4 papers · 1 filter
Revisiting the Relation Between Robustness and Universality
M. Klabunde, L. Caspari, F. Lemmerich
The modified universality hypothesis proposed by Jones et al. (2022) suggests that adversarially robust models trained for a given task are highly similar. We revisit the hypothesi…
ReSi: A Comprehensive Benchmark for Representational Similarity Measures
Max Klabunde, Tassilo Wald, Tobias Schumacher +3
Measuring the similarity of different representations of neural architectures is a fundamental task and an open research challenge for the machine learning community. This paper pr…
Towards Measuring Representational Similarity of Large Language Models
Max Klabunde, Mehdi Ben Amor, Michael Granitzer +1
Understanding the similarity of the numerous released large language models (LLMs) has many uses, e.g., simplifying model selection, detecting illegal model reuse, and advancing ou…
On the Prediction Instability of Graph Neural Networks
Max Klabunde, Florian Lemmerich
Instability of trained models, i.e., the dependence of individual node predictions on random factors, can affect reproducibility, reliability, and trust in machine learning systems…