Related papers: Attention Consistency Regularization for Interpret…

Early-Exit (EE) is a Large Language Model (LLM) architecture that accelerates inference by allowing easier tokens to be generated using only a subset of the model's layers. However, traditional batching frameworks are ill-suited for EE…

Distantly supervised relation extraction intrinsically suffers from noisy labels due to the strong assumption of distant supervision. Most prior works adopt a selective attention mechanism over sentences in a bag to denoise from wrongly…

We propose a multi-explanation graph attention network (MEGAN). Unlike existing graph explainability methods, our network can produce node and edge attributional explanations along multiple channels, the number of which is independent of…

Deep Neural Networks (DNNs) are generally designed as sequentially cascaded differentiable blocks/layers with a prediction module connected only to its last layer. DNNs can be attached with prediction modules at multiple points along the…

Disruptions at critical logistics nodes pose severe risks to global supply chains, yet existing risk prediction systems typically prioritize forecasting accuracy without providing operationally interpretable early warnings. This paper…

As a simple technique to accelerate inference of large-scale pre-trained models, early exiting has gained much attention in the NLP community. It allows samples to exit early at internal classifiers without passing through the entire model.…

Large language models (LLMs) exhibit exceptional performance across various downstream tasks. However, they encounter limitations due to slow inference speeds stemming from their extensive parameters. The early exit (EE) is an approach that…

Neural network models have been very successful at achieving high accuracy on natural language inference (NLI) tasks. However, as demonstrated in recent literature, when tested on some simple adversarial examples, most of the models suffer…

Dynamic retrieval-augmented generation (RAG) allows large language models (LLMs) to fetch external knowledge on demand, offering greater adaptability than static RAG. A central challenge in this setting lies in determining the optimal…

Adaptive inference is a simple method for reducing inference costs. The method works by maintaining multiple classifiers of different capacities, and allocating resources to each test instance according to its difficulty. In this work, we…

Deep neural network (DNN) models are increasingly popular in edge video analytic applications. However, the compute-intensive nature of DNN models pose challenges for energy-efficient inference on resource-constrained edge devices. Most…

The deployment of pre-trained perception models in novel environments often leads to performance degradation due to distributional shifts. Although recent artificial intelligence approaches for metacognition use logical rules to…

Regularizing neural networks is important for anticipating model behavior in regions of the data space that are not well represented. In this work, we propose a regularization technique for enforcing a level of smoothness in the mapping…

In recent years, new regularization methods based on (deep) neural networks have shown very promising empirical performance for the numerical solution of ill-posed problems, e.g., in medical imaging and imaging science. Due to the…

Depression is a major cause of global mental illness and significantly influences suicide rates. Timely and accurate diagnosis is essential for effective intervention. Electroencephalography (EEG) provides a non-invasive and accessible…

Accurate quantification of both aleatoric and epistemic uncertainties is essential when deploying Graph Neural Networks (GNNs) in high-stakes applications such as drug discovery and financial fraud detection, where reliable predictions are…

We propose Class Based Thresholding (CBT) to reduce the computational cost of early exit semantic segmentation models while preserving the mean intersection over union (mIoU) performance. A key idea of CBT is to exploit the…

Currently, attention mechanisms have garnered increasing attention in Graph Neural Networks (GNNs), such as Graph Attention Networks (GATs) and Graph Transformers (GTs). It is not only due to the commendable boost in performance they offer…

Chain-of-thought (CoT) reasoning improves large language model performance on complex tasks, but often produces excessively long and inefficient reasoning traces. Existing methods shorten CoTs using length penalties or global entropy…

EEG-based fatigue monitoring can effectively reduce the incidence of related traffic accidents. In the past decade, with the advancement of deep learning, convolutional neural networks (CNN) have been increasingly used for EEG signal…