mlsanityData to 13 Oct 2026

Sub-Graph Learning for Spatiotemporal Forecasting via Knowledge Distillation

arXiv 2211.09740 ↗First posted 17 Nov 2022cs.LGcited by 0

On the map: Knowledge distillation → Graph neural network distillation

Abstract (arXiv)

One of the challenges in studying the interactions in large graphs is to learn their diverse pattern and various interaction types. Hence, considering only one distribution and model to study all nodes and ignoring their diversity and local features in their neighborhoods, might severely affect the overall performance. Based on the structural information of the nodes in the graph and the interactions between them, the main graph can be divided into multiple sub-graphs. This graph partitioning can tremendously affect the learning process, however the overall performance is highly dependent on the clustering method to avoid misleading the model. In this work, we present a new framework called KD-SGL to effectively learn the sub-graphs, where we define one global model to learn the overall structure of the graph and multiple local models for each sub-graph. We assess the performance of the proposed framework and evaluate it on public datasets. Based on the achieved results, it can improve the performance of the state-of-the-arts spatiotemporal models with comparable results compared to ensemble of models with less complexity.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Placed in Graph neural network distillation, one of 12 directions in Knowledge distillation. Builds on 17 of its 26 references that are in the map. First posted on arXiv 17 Nov 2022.

Builds on

17 of 26 references.

References · 17

  1. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,130
  2. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 891
  3. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 874
  4. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 751
  5. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 527
  6. 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 434
  7. 2017PathNet: Evolution Channels Gradient Descent in Super Neural Networkscited by 363
  8. 2017A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Predictioncited by 245
  9. 2020Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecastingcited by 213
  10. 2021Spatial-Temporal Graph ODE Networks for Traffic Flow Forecastingcited by 210
  11. 2019Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecastingcited by 161
  12. 2020Structural Deep Clustering Networkcited by 145
5 more
  1. 2020FC-GAGA: Fully Connected Gated Graph Architecture for Spatio-Temporal Traffic Forecastingcited by 30
  2. 2018A Memory-Network Based Solution for Multivariate Time-Series Forecastingcited by 22
  3. 2021Encoders and Ensembles for Task-Free Continual Learningcited by 17
  4. 2021RNN with Particle Flow for Probabilistic Spatio-temporal Forecastingcited by 16
  5. 2018Multi-variable LSTM neural network for autoregressive exogenous modelcited by 2

Built on by

Not cited yet.