Bi, F., He, T., Ong, Y.-S., & Luo, X. (2025). Discovering Spatiotemporal–Individual Coupled Features From Nonstandard Tensors—A Novel Dynamic Graph Mixer Approach. IEEE Transactions on Neural Networks and Learning Systems, 36(11), 19834–19848. https://doi.org/10.1109/tnnls.2025.3592692
Abstract:
In this paper, we present Dynamic Graph Mixer
(DGM), a novel model for learning spatio-temporal-individual
coupled features from high-dimensional and incomplete (HDI)
tensors, which frequently represent dynamic interactions among
real-world data samples. In contrast to existing methods, the
proposed DGM possesses the following three advantages when
learning representations from HDI tensors. First, it performs
light graph message passing based on the conjoint attentions
learned by jointly modeling latent features and implicit structures
to extract high-order connectivity. Second, a multi-layer
nonlinear tensor neural network is adopted to learn the intricate
attribute features of node-node-time from different views. Third,
it follows the Tucker decomposition paradigm in a data density oriented
modeling mechanism to integrate node representations,
preserving the overall multi-dimensional interaction patterns.
Besides, we provide theoretical evidence that the key components
in DGM can significantly improve expressiveness. Extensive
experiments conducted on eight test datasets of HDI tensors
demonstrate that DGM outperforms state-of-the-art methods in
both learning accuracy and efficiency.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the National Research Foundation (NRF), Singapore - AI Singapore Programme
Grant Reference no. : AISG3- TC-2024-014-SGKR