mlsanityData to 7 Oct 2026

GLAudio Listens to the Sound of the Graph

arXiv 2407.14387 ↗First posted 19 Jul 2024cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose GLAudio: Graph Learning on Audio representation of the node features and the connectivity structure. This novel architecture propagates the node features through the graph network according to the discrete wave equation and then employs a sequence learning architecture to learn the target node function from the audio wave signal. This leads to a new paradigm of learning on graph-structured data, in which information propagation and information processing are separated into two distinct steps. We theoretically characterize the expressivity of our model, introducing the notion of the receptive field of a vertex, and investigate our model's susceptibility to over-smoothing and over-squashing both theoretically as well as experimentally on various graph datasets.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 34 references that are in the map. First posted on arXiv 19 Jul 2024.

Builds on

29 of 34 references.

References · 29

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  6. 2018How Powerful are Graph Neural Networks?cited by 4,355
  7. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  8. 2022Simplified State Space Layers for Sequence Modelingcited by 776
  9. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 702
  10. 2020A Generalization of Transformer Networks to Graphscited by 653
  11. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 624
  12. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 544
17 more
  1. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 471
  2. 2021Rethinking Graph Transformers with Spectral Attentioncited by 468
  3. 2019Are Transformers universal approximators of sequence-to-sequence functions?cited by 404
  4. 2017Residual Gated Graph ConvNetscited by 341
  5. 2019PairNorm: Tackling Oversmoothing in GNNscited by 297
  6. 2021GRAND: Graph Neural Diffusioncited by 258
  7. 2023A Survey on Oversmoothing in Graph Neural Networkscited by 246
  8. 2020A Note on Over-Smoothing for Graph Neural Networkscited by 245
  9. 2022Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNscited by 208
  10. 2020Directional Graph Networkscited by 132
  11. 2020Towards Deeper Graph Neural Networks with Differentiable Group Normalizationcited by 113
  12. 2023Where Did the Gap Go? Reassessing the Long-Range Graph Benchmarkcited by 83
  13. 2020Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependenciescited by 81
  14. 2022On the Trade-off between Over-smoothing and Over-squashing in Deep Graph Neural Networkscited by 63
  15. 2022Understanding convolution on graphs via energiescited by 58
  16. 2023State-space Models with Layer-wise Nonlinearity are Universal Approximators with Exponential Decaying Memorycited by 38
  17. 2023Neural Oscillators are Universalcited by 16

Built on by

Not cited yet.