Related papers: Towards Causality-Aware Inferring: A Sequential Di…
The technique of data augmentation (DA) is often used in machine learning for regularization purposes to better generalize under i.i.d. settings. In this work, we present a unifying framework with topics in causal inference to make a case…
Bias in speech emotion recognition (SER) systems often stems from spurious correlations between speaker characteristics and emotional labels, leading to unfair predictions across demographic groups. Many existing debiasing methods require…
Dialogue systems for Automatic Differential Diagnosis (ADD) have a wide range of real-life applications. These dialogue systems are promising for providing easy access and reducing medical costs. Building end-to-end ADD dialogue systems…
In routine care, individuals identified a priori as high-risk are usually tested for conditions more frequently. Protected attributes, such as sex or ethnicity may also determine testing frequency. Such heterogeneous detection rates across…
Inferring causality using longitudinal observational databases is challenging due to the passive way the data are collected. The majority of associations found within longitudinal observational data are often non-causal and occur due to…
Probabilistic linear discriminant analysis (PLDA) is a method used for biometric problems like speaker or face recognition that models the variability of the samples using two latent variables, one that depends on the class of the sample…
Explainable AI (XAI) aims to make AI systems more transparent, yet many practices emphasise mathematical rigour over practical user needs. We propose an alternative to this model-centric approach by following a design thinking process for…
Modern large language models (LLMs) are typically trained and deployed using structured role tags (e.g. system, user, assistant, tool) that explicitly mark the source of each piece of context. While these tags are essential for instruction…
Much attention and concern has been raised recently about bias and the use of machine learning algorithms in healthcare, especially as it relates to perpetuating racial discrimination and health disparities. Following an initial system…
Multimodalpersonalityunderstandingplaysacriticalroleinhuman centered artificial intelligence. Previous work mainly focus on learn-ing rich multimodal representations for video personality under standing. However, they often suffer from…
Despite ongoing efforts to defend neural classifiers from adversarial attacks, they remain vulnerable, especially to unseen attacks. In contrast, humans are difficult to be cheated by subtle manipulations, since we make judgments only based…
Psychological counseling is a fundamentally multimodal cognitive process in which clinicians integrate verbal content with visual and vocal cues to infer clients' mental states and respond empathically. However, most existing…
Scenario-based testing with driving simulators is extensively used to identify failing conditions of automated driving assistance systems (ADAS). However, existing studies have shown that repeated test execution in the same as well as in…
The ability to perform causal and counterfactual reasoning are central properties of human intelligence. Decision-making systems that can perform these types of reasoning have the potential to be more generalizable and interpretable.…
Autonomous vehicles must reason about spatial occlusions in urban environments to ensure safety without being overly cautious. Prior work explored occlusion inference from observed social behaviors of road agents, hence treating people as…
Algorithmic bias in medical imaging can perpetuate health disparities, yet its causes remain poorly understood in segmentation tasks. While fairness has been extensively studied in classification, segmentation remains underexplored despite…
We consider the estimation of average treatment effects in observational studies and propose a new framework of robust causal inference with unobserved confounders. Our approach is based on distributionally robust optimization and proceeds…
Methods for unsupervised domain adaptation (UDA) help to improve the performance of deep neural networks on unseen domains without any labeled data. Especially in medical disciplines such as histopathology, this is crucial since large…
Foundation models have brought changes to the landscape of machine learning, demonstrating sparks of human-level intelligence across a diverse array of tasks. However, a gap persists in complex tasks such as causal inference, primarily due…
When causal quantities cannot be point identified, researchers often pursue partial identification to quantify the range of possible values. However, the peculiarities of applied research conditions can make this analytically intractable.…