More Like this

1. Temporal Dependencies and Spatio-Temporal Patterns of Time Series Models

   https://doi.org/10.1609/aaai.v38i21.30396  

   Islam, Khairul (March 2024, Proceedings of the AAAI Conference on Artificial Intelligence)

   The widespread use of Artificial Intelligence (AI) has highlighted the importance of understanding AI model behavior. This understanding is crucial for practical decision-making, assessing model reliability, and ensuring trustworthiness. Interpreting time series forecasting models faces unique challenges compared to image and text data. These challenges arise from the temporal dependencies between time steps and the evolving importance of input features over time. My thesis focuses on addressing these challenges by aiming for more precise explanations of feature interactions, uncovering spatiotemporal patterns, and demonstrating the practical applicability of these interpretability techniques using real-world datasets and state-of-the-art deep learning models. 

   more » « less
2. Temporal foundations of episodic memory

   https://doi.org/10.3758/s13420-023-00608-x  

   Crystal, Jonathon D. (March 2024, Learning & Behavior)

   A fundamental question in the development of animal models of episodic memory concerns the role of temporal processes in episodic memory. Gallistel (1990) developed a framework in which animals remember specific features about an event, including the time of occurrence of the event and its location in space. Gallistel proposed that timing is based on a series of biological oscillators, spanning a wide range of periods. Accordingly, a snapshot of the phases of multiple oscillators provides a representation of the time of occurrence of the event. I review research on basic timing mechanisms that may support memory for times of occurrence. These studies suggest that animals use biological oscillators to represent time. Next, I describe recently developed animal models of episodic memory that highlight the importance of temporal representations in memory. One line of research suggests that an oscillator representation of time supports episodic memory. A second line of research highlights the flow of events in time in episodic memory. Investigations that integrate time and memory may advance the development of animal models of episodic memory. 

   more » « less
3. Online Sampling of Temporal Networks

   https://doi.org/10.1145/3442202  

   Ahmed, Nesreen K.; Duffield, Nick; Rossi, Ryan A. (August 2021, ACM Transactions on Knowledge Discovery from Data)

   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 framework for temporal network sampling with unbiased estimation. We develop online, single-pass sampling algorithms, and unbiased estimators for temporal network sampling. The proposed algorithms enable fast, accurate, and memory-efficient statistical estimation of temporal network patterns and properties. In addition, we propose a temporally decaying sampling algorithm with unbiased estimators for studying networks that evolve in continuous time, where the strength of links is a function of time, and the motif patterns are temporally weighted. In contrast to the prior notion of a △ t -temporal motif, the proposed formulation and algorithms for counting temporally weighted motifs are useful for forecasting tasks in networks such as predicting future links, or a future time-series variable of nodes and links. Finally, extensive experiments on a variety of temporal networks from different domains demonstrate the effectiveness of the proposed algorithms. A detailed ablation study is provided to understand the impact of the various components of the proposed framework. 

   more » « less
4. Temporal Graph Benchmark for Machine Learning on Temporal Graphs

   Huang, Shenyang; Poursafaei1, Farimah; Danovitch, Jacob; Fey, Matthias; Hu, Weihua; Rossi, Emanuele; Leskovec, Jure; Bronstein, Michael; Rabusseau, Guillaume; Rabbany, Reihaneh (December 2023, Advances in neural information processing systems)

   We present the Temporal Graph Benchmark (TGB), a collection of challenging and diverse benchmark datasets for realistic, reproducible, and robust evaluation of machine learning models on temporal graphs. TGB datasets are of large scale, spanning years in duration, incorporate both node and edge-level prediction tasks and cover a diverse set of domains including social, trade, transaction, and transportation networks. For both tasks, we design evaluation protocols based on realistic use-cases. We extensively benchmark each dataset and find that the performance of common models can vary drastically across datasets. In addition, on dynamic node property prediction tasks, we show that simple methods often achieve superior performance compared to existing temporal graph models. We believe that these findings open up opportunities for future research on temporal graphs. Finally, TGB provides an automated machine learning pipeline for reproducible and accessible temporal graph research, including data loading, experiment setup and performance evaluation. TGB will be maintained and updated on a regular basis and welcomes community feedback. TGB datasets, data loaders, example codes, evaluation setup, and leaderboards are publicly available at https://tgb.complexdatalab.com/. 

   more » « less
5. The Mechanical Representation of Temporal Delays

   https://doi.org/10.1038/s41598-017-07289-3  

   Leib, Raz; Karniel, Amir; Mussa-Ivaldi, Ferdinando A. (December 2017, Scientific Reports)