Related papers: Simon Says: Evaluating and Mitigating Bias in Prun…

Convolutional Neural Networks (CNN) have become de fact state-of-the-art for the main computer vision tasks. However, due to the complex underlying structure their decisions are hard to understand which limits their use in some context of…

Artificial intelligence systems, especially those using machine learning, are being deployed in domains from hiring to loan issuance in order to automate these complex decisions. Judging both the effectiveness and fairness of these AI…

Biases can filter into AI technology without our knowledge. Oftentimes, seminal deep learning networks champion increased accuracy above all else. In this paper, we attempt to alleviate biases encountered by semantic segmentation models in…

Verification of deep neural networks has witnessed a recent surge of interest, fueled by success stories in diverse domains and by abreast concerns about safety and security in envisaged applications. Complexity and sheer size of such…

While deep models have proved successful in learning rich knowledge from massive well-annotated data, they may pose a privacy leakage risk in practical deployment. It is necessary to find an effective trade-off between high utility and…

Automatic Speech Recognition (ASR) has seen remarkable advancements with deep neural networks, such as Transformer and Conformer. However, these models typically have large model sizes and high inference costs, posing a challenge to deploy…

Assessments of algorithmic bias in large language models (LLMs) are generally catered to uncovering systemic discrimination based on protected characteristics such as sex and ethnicity. However, there are over 180 documented cognitive…

Channel pruning is one of the predominant approaches for deep model compression. Existing pruning methods either train from scratch with sparsity constraints on channels, or minimize the reconstruction error between the pre-trained feature…

Knowledge distillation is an effective approach to leverage a well-trained network or an ensemble of them, named as the teacher, to guide the training of a student network. The outputs from the teacher network are used as soft labels for…

Real-world driving involves intricate interactions among vehicles navigating through dense traffic scenarios. Recent research focuses on enhancing the interaction awareness of autonomous vehicles to leverage these interactions in…

Neural network pruning typically removes connections or neurons from a pretrained converged model; while a new pruning paradigm, pruning at initialization (PaI), attempts to prune a randomly initialized network. This paper offers the first…

Channel (or 3D filter) pruning serves as an effective way to accelerate the inference of neural networks. There has been a flurry of algorithms that try to solve this practical problem, each being claimed effective in some ways. Yet, a…

Structured pruning compresses neural networks by reducing channels (filters) for fast inference and low footprint at run-time. To restore accuracy after pruning, fine-tuning is usually applied to pruned networks. However, too few remaining…

Recent research has identified discriminatory behavior of automated prediction algorithms towards groups identified on specific protected attributes (e.g., gender, ethnicity, age group, etc.). When deployed in real-world scenarios, such…

Positional bias (PB), manifesting as non-uniform sensitivity across different contextual locations, significantly impairs long-context comprehension and processing capabilities. Previous studies have addressed PB either by modifying the…

Machine learning models often make predictions based on biased features such as gender, race, and other social attributes, posing significant fairness risks, especially in societal applications, such as hiring, banking, and criminal…

Network pruning reduces the size of neural networks by removing (pruning) neurons such that the performance drop is minimal. Traditional pruning approaches focus on designing metrics to quantify the usefulness of a neuron which is often…

Dataset distillation methods have achieved remarkable success in distilling a large dataset into a small set of representative samples. However, they are not designed to produce a distilled dataset that can be effectively used for…

Spiking neural networks (SNNs), which are brain-inspired and spike-driven, achieve high energy efficiency. However, a performance gap between SNNs and artificial neural networks (ANNs) still remains. Knowledge distillation (KD) is commonly…

Classical learning theory suggests that the optimal generalization performance of a machine learning model should occur at an intermediate model complexity, with simpler models exhibiting high bias and more complex models exhibiting high…