no code implementations • 15 Mar 2024 • Tobias Leemann, Martin Pawelczyk, Bardh Prenkaj, Gjergji Kasneci
We subsequently investigate how different components in the objective functions, e. g., the machine learning model or cost function used to measure distance, determine whether the outcome can be considered an adversarial example or not.
1 code implementation • 11 Oct 2023 • Martin Pawelczyk, Seth Neel, Himabindu Lakkaraju
In this work, we propose a new class of unlearning methods for LLMs we call ''In-Context Unlearning'', providing inputs in context and without having to update model parameters.
1 code implementation • NeurIPS 2023 • Tobias Leemann, Martin Pawelczyk, Gjergji Kasneci
In particular, we derive a parametric family of $f$-MIP guarantees that we refer to as $\mu$-Gaussian Membership Inference Privacy ($\mu$-GMIP) by theoretically analyzing likelihood ratio-based membership inference attacks on stochastic gradient descent (SGD).
1 code implementation • 10 Nov 2022 • Martin Pawelczyk, Himabindu Lakkaraju, Seth Neel
As predictive models are increasingly being employed to make consequential decisions, there is a growing emphasis on developing techniques that can provide algorithmic recourse to affected individuals.
no code implementations • 3 Nov 2022 • Martin Pawelczyk, Lea Tiyavorabun, Gjergji Kasneci
In this work, we develop \texttt{DEAR} (DisEntangling Algorithmic Recourse), a novel and practical recourse framework that bridges the gap between the IMF and the strong causal assumptions.
1 code implementation • 25 Oct 2022 • Tobias Leemann, Martin Pawelczyk, Christian Thomas Eberle, Gjergji Kasneci
In this work, we show that the decision not to share data can be considered as information in itself that should be protected to respect users' privacy.
1 code implementation • 12 Oct 2022 • Vadim Borisov, Kathrin Seßler, Tobias Leemann, Martin Pawelczyk, Gjergji Kasneci
Tabular data is among the oldest and most ubiquitous forms of data.
no code implementations • 30 Aug 2022 • Martin Pawelczyk, Tobias Leemann, Asia Biega, Gjergji Kasneci
Thus, our work raises fundamental questions about the compatibility of "the right to an actionable explanation" in the context of the "right to be forgotten", while also providing constructive insights on the determining factors of recourse robustness.
2 code implementations • 22 Jun 2022 • Chirag Agarwal, Dan Ley, Satyapriya Krishna, Eshika Saxena, Martin Pawelczyk, Nari Johnson, Isha Puri, Marinka Zitnik, Himabindu Lakkaraju
OpenXAI comprises of the following key components: (i) a flexible synthetic data generator and a collection of diverse real-world datasets, pre-trained models, and state-of-the-art feature attribution methods, and (ii) open-source implementations of eleven quantitative metrics for evaluating faithfulness, stability (robustness), and fairness of explanation methods, in turn providing comparisons of several explanation methods across a wide variety of metrics, models, and datasets.
no code implementations • 14 Mar 2022 • Chirag Agarwal, Nari Johnson, Martin Pawelczyk, Satyapriya Krishna, Eshika Saxena, Marinka Zitnik, Himabindu Lakkaraju
As attribution-based explanation methods are increasingly used to establish model trustworthiness in high-stakes situations, it is critical to ensure that these explanations are stable, e. g., robust to infinitesimal perturbations to an input.
1 code implementation • 13 Mar 2022 • Martin Pawelczyk, Teresa Datta, Johannes van-den-Heuvel, Gjergji Kasneci, Himabindu Lakkaraju
To this end, we propose a novel objective function which simultaneously minimizes the gap between the achieved (resulting) and desired recourse invalidation rates, minimizes recourse costs, and also ensures that the resulting recourse achieves a positive model prediction.
2 code implementations • 5 Oct 2021 • Vadim Borisov, Tobias Leemann, Kathrin Seßler, Johannes Haug, Martin Pawelczyk, Gjergji Kasneci
Moreover, we discuss deep learning approaches for generating tabular data, and we also provide an overview over strategies for explaining deep models on tabular data.
4 code implementations • 2 Aug 2021 • Martin Pawelczyk, Sascha Bielawski, Johannes van den Heuvel, Tobias Richter, Gjergji Kasneci
In summary, our work provides the following contributions: (i) an extensive benchmark of 11 popular counterfactual explanation methods, (ii) a benchmarking framework for research on future counterfactual explanation methods, and (iii) a standardized set of integrated evaluation measures and data sets for transparent and extensive comparisons of these methods.
no code implementations • 18 Jun 2021 • Martin Pawelczyk, Chirag Agarwal, Shalmali Joshi, Sohini Upadhyay, Himabindu Lakkaraju
As machine learning (ML) models become more widely deployed in high-stakes applications, counterfactual explanations have emerged as key tools for providing actionable model explanations in practice.
no code implementations • 2 Feb 2021 • Hamed Jalali, Martin Pawelczyk, Gjergji Kasneci
Imposing the \emph{conditional independence assumption} (CI) between the experts renders the aggregation of different expert predictions time efficient at the cost of poor uncertainty quantification.
no code implementations • 23 Jun 2020 • Martin Pawelczyk, Klaus Broelemann, Gjergji Kasneci
In this work, we derive a general upper bound for the costs of counterfactual explanations under predictive multiplicity.
1 code implementation • 18 Jun 2020 • Johannes Haug, Martin Pawelczyk, Klaus Broelemann, Gjergji Kasneci
Feature selection can be a crucial factor in obtaining robust and accurate predictions.
3 code implementations • 21 Oct 2019 • Martin Pawelczyk, Johannes Haug, Klaus Broelemann, Gjergji Kasneci
On one hand, we suggest to complement the catalogue of counterfactual quality measures [1] using a criterion to quantify the degree of difficulty for a certain counterfactual suggestion.