Lukas Gosch

Hello, welcome to my corner of the web!

I am a researcher on machine learning focusing on robust and reliable learning on graphs. I am doing my PhD at TU Munich under the supervision of Prof. Günnemann in the DAML research group and am part of the relAI graduate school. Currently, I am especially interested in provable robustness. Furthermore, I am also interested in theoretical machine learning, high-dimensional statistics and combinatorial optimization.

If you want to contact me, best write me an e-mail: lukas . gosch [at] tum.de. Scroll down to find my other social media appearances.

Quick Link: Resume/CV

news

Oct 1, 2023	Our paper Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions got accepted at NeurIPS 2023 .
Jun 1, 2023	Our paper Expressivity of Graph Neural Networks Through the Lens of Adversarial Robustness got accepted at AdvML Frontiers@ICML2023 .
Feb 1, 2023	Our paper Revisiting Robustness in Graph Machine Learning got accepted at ICLR 2023 .
Dec 9, 2022	I gave an oral talk today at TSRML@NeurIPS22 about Revisiting Robustness in Graph Machine Learning.
Nov 1, 2022	Our paper Training Differentially Private Graph Neural Networks with Random Walk Sampling got accepted at the TSRML@NeurIPS22 workshop .
Nov 1, 2022	Our paper Revisiting Robustness in Graph Machine Learning got accepted and selected for an oral talk at TSRML@NeurIPS22 and accepted at ML-Safety@NeurIPS22 .

selected publications

Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions

Lukas Gosch, Simon Geisler, Daniel Sturm, and 3 more authors

In Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023

Abs Bib PDF Website

Despite its success in the image domain, adversarial training did not (yet) stand out as an effective defense for Graph Neural Networks (GNNs) against graph structure perturbations. In the pursuit of fixing adversarial training (1) we show and overcome fundamental theoretical as well as practical limitations of the adopted graph learning setting in prior work; (2) we reveal that more flexible GNNs based on learnable graph diffusion are able to adjust to adversarial perturbations, while the learned message passing scheme is naturally interpretable; (3) we introduce the first attack for structure perturbations that, while targeting multiple nodes at once, is capable of handling global (graph-level) as well as local (node-level) constraints. Including these contributions, we demonstrate that adversarial training is a state-of-the-art defense against adversarial structure perturbations.
@inproceedings{gosch2023adversarial, title = {Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions}, author = {Gosch, Lukas and Geisler, Simon and Sturm, Daniel and Charpentier, Bertrand and Z{\"u}gner, Daniel and G{\"u}nnemann, Stephan}, booktitle = {Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS)}, year = {2023}, }
Revisiting Robustness in Graph Machine Learning

Lukas Gosch, Daniel Sturm, Simon Geisler, and 1 more author

In The Eleventh International Conference on Learning Representations (ICLR), 2023

Abs Bib PDF Website

Many works show that node-level predictions of Graph Neural Networks (GNNs) are unrobust to small, often termed adversarial, changes to the graph structure. However, because manual inspection of a graph is difficult, it is unclear if the studied perturbations always preserve a core assumption of adversarial examples: that of unchanged semantic content. To address this problem, we introduce a more principled notion of an adversarial graph, which is aware of semantic con- tent change. Using Contextual Stochastic Block Models (CSBMs) and real-world graphs, our results uncover: i) for a majority of nodes the prevalent perturba- tion models include a large fraction of perturbed graphs violating the unchanged semantics assumption; ii) surprisingly, all assessed GNNs show over-robustness - that is robustness beyond the point of semantic change. We find this to be a complementary phenomenon to adversarial examples and show that including the label-structure of the training graph into the inference process of GNNs signif- icantly reduces over-robustness, while having a positive effect on test accuracy and adversarial robustness. Theoretically, leveraging our new semantics-aware notion of robustness, we prove that there is no robustness-accuracy tradeoff for inductively classifying a newly added node.
@inproceedings{gosch2023revisiting, title = {Revisiting Robustness in Graph Machine Learning}, author = {Gosch, Lukas and Sturm, Daniel and Geisler, Simon and G{\"u}nnemann, Stephan}, booktitle = {The Eleventh International Conference on Learning Representations (ICLR)}, year = {2023}, url = {https://openreview.net/forum?id=h1o7Ry9Zctm}, }