconfident predictions.
method Proposes TeLeS, a novel confidence score that considers temporal alignment and lexical errors, and uses shrinkage loss to handle data imbalance.
result TeLeS generalizes well across different languages and ASR models, leading to significant WER reduction.
Word evolution refers to the changing meanings and associations of words throughout time, as a byproduct of human language evolution. By studying word evolution, we can infer social trends and language constructs over different periods of human history. However, traditional techniques such as word representation learni…
TTW aligns time-series faster and more accurately than existing methods.
problem Efficiently aligning multiple time-series signals with varying lengths.
method TTW uses a sinc convolutional kernel and gradient-based optimization for linear time and sequence complexity.
result TTW outperforms existing methods in time-series averaging and classification tasks.
CATS adapts multivariate time series models by addressing correlation shift.
problem Correlation differences across domains in multivariate time series data.
method CATS introduces correlation shift to measure domain differences, and uses a graph attention module and temporal convolution to align target correlations with source correlations.
result CATS increases over 10% average accuracy compared to vanilla Transformer-based models with minimal additional parameters.
We study alignment in linear neural networks and its relation to gradient descent.
problem Understanding alignment in linear neural networks and its impact on training.
method Defined alignment for fully connected networks, analyzed alignment under gradient descent, and compared gradient descent to projected gradient descent for layer-constrained networks.
result Gradient descent can converge linearly to a global minimum when alignment is invariant, and alignment is impossible with large datasets in layer-constrained networks.
Method learns node embeddings over time for graph prediction tasks.
problem Predicting links and classifying nodes in evolving graphs.
method Proposes a joint loss function for temporal node embedding.
result Improves performance on various temporal graph tasks.
A function that optimally aligns a timelike vector field with its gradients
problem Finding a time function that aligns a timelike vector field with its gradients
method Introducing a functional that penalizes null gradients and minimizes misalignment
result Proving the existence of a unique alignment time function under suitable conditions
Unified deep architecture for domain-invariant network alignment.
problem Eliminate domain representation bias in network alignment.
method DANA (Domain Adversarial Network Alignment) using graph convolutional networks and semi-supervised learning.
result Achieves state-of-the-art alignment results on real-world social networks.
The study explains how neural networks align their kernels to target functions during training.
problem Understanding how neural networks align their kernels to target functions during training.
method Theoretical analysis of kernel evolution in toy models and deep networks.
result Kernel alignment naturally emerges during training to accelerate convergence and improve generalization.
Enhances thematic investing with stock embeddings from textual data.
problem Challenges in constructing thematic portfolios due to overlapping sector boundaries and evolving market dynamics.
method Introduces THEME, a framework that fine-tunes embeddings using hierarchical contrastive learning, aligning themes and stocks using their hierarchical relationship and incorporating stock returns.
result Theme-aligned portfolios demonstrate compelling performance, significantly outperforming large language models in thematic asset retrieval.
DFA trains deep networks by aligning weights then memorizing data.
problem Understanding why DFA works for some networks but not others.
method Two-step learning process: alignment followed by memorization.
result DFA aligns weights to maximize gradient alignment, breaking degeneracy.