1,721,086 research outputs found
Explaining Siamese Networks in Few-Shot Learning for Audio Data
No full textMachine learning models are not able to generalize correctly when queried on samples belonging to class distributions that were never seen during training. This is a critical issue, since real world applications might need to quickly adapt without the necessity of re-training. To overcome these limitations, few-shot learning frameworks have been proposed and their applicability has been studied widely for computer vision tasks. Siamese Networks learn pairs similarity in form of a metric that can be easily extended on new unseen classes. Unfortunately, the downside of such systems is the lack of explainability. We propose a method to explain the outcomes of Siamese Networks in the context of few-shot learning for audio data. This objective is pursued through a local perturbation-based approach that evaluates segments-weighted-average contributions to the final outcome considering the interplay between different areas of the audio spectrogram. Qualitative and quantitative results demonstrate that our method is able to show common intra-class characteristics and erroneous reliance on silent sections
Preface [to: Discovery Science : 27th International Conference, DS 2024, Pisa, Italy, October 14–16, 2024, Proceedings, Part II, a cura di Dino Pedreschi, Anna Monreale, Riccardo Guidotti, Roberto Pellungrini e Francesca Naretto, Cham, Springer Nature Switzerland, 2025]
No full text
Causal inference for social discrimination reasoning
Full text linkThe discovery of discriminatory bias in human or automated decision making is a task of increasing importance and difficulty, exacerbated by the pervasive use of machine learning and data mining. Currently, discrimination discovery largely relies upon correlation analysis of decisions records, disregarding the impact of confounding biases. We present a method for causal discrimination discovery based on propensity score analysis, a statistical tool for filtering out the effect of confounding variables. We introduce causal measures of discrimination which quantify the effect of group membership on the decisions, and highlight causal discrimination/favoritism patterns by learning regression trees over the novel measures. We validate our approach on two real world datasets. Our proposed framework for causal discrimination has the potential to enhance the transparency of machine learning with tools for detecting discriminatory bias both in the training data and in the learning algorithms
Discovery Science 27th International Conference, DS 2024, Pisa, Italy, October 14–16, 2024, Proceedings, Part I
No full textFairLens: Auditing black-box clinical decision support systems
No full textThe pervasive application of algorithmic decision-making is raising concerns on the risk of unintended bias in AI systems deployed in critical settings such as healthcare. The detection and mitigation of model bias is a very delicate task that should be tackled with care and involving domain experts in the loop. In this paper we introduce FairLens, a methodology for discovering and explaining biases. We show how this tool can audit a fictional commercial black-box model acting as a clinical decision support system (DSS). In this scenario, the healthcare facility experts can use FairLens on their historical data to discover the biases of the model before incorporating it into the clinical decision flow. FairLens first stratifies the available patient data according to demographic attributes such as age, ethnicity, gender and healthcare insurance; it then assesses the model performance on such groups highlighting the most common misclassifications. Finally, FairLens allows the expert to examine one misclassification of interest by explaining which elements of the affected patients’ clinical history drive the model error in the problematic group. We validate FairLens’ ability to highlight bias in multilabel clinical DSSs introducing a multilabel-appropriate metric of disparity and proving its efficacy against other standard metrics
Diffusive phenomena in dynamic networks: A data-driven study
No full textEveryday, ideas, information as well as viruses spread over complex social tissues described by our interpersonal relations. So far, the network contexts upon which diffusive phenomena unfold have usually been considered static, composed by a fixed set of nodes and edges. Recent studies describe social networks as rapidly changing topologies. In this work — following a data-driven approach — we compare the behaviors of classical spreading models when used to analyze a given social network whose topological dynamics are observed at different temporal granularities. Our goal is to shed some light on the impacts that the adoption of a static topology has on spreading simulations as well as to provide an alternative formulation of two classical diffusion models
- …
