DGRCL integrates dynamic and static graph relations for financial market prediction.
problem Capturing the evolving nature of stock markets while considering both temporal changes and static relational structures.
method Dynamic Graph Representation with Contrastive Learning (DGRCL) framework, including Embedding Enhancement (EE) and Contrastive Constrained Training (CCT) modules.
result DGRCL significantly outperforms state-of-the-art TGL baselines on NASDAQ and NYSE datasets.
SoftCLT improves time series representation learning by soft contrastive loss.
problem Ignoring inherent correlations in time series leads to poor representation quality.
method SoftCLT introduces instance-wise and temporal contrastive loss with soft assignments.
result SoftCLT consistently improves various downstream tasks in time series learning.
FactorGCL uses hypergraph learning to predict stock returns by mining hidden factors.
problem Mining effective factors in data-driven models is challenging due to low signal-to-noise ratio in market data.
method FactorGCL employs a hypergraph structure and temporal residual contrastive learning to extract hidden factors.
result FactorGCL outperforms existing methods and mines effective hidden factors for predicting stock returns.
ST-MTM models complex time series by decomposing and masking seasonal and trend components.
problem Forecasting complex time series with intricate temporal variations.
method Seasonal-Trend Decomposition with Masking and Contrastive Learning.
result ST-MTM achieves superior forecasting performance compared to existing methods.
TNC learns time series representations by leveraging temporal neighborhoods.
problem Complex, unlabeled time series data.
method Temporal Neighborhood Coding (TNC) with a debiased contrastive objective.
result TNC outperforms other unsupervised methods in time series clustering and classification.
New unsupervised deep learning method improves temporal resolution in tMRA.
problem Limited temporal resolution in tMRA due to fixed view-sharing scheme.
method Optimal transport driven cycle-consistent generative adversarial network (cycleGAN) without fully sampled k-space reference data.
result Can generate high quality reconstructions at various temporal resolutions.
SSL framework identifies non-linear systems without labeled data.
problem System identification in non-linear environments without labeled data.
method Dynamics contrastive learning framework.
result SSL can identify non-linear dynamics in latent space.
Novel bio-inspired masking for robust speech emotion recognition.
problem Noise degradation in speech emotion recognition.
method Cochlear cepstrogram-based contrastive learning with temporal and frequency masking.
result Improved speech emotion recognition performance on K-EmoCon benchmark.
Paper proposes a new method for learning compact representations of sequential data.
problem Learning compact representations of sequential data capturing spatio-temporal cues.
method Contrastive representation learning via adversarial optimal transport on the Grassmann manifold.
result Empirical results show competitive performance in human action recognition.
Proposes a novel method for generating hard negatives near time series data boundaries.
problem Challenges in generating effective negative samples for time series anomaly detection.
method Reconstruction-driven boundary negative generation framework using reinforcement learning.
result Improves anomaly representation learning and achieves competitive detection performance.
Two autoencoding models learn latent traffic scene representations.
problem Learning latent representations of traffic scenarios.
method CNN and RNN models for spatio-temporal and temporal data, incorporating permutation invariance.
result Latent scenario embeddings can be used for clustering and similarity retrieval.
New unsupervised learning task improves RL performance.
problem Reward-driven feature learning limitations in RL from images.
method Introduce Augmented Temporal Contrast (ATC) for unsupervised learning of image representations.
result Training encoders using ATC matches or outperforms end-to-end RL in most environments.
Capsule networks excel in understanding spatial relationships in 2D data for vision related tasks. Even though they are not designed to capture 1D temporal relationships, with TimeCaps we demonstrate that given the ability, capsule networks excel in understanding temporal relationships. To this end, we generate capsule…
Interpretability has arisen as a key desideratum of machine learning models alongside performance. Approaches so far have been primarily concerned with fixed dimensional inputs emphasizing feature relevance or selection. In contrast, we focus on temporal modeling and the problem of tailoring the predictor, functionally…
A simple baseline outperforms deep learning methods in transportation forecasting.
problem The importance of stationarity and recurrent patterns in transportation data.
method A naive baseline based on average weekly patterns and linear regression.
result The baseline method achieves comparable or better results than state-of-the-art deep learning approaches.
CNPs improve function approximation by contrastive learning.
problem Learning from non-i.i.d function instantiations in high-dimensional, noisy spaces.
method CNPs with TCL and FCL contrastive branches for better function approximation.
result CNPs outperform other variants in function distribution reconstruction and parameter identification.
TCFimt forecasts causal effects of multiple interventions from individual data.
problem Estimating causal effects of temporal multi-interventions from individual data.
method TCFimt uses adversarial tasks in seq2seq framework to alleviate bias and contrastive learning to decouple effects.
result TCFimt outperforms state-of-the-art methods in predicting future outcomes and choosing optimal treatments.
The paper shows how to answer future and past questions from high-dimensional time series data.
problem Challenges in answering probabilistic inference questions from high-dimensional time series data.
method Temporal contrastive learning to learn Gaussian representations that enable compact closed-form solutions.
result Representations learned via contrastive learning follow a Gauss-Markov chain, enabling efficient inference and planning.
New TD method stabilizes average-reward learning.
problem Stability issues in average-reward TD learning.
method Implicit fixed point update for average-reward TD(λ). result Improved numerical stability and broader step-size range.
The paper introduces a method to learn Markov state abstractions for reinforcement learning.
problem Learning Markov state representations in complex environments.
method The paper introduces a novel set of conditions and a training procedure combining inverse model estimation and temporal contrastive learning.
result The approach learns representations that capture the underlying structure of the domain and improve sample efficiency.
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.
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.
Nonlinear independent component analysis (ICA) provides an appealing framework for unsupervised feature learning, but the models proposed so far are not identifiable. Here, we first propose a new intuitive principle of unsupervised deep learning from time series which uses the nonstationary structure of the data. Our l…
Spiking neural networks (SNNs) could play a key role in unsupervised machine learning applications, by virtue of strengths related to learning from the fine temporal structure of event-based signals. However, some spike-timing-related strengths of SNNs are hindered by the sensitivity of spike-timing-dependent plasticit…
Temporal networks representing a stream of timestamped edges are seemingly ubiquitous in the real-world. However, the massive size and continuous nature of these networks make them fundamentally challenging to analyze and leverage for descriptive and predictive modeling tasks. In this work, we propose a general framewo…
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.
Knowledge graphs (KGs) typically contain temporal facts indicating relationships among entities at different times. Due to their incompleteness, several approaches have been proposed to infer new facts for a KG based on the existing ones-a problem known as KG completion. KG embedding approaches have proved effective fo…
Improved topic modeling captures temporal relationships in speech.
problem Lack of temporal information in LDA for speech analysis.
method Temporal Markov chain extension to LDA for acoustic unit discovery.
result Improved phone segmentation results compared to base LDA.
This paper addresses the energy disaggregation problem, i.e. decomposing the electricity signal of a whole home to its operating devices. First, we cast the problem as a dictionary learning (DL) problem where the key electricity patterns representing consumption behaviors are extracted for each device and stored in a d…
Paper models market dynamics using bull and bear forces.
problem Complex market dynamics influenced by biases and narratives.
method Bias to Behavior from Bull-Bear Dynamics (B4) model.
result Model predicts market trends with superior performance and interpretable insights.
CTGCN learns dynamic graph embeddings preserving both local and global graph structure.
problem Learning node representations for evolving graphs while preserving both local and global graph structure.
method CTGCN uses k-core based temporal graph convolutional network to learn dynamic graph embeddings.
result CTGCN outperforms existing methods in link prediction and structural role classification.
Proposes a feature transformation for spatio-temporal traffic models to improve performance and transferability.
problem Limited transferability of deep learning models for traffic flow prediction across different locations.
method Integrates Newell's traffic flow estimators to capture broader dynamics and incorporates spatial dependencies.
result Improves model performance in predicting traffic flows over different horizons.
Many advanced Learning from Demonstration (LfD) methods consider the decomposition of complex, real-world tasks into simpler sub-tasks. By reusing the corresponding sub-policies within and between tasks, they provide training data for each policy from different high-level tasks and compose them to perform novel ones. E…
Time-resolved angiography with interleaved stochastic trajectories (TWIST) has been widely used for dynamic contrast enhanced MRI (DCE-MRI). To achieve highly accelerated acquisitions, TWIST combines the periphery of the k-space data from several adjacent frames to reconstruct one temporal frame. However, this view-sha…
Framework predicts patient risk progression over time.
problem Predicting how patient risk changes over time.
method Supervised contrastive learning framework with embedding properties.
result Framework outperforms baselines in mortality and cognitive impairment datasets.
Proposes a GNN for multivariate time-series prediction with filtering.
problem Low signal-to-noise ratio in complex systems data.
method Integrates a spatial-temporal GNN with a matrix filtering module to generate filtered graphs.
result Proposed model outperforms baseline approaches in multivariate time-series prediction.
Enhances SSL methods with depth cues for better image understanding.
problem Lack of depth cues in 2D image pixel maps limits SSL performance.
method Integrates depth signals from a pretrained monocular RGB-to-depth model into contrastive learning frameworks.
result Improves SSL methods' robustness and generalization with depth signals.
New algorithm for online training of Spiking Neural Networks (SNNs).
problem Training Spiking Neural Networks (SNNs) online with BPTT-equivalent gradients.
method Clear separation of spatial and temporal gradient components, derived from biological insights.
result Online training of SNNs with BPTT-equivalent gradients and low time complexity.
Gaussian graphical models (GGMs) are probabilistic tools of choice for analyzing conditional dependencies between variables in complex systems. Finding changepoints in the structural evolution of a GGM is therefore essential to detecting anomalies in the underlying system modeled by the GGM. In order to detect structur…
In this work we reduce undersampling artefacts in two-dimensional (2D) golden-angle radial cine cardiac MRI by applying a modified version of the U-net. We train the network on 2D spatio-temporal slices which are previously extracted from the image sequences. We compare our approach to two 2D and a 3D Deep Lear…
The use of target networks has been a popular and key component of recent deep Q-learning algorithms for reinforcement learning, yet little is known from the theory side. In this work, we introduce a new family of target-based temporal difference (TD) learning algorithms and provide theoretical analysis on their conver…
There is often latent network structure in spatial and temporal data and the tools of network analysis can yield fascinating insights into such data. In this paper, we develop a nonparametric method for network reconstruction from spatiotemporal data sets using multivariate Hawkes processes. In contrast to prior work o…
Spacetimeformer learns spatiotemporal relationships from data alone.
problem Forecasting multivariate time series with distinct spatial relationships.
method Transformers with dynamic graph connections learning interactions between space, time, and value.
result Competitive results on various time series prediction benchmarks.
Self-supervised learning improves EEG signal analysis without labeled data.
problem Limited labeled data in clinical EEG signals.
method Temporal context prediction and contrastive predictive coding tasks.
result SSL-learned features outperform supervised deep neural networks in low-labeled data regimes.
Modern deep learning approaches have achieved groundbreaking performance in modeling and classifying sequential data. Specifically, attention networks constitute the state-of-the-art paradigm for capturing long temporal dynamics. This paper examines the efficacy of this paradigm in the challenging task of emotion recog…
Study develops curvature for contact-sequence networks, revealing temporal dynamics.
problem Lack of geometric analysis for temporal network sequences.
method Develops Forman--Ricci curvature on spatiotemporal prism complexes.
result Two curvature variants disagree on 56-67% of temporal edges.
Study on distributional TD learning with linear approximations for better return estimation.
problem Estimating the return distribution of a policy in reinforcement learning.
method Finite-sample analysis of distributional TD learning with linear function approximation, using the linear-categorical Bellman equation and exponential stability arguments for products of random matrices.
result Sample complexity of linear distributional TD learning matches that of classic linear TD learning, indicating similar difficulty in estimating return distribution versus its expectation.
Novel approach to learning models based on subjective timescales for better exploration and decision-making.
problem Learning models over multi-step timescales in environments with intermediate states.
method Developed a subjective-timescale model (STM) based on episodic memories, enabling systematic variation of temporal extent of predictions.
result STM produces more informative action-conditioned roll-outs, leading to better decision-making and exploration.