REVIEW 5 cited by
Graph Deep Learning for Time Series Forecasting
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Graph deep learning methods have become popular tools to process collections of correlated time series. Unlike traditional multivariate forecasting methods, graph-based predictors leverage pairwise relationships by conditioning forecasts on graphs spanning the time series collection. The conditioning takes the form of architectural inductive biases on the forecasting architecture, resulting in a family of models called spatiotemporal graph neural networks. These biases allow for training global forecasting models on large collections of time series while localizing predictions w.r.t. each element in the set (nodes) by accounting for correlations among them (edges). Recent advances in graph neural networks and deep learning for time series forecasting make the adoption of such processing framework appealing and timely. However, most studies focus on refining existing architectures by exploiting modern deep-learning practices. Conversely, foundational and methodological aspects have not been subject to systematic investigation. To fill this void, this tutorial paper aims to introduce a comprehensive methodological framework formalizing the forecasting problem and providing design principles for graph-based predictors, as well as methods to assess their performance. In addition, together with an overview of the field, we provide design guidelines and best practices, as well as an in-depth discussion of open challenges and future directions.
Forward citations
Cited by 5 Pith papers
-
Bridge: Retrieval-Augmented Spatiotemporal Modeling for Urban Delivery Demand
Bridge augments a graph neural network backbone with time-aware retrieval from a memory of region-time windows to improve cold-start and cross-city urban delivery demand forecasting.
-
Boosting Team Modeling through Tempo-Relational Representation Learning
A tempo-relational neural architecture jointly models temporal and relational aspects of team interactions to outperform prior approaches on team performance prediction and enable efficient multi-task prediction of te...
-
Globalization for Scalable Short-term Load Forecasting
On Alberta's 42-area load data, global LightGBM and XGBoost with weighted instance clustering outperform local models, while global Ridge regression is slightly less accurate but far more scalable.
-
Interpreting Temporal Graph Neural Networks with Koopman Theory
Proposes DMD and SINDy as new explainability tools for STGNNs, showing they recover interpretable features like infection times and nodes on semi-synthetic data and action-relevant body parts on real motion data.
-
Fourier Basis Mapping: A Time-Frequency Learning Framework for Time Series Forecasting
Using Fourier basis expansion to build time-frequency features improves long-term and short-term time series forecasting across linear, MLP, and transformer backbones.
Discussion (0). Sign in to comment.