arXiv subjects

Jörg Schlötterer

Publications and source records attributed to Jörg Schlötterer.

43 records · Page 3Linked to original sources

arXiv2023

Interpreting and Correcting Medical Image Classification with PIP-Net

Part-prototype models are explainable-by-design image classifiers, and a promising alternative to black box AI. This paper explores the applicability and potential of interpretable machine learning, in particular PIP-Net, for automated diagnosis support on real-world medical imaging data. PIP-Net learns human-understandable prototypical image parts and we evaluate its accuracy and interpretability for fracture detection and skin cancer diagnosis. We find that PIP-Net's decision making process is in line with medical classification standards, while only provided with image-level class labels. Because of PIP-Net's unsupervised pretraining of prototypes, data quality problems such as undesired text in an X-ray or labelling errors can be easily identified. Additionally, we are the first to show that humans can manually correct the reasoning of PIP-Net by directly disabling undesired prototypes. We conclude that part-prototype models are promising for medical applications due to their interpretability and potential for advanced model debugging.

cs.CV↗

arXiv2023

Guidance in Radiology Report Summarization: An Empirical Evaluation and Error Analysis

Automatically summarizing radiology reports into a concise impression can reduce the manual burden of clinicians and improve the consistency of reporting. Previous work aimed to enhance content selection and factuality through guided abstractive summarization. However, two key issues persist. First, current methods heavily rely on domain-specific resources to extract the guidance signal, limiting their transferability to domains and languages where those resources are unavailable. Second, while automatic metrics like ROUGE show progress, we lack a good understanding of the errors and failure modes in this task. To bridge these gaps, we first propose a domain-agnostic guidance signal in form of variable-length extractive summaries. Our empirical results on two English benchmarks demonstrate that this guidance signal improves upon unguided summarization while being competitive with domain-specific methods. Additionally, we run an expert evaluation of four systems according to a taxonomy of 11 fine-grained errors. We find that the most pressing differences between automatic summaries and those of radiologists relate to content selection including omissions (up to 52%) and additions (up to 57%). We hypothesize that latent reporting factors and corpus-level inconsistencies may limit models to reliably learn content selection from the available data, presenting promising directions for future work.

cs.CL↗

arXiv2023

From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI

The rising popularity of explainable artificial intelligence (XAI) to understand high-performing black boxes raised the question of how to evaluate explanations of machine learning (ML) models. While interpretability and explainability are often presented as a subjectively validated binary property, we consider it a multi-faceted concept. We identify 12 conceptual properties, such as Compactness and Correctness, that should be evaluated for comprehensively assessing the quality of an explanation. Our so-called Co-12 properties serve as categorization scheme for systematically reviewing the evaluation practices of more than 300 papers published in the last 7 years at major AI and ML conferences that introduce an XAI method. We find that 1 in 3 papers evaluate exclusively with anecdotal evidence, and 1 in 5 papers evaluate with users. This survey also contributes to the call for objective, quantifiable evaluation methods by presenting an extensive overview of quantitative XAI evaluation methods. Our systematic collection of evaluation methods provides researchers and practitioners with concrete tools to thoroughly validate, benchmark and compare new and existing XAI methods. The Co-12 categorization scheme and our identified evaluation methods open up opportunities to include quantitative metrics as optimization criteria during model training in order to optimize for accuracy and interpretability simultaneously.

cs.AI↗

arXiv2022

Towards a trustworthy, secure and reliable enclave for machine learning in a hospital setting: The Essen Medical Computing Platform (EMCP)

AI/Computing at scale is a difficult problem, especially in a health care setting. We outline the requirements, planning and implementation choices as well as the guiding principles that led to the implementation of our secure research computing enclave, the Essen Medical Computing Platform (EMCP), affiliated with a major German hospital. Compliance, data privacy and usability were the immutable requirements of the system. We will discuss the features of our computing enclave and we will provide our recipe for groups wishing to adopt a similar setup.

cs.CR↗

arXiv2019

Competitive Influence Maximization: Integrating Budget Allocation and Seed Selection

Today, many companies take advantage of viral marketing to promote their new products, and since there are several competing companies in many markets, Competitive Influence Maximization has attracted much attention. Two categories of studies exist in the literature. First, studies that focus on which nodes from the network to select considering the existence of the opponents. Second, studies that focus on the problem of budget allocation. In this work, we integrate these two lines of research and propose a new scenario where competition happens in two phases. First, parties identify the most influential nodes of the network. Then they compete over only these influential nodes by the amount of budget they allocate to each node. We provide a strong motivation for this integration. Also, in previous budget allocation studies, any fraction of the budget could be allocated to a node, which means that the action space was continuous. However, in our scenario, we consider that the action space is discrete. This consideration is far more realistic, and it significantly changes the problem. We model the scenario as a game and propose a novel framework for calculating the Nash equilibrium. Notably, building an efficient framework for this problem with such a huge action space and also handling the stochastic environment of influence maximization is very challenging. To tackle these difficulties, we devise a new payoff estimation method and a novel best response oracle to boost the efficiency of our framework. Also, we validate each aspect of our work through extensive experiments.

cs.SI↗

arXiv2019

Parallel Total Variation Distance Estimation with Neural Networks for Merging Over-Clusterings

We consider the initial situation where a dataset has been over-partitioned into $k$ clusters and seek a domain independent way to merge those initial clusters. We identify the total variation distance (TVD) as suitable for this goal. By exploiting the relation of the TVD to the Bayes accuracy we show how neural networks can be used to estimate TVDs between all pairs of clusters in parallel. Crucially, the needed memory space is decreased by reducing the required number of output neurons from $k^2$ to $k$. On realistically obtained over-clusterings of ImageNet subsets it is demonstrated that our TVD estimates lead to better merge decisions than those obtained by relying on state-of-the-art unsupervised representations. Further the generality of the approach is verified by evaluating it on a a point cloud dataset.

cs.LG↗

arXiv2019

Policy Learning for Malaria Control

Sequential decision making is a typical problem in reinforcement learning with plenty of algorithms to solve it. However, only a few of them can work effectively with a very small number of observations. In this report, we introduce the progress to learn the policy for Malaria Control as a Reinforcement Learning problem in the KDD Cup Challenge 2019 and propose diverse solutions to deal with the limited observations problem. We apply the Genetic Algorithm, Bayesian Optimization, Q-learning with sequence breaking to find the optimal policy for five years in a row with only 20 episodes/100 evaluations. We evaluate those algorithms and compare their performance with Random Search as a baseline. Among these algorithms, Q-Learning with sequence breaking has been submitted to the challenge and got ranked 7th in KDD Cup.

cs.LG↗