Author: Leo Brown

Authors: Xiaodong Yang、Xiaoting Li、Huiyuan Chen、Yiwei Cai Paper: https://arxiv.org/abs/2408.10948 Introduction Graph Neural Networks (GNNs) have become powerful tools for graph understanding and mining, significantly advancing tasks like node classification and link prediction. However, GNNs are vulnerable to adversarial attacks, where carefully crafted perturbations on graph structures or node features can mislead trained models. Existing attack methods often rely on impractical assumptions or separate vital attack components, limiting their effectiveness. In response, the study introduces GAIM, an integrated adversarial attack method that unifies target node selection and feature perturbation into a single optimization problem, ensuring consistent and effective attacks on GNNs. Related…

Authors: Huifa Li、Jie Fu、Xinpeng Ling、Zhiyu Sun、Kuncan Wang、Zhili Chen Paper: https://arxiv.org/abs/2408.10511 Single-cell Curriculum Learning-based Deep Graph Embedding Clustering: A Detailed Interpretive Blog Introduction The rapid advancement of single-cell RNA sequencing (scRNA-seq) technologies has revolutionized our ability to investigate cellular-level tissue heterogeneity. This technology allows for the measurement of gene expressions in individual cells, providing detailed and high-resolution insights into the complex cellular landscape. The analysis of scRNA-seq data is crucial in various biomedical research areas, including identifying cell types and subtypes, studying developmental processes, investigating disease mechanisms, exploring immunological responses, and supporting drug development and personalized therapy. However, the analysis of…

Authors: Yuchao Liao、Tosiron Adegbija、Roman Lysecky Paper: https://arxiv.org/abs/2408.10428 Introduction The rapid advancement in technology and the increasing demand for custom hardware accelerators, driven by applications such as artificial intelligence and high-performance computing, necessitate innovative design methodologies. High-Level Synthesis (HLS) has emerged as a valuable approach for designing, synthesizing, and optimizing hardware systems. HLS allows designers to define systems at a high abstraction level, independent of low-level circuit specifics, and utilize HLS tools to produce optimized low-level hardware descriptions. Despite the advantages of HLS, the tools can still be time-consuming to use and demand considerable expertise. This paper explores the potential of…

Authors: Shiming Xie、Hong Chen、Fred Yu、Zeye Sun、Xiuyu Wu Paper: https://arxiv.org/abs/2408.10642 Minor SFT Loss for LLM Fine-Tuning to Increase Performance and Reduce Model Deviation Introduction Large Language Models (LLMs) have revolutionized the field of natural language processing, demonstrating remarkable capabilities in various tasks. However, aligning these models to human preferences and specific domain requirements remains a challenge. The paradigm of Instruct LLM, which includes Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), has been widely adopted to address this issue. While significant efforts have been made to enhance RLHF, SFT has primarily focused on data quality. This study introduces a…

Authors: Stefano Bannò、Kate Knill、Mark J. F. Gales Paper: https://arxiv.org/abs/2408.09565 Introduction In the realm of natural language processing (NLP), computer-assisted language learning (CALL) has emerged as a significant area of research. One of the critical components of CALL is providing feedback on grammatical usage to learners. Traditionally, this feedback has been delivered through grammatical error detection (GED) and grammatical error correction (GEC) systems. However, while these systems are beneficial, they often fall short of providing comprehensive feedback that can help learners understand and correct their mistakes more effectively. This paper introduces a novel approach to grammatical error feedback (GEF) that leverages…

Authors: Lorenzo Ceragioli、Pierpaolo Degano、Letterio Galletta、Luca Viganò Paper: https://arxiv.org/abs/2408.09516 Introduction In the realm of multiagent systems, autonomous agents interact to achieve both individual and collective goals. A central aspect of these interactions is the negotiation and agreement on resource exchanges. Modeling and formalizing these agreements pose significant challenges, particularly in capturing the dynamic behavior of agents and ensuring that resources are correctly handled. This study introduces exchange environments as a formal setting where agents specify and obey exchange policies. These policies are declarative statements about what resources they offer and what they require in return. The study also proposes a decidable…

Authors: Zhiwei Xu、Hangyu Mao、Nianmin Zhang、Xin Xin、Pengjie Ren、Dapeng Li、Bin Zhang、Guoliang Fan、Zhumin Chen、Changwei Wang、Jiangjin Yin Paper: https://arxiv.org/abs/2408.09501 Introduction Background Cooperative Multi-Agent Reinforcement Learning (MARL) has seen significant advancements and applications in various domains such as online ride-hailing platforms, drone swarm management, and energy system scheduling. However, a persistent challenge in MARL is the partial observability of the environment, where agents only have access to local observations. This limitation hinders their ability to make optimal decisions during decentralized execution. Problem Statement In partially observable Markov decision processes (POMDPs), the absence of global state awareness during execution can impede the agents’ ability to make…

Authors: Antonis Maronikolakis、Ana Peleteiro Ramallo、Weiwei Cheng、Thomas Kober Paper: https://arxiv.org/abs/2408.08907 Evaluating Conversational Agents in the Fashion Domain: What Should I Wear to a Party in a Greek Taverna? Introduction The advent of large language models (LLMs) and generative artificial intelligence has significantly transformed natural language processing, both in academia and industry. LLMs, developed through large-scale pretraining and reinforcement learning from human feedback, have demonstrated remarkable proficiency in language comprehension. This has led to their widespread use in customer support services, particularly in e-commerce and healthcare. In this study, we focus on the domain of online fashion retail and the use of…

Authors: Ruihui Hou、Shencheng Chen、Yongqi Fan、Lifeng Zhu、Jing Sun、Jingping Liu、Tong Ruan Paper: https://arxiv.org/abs/2408.10039 Introduction Clinical diagnosis is a critical aspect of medical practice, involving a continuous and evolving process that includes primary diagnosis, differential diagnosis, and final diagnosis. However, most existing clinical diagnostic tasks are single-step processes, which do not align with the complex multi-step diagnostic procedures found in real-world clinical settings. This paper introduces a multi-step diagnostic task and annotates a clinical diagnostic dataset called MSDiagnosis. The dataset includes primary diagnosis, differential diagnosis, and final diagnosis questions. Additionally, a novel framework combining forward inference, backward inference, reflection, and refinement is proposed…