Research
On-device research index

arXiv research

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.

169,181 papers · 148 categories

Trend · papers per month

25.0%50.0%75.0%100.0% · Jun 199319922001200920182026
48 results for temporal relation extraction

This study uses partially annotated data to improve TempRel extraction.

problem Lack of fully annotated data for TempRel extraction makes the task labor-intensive and limited in coverage.
method Utilizes partially annotated data (P) for TempRel extraction, even when annotations are missing.
result Partially annotated data (P) can still be a useful supervision signal for TempRel extraction within a constrained learning framework.

Model predicts spatial-temporal series with latent dynamical component.

problem Forecasting and discovering spatial-temporal relations in series.
method Recurrent neural network with latent dynamical component and various prior hypotheses.
result Model outperforms baselines in various forecasting tasks.

StrGNN detects anomalies in dynamic graphs by analyzing subgraphs and temporal features.

problem Detecting anomalies in dynamic graphs with structural changes.
method StrGNN is an end-to-end model that uses structural subgraphs and temporal features for anomaly detection.
result StrGNN effectively detects anomalies in dynamic graphs, as shown by extensive experiments.

FIBS extracts relevant features from IBTSs for classification.

problem Classifying interval-based temporal sequences (IBTSs) using common algorithms is challenging.
method FIBS extracts features from IBTSs based on relative frequency and temporal relations, incorporating a filter-based selection strategy to avoid irrelevant features.
result FIBS effectively represents IBTSs for classification algorithms, providing similar or better accuracy compared to state-of-the-art competitors.

This paper tackles spatio-temporal information preservation in machine learning.

problem Conventional machine learning assumes orthogonal data attributes, disrupting spatio-temporal information.
method Shift-invariant k-means, convolutional dictionary learning, and spatio-temporal hypercomplex encoding schemes are proposed.
result Gabor feature extraction outperforms convolutional dictionary learning in spatio-temporal information preservation.

Bayesian framework extracts features from high-dimensional spatio-temporal data.

problem Sparse structure and spatio-temporal dependence in high-dimensional data.
method Develops a Bayesian feature-extraction framework using Gaussian and Diffused-gamma priors, employing Bregman divergence likelihood and MCMC for posterior computation.
result Improves recovery of sparse features and enhances interpretability in the presence of spatio-temporal dependence.

Enhances SNNs for spatio-temporal feature extraction.

problem Insufficient temporal dependencies in existing SNN synaptic structures.
method Integrates temporal convolution and attention mechanisms into synaptic connections.
result Improves SNN performance on classification tasks.

A new framework combines CNN and GRU for better structural damage detection.

problem Improving damage detection in structural engineering using machine learning.
method Hierarchical CNN and Gated Recurrent Unit (GRU) framework to model spatial and temporal relations.
result The proposed HCG framework significantly outperforms existing methods for structural damage detection.

Gradient-based method extracts slow features from high-dimensional data.

problem Extracting meaningful low-dimensional features from high-dimensional, temporally varying data.
method Power Slow Feature Analysis (PowerSFA) using gradient-based training of differentiable architectures.
result PowerSFA effectively extracts meaningful low-dimensional features in various data types.

MTHetGNN models complex relations in multivariate time series forecasting.

problem Complex relations among variables in multivariate time series forecasting.
method Designs a relation embedding module and a temporal embedding module, using graph neural networks and CNNs.
result Achieves state-of-the-art results in multivariate time series forecasting.

System detects relevant financial news and predictions from unstructured text.

problem Manual extraction of relevant financial information from news is cumbersome and error-prone.
method Topic modeling with LDA, co-reference resolution, multi-paragraph segmentation, and temporal analysis.
result ROUGE-L values for relevant text and predictions/forecasts were 0.662 and 0.982, respectively.

Sentinel improves time series forecasting by modeling both temporal and channel dependencies.

problem Limited effectiveness of existing transformer-based architectures in multivariate time-series forecasting.
method Proposes Sentinel, a full transformer-based architecture with multi-patch attention mechanism.
result Sentinel achieves better or comparable performance compared to state-of-the-art approaches.

SWoTTeD discovers hidden temporal patterns in EHR data.

problem Complex temporal patterns in EHR data.
method Sliding Window for Temporal Tensor Decomposition (SWoTTeD) with constraints and regularizations.
result SWoTTeD achieves at least as accurate reconstruction as state-of-the-art models and extracts meaningful temporal phenotypes.

Paper proposes a neural network to improve traffic flow forecasting.

problem Forecasting future traffic flow distribution in an area.
method Position-aware convolutional neural network integrating data features and position information.
result Our approach outperforms previous methods even with fewer data sources.

A new model learns demand patterns from data, reducing complexity and improving accuracy.

problem Forecasting short-term demand from spatiotemporal data with complex patterns.
method Temporal-Guided Network (TGNet) using graph networks and temporal-guided embedding.
result TGNet achieves competitive performance with fewer parameters compared to state-of-the-art models.

HRHN predicts time series by integrating exogenous data and temporal dynamics.

problem Challenges in predicting time series with exogenous data and temporal dynamics.
method Hierarchical attention-based Recurrent Highway Network (HRHN) that considers interactions among exogenous variables and temporal dynamics.
result HRHN outperforms state-of-the-art methods in time series prediction, especially in capturing sudden changes and oscillations.

Paper tackles class-incremental time series classification with dual-stream feature extraction.

problem Class-incremental continual learning for multivariate time series data.
method Dual-stream feature extraction pipeline combining deep temporal embedding features and statistical features.
result Competitive average accuracy across multiple datasets with low forgetting rates.

TASTE combines static and temporal data for phenotyping EHRs.

problem Phenotyping EHRs with both static and temporal data.
method Jointly models static and temporal tensors using PARAFAC2 and non-negative matrix factorization, alternatingly solving sub-problems.
result TASTE outperforms existing methods in speed and clinical meaningfulness of phenotypes.

Deep learning predicts real-time parking occupancy using multiple data sources.

problem Predicting real-time parking occupancy in spatio-temporal networks.
method Graph-Convolutional Neural Networks (GCNN) for spatial relations, Recurrent Neural Networks (RNN) with Long-Short Term Memory (LSTM) for temporal features, multiple data sources.
result The model outperforms other methods with an average testing MAPE of 10.6%.

A new model improves relation extraction accuracy through relation-gated adversarial learning.

problem Relation extraction from sentences is challenging due to expensive human annotation and noisy distant supervision.
method Proposes relation-gated adversarial learning for relation extraction, extending domain adaptation methods.
result The model outperforms previous domain adaptation methods and improves accuracy of distance supervised relation extraction.

Paper introduces an unsupervised tensor-based anomaly detection method for spatiotemporal data.

problem Challenges in detecting anomalies in spatiotemporal data, especially in urban traffic monitoring and medical imaging.
method Formulates anomaly detection as a regularized robust low-rank + sparse tensor decomposition, incorporating spatiotemporal smoothness and local dependencies.
result Demonstrates improved anomaly detection performance on both synthetic and real data.

The paper tackles energy disaggregation by improving dictionary learning with deep neural models.

problem Decomposing electricity signals of a whole home into its operating devices.
method Proposes a novel optimization program that learns both the dictionary and sparse coefficients using a deep neural model (LSTM-AE) to capture temporal energy signals.
result Significant improvement in disaggregation accuracy and F-score metrics compared to state-of-the-art methods.

KEDformer improves long-term time series forecasting with seasonal-trend decomposition.

problem Accurate long-term predictions in energy, finance, and meteorology.
method Knowledge extraction-driven framework integrating seasonal-trend decomposition.
result KEDformer enhances model's ability to capture short-term and long-term patterns.

CAWs learn temporal network dynamics without node identities or edge attributes.

problem Learning temporal network dynamics without node identities or edge attributes.
method Causal Anonymous Walks (CAWs) using temporal random walks and hitting counts.
result CAW-N outperforms previous methods in predicting links over 6 real temporal networks.

Algorithm learns causal structures from time-series data, reducing tests for temporal vs. contemporaneous relations.

problem Learning causal structures from time-series data with latent confounders.
method Constraint-based algorithm that refines a causal graph by learning temporal relations first, then contemporaneous ones.
result Reduces the number of statistical tests and improves accuracy for synthetic and real-world data.

New model extracts shared brain activity patterns from fMRI data.

problem Challenges in aggregating multi-subject fMRI data due to variability.
method Shared Gaussian Process Factor Analysis (S-GPFA) incorporating temporal information.
result Model reveals ground truth latent structures and replicates experimental performance.

IETNet identifies important channels for MVTS classification.

problem Multivariate time series classification with blackbox deep networks.
method End-to-end network combining temporal feature extraction, variable selection, and interaction.
result IETNet improves model accuracy and reduces overfitting by identifying and removing non-predictive variables.

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.

CURE extracts relations without supervision by clustering similar entity pairs.

problem Extracting relations unsupervised without considering sentence correlations.
method CURE uses Encoder-Decoder architecture for self-supervised learning and clustering similar relations.
result CURE outperforms state-of-the-art models on NYT and UNPC datasets.

Model predicts treatment initiation from clinical data using patient-clinician relations.

problem Predicting treatment initiation from clinical time series data considering patient-clinician relations.
method Graph-Augmented Time-Sensitive Model using top eigenvectors of graph Laplacian.
result Relational similarity improves prediction over baselines, e.g., 5% improvement in AUPRC.