Related papers: Can Information Flows Suggest Targets for Interven…
This work presents insights gained by investigating the relationship between algorithmic fairness and the concept of secure information flow. The problem of enforcing secure information flow is well-studied in the context of information…
Inspired by the prevalence of recurrent circuits in biological brains, we investigate the degree to which directionality is a helpful inductive bias for artificial neural networks. Taking directionality as topologically-ordered information…
Avoiding bias and understanding the real-world consequences of AI-supported decision-making are critical to address fairness and assign accountability. Existing approaches often focus either on technical aspects, such as datasets and…
The wide spread usage of automated data-driven decision support systems has raised a lot of concerns regarding accountability and fairness of the employed models in the absence of human supervision. Existing fairness-aware approaches tackle…
Attribution methods provide insights into the decision-making of machine learning models like artificial neural networks. For a given input sample, they assign a relevance score to each individual input variable, such as the pixels of an…
Language models are prone to dataset biases, known as shortcuts and spurious correlations in data, which often result in performance drop on new data. We present a new debiasing framework called ``FairFlow'' that mitigates dataset biases by…
In machine learning systems, bias mitigation approaches aim to make outcomes fairer across privileged and unprivileged groups. Bias mitigation methods work in different ways and have known "waterfall" effects, e.g., mitigating bias at one…
This paper proposes an information-theoretic representation learning framework, named conditional information flow maximization, to extract noise-invariant sufficient representations for the input data and target task. It promotes the…
In today's machine learning (ML) models, any part of the training data can affect the model output. This lack of control for information flow from training data to model output is a major obstacle in training models on sensitive data when…
Computers are increasingly used to make decisions that have significant impact in people's lives. Often, these predictions can affect different population subgroups disproportionately. As a result, the issue of fairness has received much…
Deep Neural Networks (DNNs) have become ubiquitous in medical image processing and analysis. Among them, U-Nets are very popular in various image segmentation tasks. Yet, little is known about how information flows through these networks…
Existing machine learning methods for causal inference usually estimate quantities expressed via the mean of potential outcomes (e.g., average treatment effect). However, such quantities do not capture the full information about the…
We develop a theoretical framework for defining and identifying flows of information in computational systems. Here, a computational system is assumed to be a directed graph, with "clocked" nodes that send transmissions to each other along…
Information flow analysis is a powerful technique for reasoning about the sensitive information exposed by a program during its execution. While past work has proposed information theoretic metrics (e.g., Shannon entropy, min-entropy,…
Analysing how information flows along the layers of a multilayer perceptron is a topic of paramount importance in the field of artificial neural networks. After framing the problem from the point of view of information theory, in this…
In recent years the ubiquitous deployment of AI has posed great concerns in regards to algorithmic bias, discrimination, and fairness. Compared to traditional forms of bias or discrimination caused by humans, algorithmic bias generated by…
The objective of this paper is to explore the opportunities for human information behaviour research to inform and influence the field of machine learning and the resulting machine information behaviour. Using the development of foundation…
In high-stakes settings where machine learning models are used to automate decision-making about individuals, the presence of algorithmic bias can exacerbate systemic harm to certain subgroups of people. These biases often stem from the…
Feed-forward deep neural networks have been used extensively in various machine learning applications. Developing a precise understanding of the underling behavior of neural networks is crucial for their efficient deployment. In this paper,…
Machine learning models often inherit biases from historical data, raising critical concerns about fairness and accountability. Conventional fairness interventions typically require access to sensitive attributes like gender or race, but…