Bibtex entries

Attention is not all you need

@inproceedings{Bouritsas2021Partition,
      title={Partition and code: learning how to compress graphs}, 
      author={Giorgos Bouritsas and Andreas Loukas and Nikos Karalias and Michael Bronstei},
      year={2021},
      booktitle={Neural Information Processing Systems},
      series={NeurIPS},
      url={https://arxiv.org/abs/2107.01952}
}

What training reveals about neural network complexity

@inproceedings{Loukas2021Training,
      title={What training reveals about neural network complexity}, 
      author={Andreas Loukas and Marinos Poiitis and Stefanie Jegelka},
      year={2021},
      booktitle={Neural Information Processing Systems},
      series={NeurIPS},
      url={https://arxiv.org/abs/2106.04186}
}

Attention is not all you need

@inproceedings{Dong2021Attention,
      title={Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth}, 
      author={Yihe Dong and Jean-Baptiste Cordonnier and Andreas Loukas},
      year={2021},
      booktitle={International Conference on Machine Learning},
      series={ICML},
      url={https://arxiv.org/abs/2103.03404}
}

Erdős goes neural

@inproceedings{Karalias2020Erdos,
    title={Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs},
    author={Nikos Karalias and Andreas Loukas},
    booktitle={Neural Information Processing Systems},
    year={2020},
    series={NeurIPS},
    url={https://arxiv.org/abs/2006.10643}
}

Building powerful and equivariant graph neural networks with structural message passing

@inproceedings{Vignac2020,
   author = {Vignac, Cl\'{e}ment and Loukas, Andreas and Frossard, Pascal},
   booktitle = {Advances in Neural Information Processing Systems},
   editor = {H. Larochelle and M. Ranzato and R. Hadsell and M. F. Balcan and H. Lin},
   pages = {14143--14155},
   publisher = {Curran Associates, Inc.},
   title = {Building powerful and equivariant graph neural networks with structural message-passing},
   url = {https://proceedings.neurips.cc/paper/2020/file/a32d7eeaae19821fd9ce317f3ce952a7-Paper.pdf},
   volume = {33},
   year = {2020}
}

How hard is to distinguish graphs with GNN

@inproceedings{Loukas2020How,
    title={How hard is to distinguish graphs with graph neural networks?},
    author={Andreas Loukas},
    booktitle={Neural Information Processing Systems},
    year={2020},
    series={NeurIPS},
    url={https://proceedings.neurips.cc//paper_files/paper/2020/hash/23685a2431acad7789c1e3d43ea1522c-Abstract.html}
}

Structural message passing

@inproceedings{Vignac2020Building,
    title={Building powerful and equivariant graph neural networks with structural message-passing},
    author={Clement Vignac and Andreas Loukas and Pascal Frossard},
    booktitle={Neural Information Processing Systems},
    year={2020},
    series={NeurIPS},
    url={https://arxiv.org/abs/2006.15107}
}

What graph neural networks cannot learn

@inproceedings{Loukas2020What,
    title={What graph neural networks cannot learn: depth vs width},
    author={Andreas Loukas},
    booktitle={International Conference on Learning Representations},
    year={2020},
    url={https://openreview.net/forum?id=B1l2bp4YwS}
}

On the relationship between self-attention and convolution

@inproceedings{Cordonnier2020On,
    title={On the Relationship between Self-Attention and Convolutional Layers},
    author={Jean-Baptiste Cordonnier and Andreas Loukas and Martin Jaggi},
    booktitle={International Conference on Learning Representations},
    year={2020},
    url={https://openreview.net/forum?id=HJlnC1rKPB}
}

Extrapolating Paths with Graph Neural Networks

@inproceedings{ijcai2019-303,
   title={Extrapolating Paths with Graph Neural Networks},
   author={Cordonnier, Jean-Baptiste and Loukas, Andreas},
   booktitle={Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, {IJCAI-19}},
   publisher={International Joint Conferences on Artificial Intelligence Organization},
   pages={2187--2194},
   year={2019},
   month={7},
   doi={10.24963/ijcai.2019/303},
   url={https://doi.org/10.24963/ijcai.2019/303},
}

Graph reduction with spectral and cut guarantees

@article{JMLR:v20:18-680, 
   author={Andreas Loukas}, 
   title={Graph Reduction with Spectral and Cut Guarantees}, 
   journal={Journal of Machine Learning Research}, 
   year={2019}, 
   volume={20}, 
   number={116}, 
   pages={1-42}, 
   url = {http://jmlr.org/papers/v20/18-680.html} 
}

How Close Are the Eigenvectors of the Sample and Actual Covariance Matrices?

@inproceedings{pmlr-v70-loukas17a, 
    title={How Close Are the Eigenvectors of the Sample and Actual Covariance Matrices?}, 
    author={Andreas Loukas}, 
    booktitle={Proceedings of the 34th International Conference on Machine Learning}, 
    pages={2228--2237}, 
    year={2017}, 
    volume={70}, 
    series={Proceedings of Machine Learning Research}, 
    publisher = {PMLR}
}

A Time-Vertex Signal Processing Framework

@article{Grassi:228233, 
    title={A Time-Vertex Signal Processing Framework}, 
    author = {Grassi, Francesco and Loukas, Andreas and Perraudin, Nathanaël and Ricaud, Benjamin}, 
    publisher = {Institute of Electrical and Electronics Engineers}, 
    journal = {IEEE Transactions on Signal Processing}, 
    number = {3}, 
    volume = {66}, 
    pages = {817-829}, 
    year = {2018},  
    url = {http://infoscience.epfl.ch/record/228233}, 
    doi = {10.1109/TSP.2017.2775589}
}

Stationary time-vertex signal processing

@article{loukas2019stationary, 
    title={Stationary time-vertex signal processing}, 
    author={Loukas, Andreas and Perraudin, Nathana{\"e}l}, 
    journal={EURASIP Journal on Advances in Signal Processing}, 
    volume={2019}, 
    number={1}, 
    pages={36}, 
    year={2019}, 
    publisher={Springer} 
}

Autoregressive Moving Average Graph Filtering

@ARTICLE{7581108, 
    author={Elvin {Isufi} and Andreas {Loukas} and Andrea {Simonetto} and Geert {Leus}}, 
    journal={IEEE Transactions on Signal Processing}, 
    title={Autoregressive Moving Average Graph Filtering}, 
    year={2017}, 
    volume={65}, 
    number={2}, 
    pages={274-288}, 
    doi={10.1109/TSP.2016.2614793}, 
    ISSN={1941-0476}
}