Author: Abigail Kelly

Authors:Manuel R. Torres、Parisa Zehtab、Michael Cashmore、Daniele Magazzeni、Manuela Veloso ArXiv：https://arxiv.org/abs/2408.13208 Introduction Background One of the most amazing implementations of AI in so many areas such as scheduling, resources allocation, robotics and autonomous vehicles is automated decision-making. Traditionally, these decision-making processes are designed to maximize an overall benefit (or minimize a cost). But as AI systems are more and more embedded into society, it becomes essential to ensure that those system function correctly. Problem Statement While decision-making fairness is a well-studied area, existing approaches mostly consider static one-time decisions. In this paper, we take a new perspective and develop the notion of temporal…

Authors: Jaylin Herskovitz、Andi Xu、Rahaf Alharbi、Anhong Guo Paper: https://arxiv.org/abs/2408.10499 Introduction In the realm of assistive technologies, visual access tools have significantly improved the lives of blind and visually impaired individuals. However, these tools often cater to common scenarios and lack the flexibility to be customized for unique, personal needs. This limitation imposes additional cognitive load on users, who must adapt their usage to fit the tool’s capabilities. Addressing this gap, the paper introduces ProgramAlly, a novel end-user programming tool designed to empower blind users to create and customize visual information filtering programs. ProgramAlly leverages three end-user programming approaches: block-based programming, natural…

Authors: Matthew Morris、David J. Tena Cucala、Bernardo Cuenca Grau、Ian Horrocks Paper: https://arxiv.org/abs/2408.10261 Introduction Knowledge graphs (KGs) are structured knowledge bases where nodes and edges represent entities and their relationships, respectively. They are widely used in various applications, but often suffer from incompleteness. To address this, the field of KG completion has emerged, aiming to predict missing facts in KGs. Graph neural networks (GNNs), particularly Relational Graph Convolutional Networks (R-GCNs), have shown promise in this area. However, the explainability of their predictions remains a challenge. This study investigates whether R-GCNs can learn sound rules that explain their predictions and proposes methods to…

Authors: Tianyu Zhang、Yuxiang Ren、Chengbin Hou、Hairong Lv、Xuegong Zhang Paper: https://arxiv.org/abs/2408.10124 Introduction Molecular property prediction is a cornerstone of drug discovery, enabling the identification and optimization of potential drug candidates. Traditionally, this task has relied heavily on biochemical expertise and extensive domain knowledge, which is both time-consuming and costly to acquire. Recent advancements in deep learning, particularly the use of pre-trained models, have shown promise in automating and enhancing molecular property prediction. However, these models often require large amounts of labeled data and domain-specific knowledge, posing significant challenges. Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and generating general knowledge…

Authors: Rasha Alshawi、Md Meftahul Ferdaus、Md Tamjidul Hoque、Kendall Niles、Ken Pathak、Steve Sloan、Mahdi Abdelguerfi Paper: https://arxiv.org/abs/2408.08879 Introduction Accurate detection and segmentation of defects in culverts and sewer pipes are crucial for effective infrastructure management. Undetected defects can lead to severe consequences, including structural failures, increased maintenance costs, and environmental hazards. Traditional defect detection methods involve manual inspection, which is time-consuming and prone to human error. Advanced computer vision techniques, like semantic segmentation, offer potential to automate these processes, providing pixel-level labels to objects or regions in an image, making it a powerful tool for understanding and analyzing visual scenes. Despite its potential, applying…

Authors: Alessio Devoto、Federico Alvetreti、Jary Pomponi、Paolo Di Lorenzo、Pasquale Minervini、Simone Scardapane Paper: https://arxiv.org/abs/2408.08670 Introduction Vision Transformers (ViTs) have emerged as a powerful paradigm in computer vision, leveraging the self-attention mechanism to capture long-range dependencies in images. However, the fine-tuning process of ViTs is resource-intensive, posing challenges for deployment in edge or low-energy applications. This paper introduces ALaST (Adaptive Layer Selection Fine-Tuning for Vision Transformers), a method designed to optimize the fine-tuning process by adaptively allocating computational resources to different layers based on their importance. This approach significantly reduces computational cost, memory load, and training time. Background on Vision Transformer A Vision Transformer…

Authors: Abdur R. Fayjie、Jutika Borah、Florencia Carbone、Jan Tack、Patrick Vandewalle Paper: https://arxiv.org/abs/2408.08432 Predictive Uncertainty Estimation in Deep Learning for Lung Carcinoma Classification in Digital Pathology under Real Dataset Shifts Introduction Deep learning (DL) has revolutionized various fields, including digital pathology and medical image classification. However, the reliability of DL models in clinical decision-making is often compromised due to distributional shifts in real-world data. This paper investigates the role of predictive uncertainty estimation in enhancing the robustness of DL models for lung carcinoma classification under different dataset shifts. Background Related Work Uncertainty estimation in DL is crucial for providing calibrated predictions and enhancing…

Authors: Genet Asefa Gesese、Jörg Waitelonis、Zongxiong Chen、Sonja Schimmler、Harald Sack Paper: https://arxiv.org/abs/2408.08698 Introduction The German National Research Data Infrastructure (NFDI) is a non-profit association established to coordinate the creation of a national research data infrastructure. It encompasses 26 consortia covering a broad spectrum of scientific disciplines, including cultural sciences, social sciences, humanities, engineering, life sciences, and natural sciences. These consortia share common goals and concepts, such as their members, structure, data repositories, and services. To enhance interoperability across these consortia, the NFDICore ontology has been developed. This mid-level ontology represents metadata related to NFDI resources, including individuals, organizations, projects, and data portals.…

Authors: Yuhong Deng、David Hsu Paper: https://arxiv.org/abs/2408.08160 Introduction The dream of an intelligent household robot that can manage and organize clothes is becoming more tangible with recent advancements in robotics. However, the challenge remains in developing a robot that can generalize its manipulation skills to a wide range of clothes and tasks. Traditional methods often fail when faced with new tasks or different types of clothing. This paper introduces a novel approach that leverages language instructions and a hierarchical learning method to enhance the generalization of clothes manipulation tasks. Challenges in Clothes Manipulation Clothes manipulation is inherently complex due to the…

Authors: Kaiser Sun、Mark Dredze Paper: https://arxiv.org/abs/2408.06663 Introduction The rise of large language models (LLMs) has significantly transformed the field of natural language processing (NLP). These models are typically trained using a two-stage process: pre-training on a large text corpus followed by fine-tuning to align the model with specific tasks or human preferences. This paper investigates the relationship between these two stages by fine-tuning multiple intermediate pre-trained model checkpoints. The study aims to understand how pre-training and fine-tuning interact and affect the resulting model’s performance. Background: Model Training Pre-training Pre-training involves training a model on a massive text corpus to learn…