AI Open最新文献

{"title":"FedGPA: Federated Learning with Global Personalized Aggregation","authors":"Zongfu Han ,&nbsp;Yu Feng ,&nbsp;Yifan Zhu ,&nbsp;Zhen Tian ,&nbsp;Fangyu Hao ,&nbsp;Meina Song","doi":"10.1016/j.aiopen.2025.03.001","DOIUrl":"10.1016/j.aiopen.2025.03.001","url":null,"abstract":"<div><div>A significant challenge in Federated Learning (FL) is addressing the heterogeneity of local data distribution across clients. Personalized Federated Learning (PFL), an emerging method aimed at overcoming data heterogeneity, can either integrate personalized components into the global model or train multiple models to achieve personalization. However, little research has simultaneously considered both directions. One such approach involves adopting a weighted aggregation method to generate personalized models, where the weights are determined by solving an optimization problem among different clients. In brief, previous works either neglect the use of global information during local representation learning or simply treat the personalized model as learning a set of individual weights. In this work, we initially decouple the model into a feature extractor, associated with generalization, and a classifier, linked to personalization. Subsequently, we conduct local–global alignment based on prototypes to leverage global information for learning better representations. Moreover, we fully utilize these representations to calculate the distance between clients and develop individual aggregation strategies for feature extractors and classifiers, respectively. Finally, extensive experimental results on five benchmark datasets under three different heterogeneous data scenarios demonstrate the effectiveness of our proposed FedGPA.</div></div>","PeriodicalId":100068,"journal":{"name":"AI Open","volume":"6 ","pages":"Pages 82-92"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143847949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SafeCast: Risk-responsive motion forecasting for autonomous vehicles","authors":"Haicheng Liao ,&nbsp;Hanlin Kong ,&nbsp;Zhenning Li ,&nbsp;Chengzhong Xu","doi":"10.1016/j.aiopen.2025.08.001","DOIUrl":"10.1016/j.aiopen.2025.08.001","url":null,"abstract":"<div><div>Accurate motion forecasting is essential for the safety and reliability of autonomous driving (AD) systems. While existing methods have made significant progress, they often overlook explicit safety constraints and struggle to capture the complex interactions among traffic agents, environmental factors, and motion dynamics. To address these challenges, we present SafeCast, a risk-responsive motion forecasting model that integrates safety-aware decision-making with uncertainty-aware adaptability. SafeCast is the first to incorporate the Responsibility-Sensitive Safety (RSS) framework into motion forecasting, encoding interpretable safety rules — such as safe distances and collision avoidance — based on traffic norms and physical principles. To further enhance robustness, we introduce the Graph Uncertainty Feature (GUF), a graph-based module that injects learnable noise into Graph Attention Networks, capturing real-world uncertainties and enhancing generalization across diverse scenarios. We evaluate SafeCast on four real-world benchmark datasets — Next Generation Simulation (NGSIM), Highway Drone (HighD), ApolloScape, and the Macao Connected Autonomous Driving (MoCAD) — covering highway, urban, and mixed-autonomy traffic environments. Our model achieves state-of-the-art (SOTA) accuracy while maintaining a lightweight architecture and low inference latency, underscoring its potential for real-time deployment in safety-critical AD systems.</div></div>","PeriodicalId":100068,"journal":{"name":"AI Open","volume":"6 ","pages":"Pages 118-129"},"PeriodicalIF":14.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144907874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Methodologies and their comparison in complex compound aspect-based sentiment analysis: A survey","authors":"Faiz Ghifari Haznitrama,&nbsp;Ho-Jin Choi,&nbsp;Chin-Wan Chung","doi":"10.1016/j.aiopen.2025.02.002","DOIUrl":"10.1016/j.aiopen.2025.02.002","url":null,"abstract":"<div><div>Sentiment analysis as a part of natural language processing (NLP) has received much attention following the demand to understand people’s opinions. Aspect-based sentiment analysis (ABSA) is a fine-grained task from sentiment analysis that aims to classify the sentiment at the aspect level. Throughout the years, researchers have formulated ABSA into various tasks for different scenarios. Unlike early works, current ABSA tasks utilize many elements to provide more details to produce informative results. However, it is difficult to completely explore the works of ABSA because of the many different tasks, terms, and results. This paper surveyed recent studies on ABSA, specifically on its complex compound tasks. We investigated some key elements, problem formulations, and datasets currently utilized by most ABSA communities. We focused on reviewing the latest methodologies and worked to find the current <em>state-of-the-art</em> methodologies by performing a comparative analysis. From our study, we found that there has been a shift to generative methods in solving the ABSA problem, which signifies the evolving emphasis on holistic, end-to-end approaches. Finally, we identified some open challenges and future directions for ABSA research.</div></div>","PeriodicalId":100068,"journal":{"name":"AI Open","volume":"6 ","pages":"Pages 53-69"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143601111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DFM: Dialogue foundation model for universal large-scale dialogue-oriented task learning","authors":"Zhi Chen ,&nbsp;Da Ma ,&nbsp;Hanqi Li ,&nbsp;Lu Chen ,&nbsp;Jiabao Ji ,&nbsp;Yuncong Liu ,&nbsp;Bei Chen ,&nbsp;Mengyue Wu ,&nbsp;Su Zhu ,&nbsp;Xin Dong ,&nbsp;Fujiang Ge ,&nbsp;Qingliang Miao ,&nbsp;Jian-Guang Lou ,&nbsp;Shuai Fan ,&nbsp;Kai Yu","doi":"10.1016/j.aiopen.2025.04.001","DOIUrl":"10.1016/j.aiopen.2025.04.001","url":null,"abstract":"<div><div>Building a universal conversational agent has been a long-standing goal of the dialogue research community. Most previous works only focus on a small set of dialogue tasks. In this work, we aim to build a unified dialogue foundation model (DFM) which can be used to solve massive diverse dialogue tasks. To achieve this goal, a large-scale well-annotated dialogue dataset with rich task diversity (DialogZoo) is collected. We introduce a framework to unify all dialogue tasks and propose novel auxiliary self-supervised tasks to achieve stable training of DFM on the highly diverse large scale DialogZoo corpus. Experiments show that, compared with models of the same size, DFM can achieve competitive performance on very rich cross-domain downstream dialogue tasks. Furthermore, when scaling to large language models, DFM remains effective. This demonstrates that DFM largely extends the ability of unified dialogue pre-trained model.</div></div>","PeriodicalId":100068,"journal":{"name":"AI Open","volume":"6 ","pages":"Pages 108-117"},"PeriodicalIF":14.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144828236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Proactive Recommendation in Social Networks: Steering user interest with causal inference","authors":"Hang Pan ,&nbsp;Shuxian Bi ,&nbsp;Wenjie Wang ,&nbsp;Haoxuan Li ,&nbsp;Peng Wu ,&nbsp;Fuli Feng","doi":"10.1016/j.aiopen.2025.08.003","DOIUrl":"10.1016/j.aiopen.2025.08.003","url":null,"abstract":"<div><div>Recommending items that solely cater to users’ historical interests narrows users’ horizons. Recent works have considered steering target users beyond their historical interests by directly adjusting items exposed to them. However, the recommended items for direct steering might not align perfectly with the evolution of users’ interests, detrimentally affecting the target users’ experience.</div><div>To avoid this issue, we propose a new task named <em>Proactive Recommendation in Social Networks</em> (<strong>PRSN</strong>) that indirectly steers users’ interest by utilizing the influence of social neighbors, <em>i.e.,</em>indirect steering by adjusting the exposure of a target item to target users’ neighbors. The key to PRSN lies in answering an interventional question: <em>what would a target user’s feedback be on a target item if the item is exposed to the user’s different neighbors?</em> To answer this question, we resort to causal inference and formalize PRSN as: (1) estimating the potential feedback of a user on an item, under the network interference by the item’s exposure to the user’s neighbors; and (2) adjusting the exposure of a target item to target users’ neighbors to trade-off steering performance and the damage to the neighbors’ experience. To this end, we propose a <strong>N</strong>eighbor <strong>I</strong>nterference <strong>Rec</strong>ommendation (<strong>NIRec</strong>) framework with two modules: (1) an interference representation-based estimation module for modeling potential feedback; (2) a post-learning-based optimization module for adjusting a target item’s exposure to trade-off steering performance and the neighbors’ experience through greedy search. We conduct extensive semi-simulation experiments on real-world datasets, validating the steering effectiveness of NIRec. The code is available at <span><span>https://github.com/HungPaan/NIRec</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":100068,"journal":{"name":"AI Open","volume":"6 ","pages":"Pages 130-141"},"PeriodicalIF":14.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145120788","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ChatLLM network: More brains, more intelligence","authors":"Rui Hao ,&nbsp;Linmei Hu ,&nbsp;Weijian Qi ,&nbsp;Qingliu Wu ,&nbsp;Yirui Zhang ,&nbsp;Liqiang Nie","doi":"10.1016/j.aiopen.2025.01.001","DOIUrl":"10.1016/j.aiopen.2025.01.001","url":null,"abstract":"<div><div>Dialogue-based language models mark a huge milestone in the field of artificial intelligence, by their impressive ability to interact with users, as well as a series of challenging tasks prompted by customized instructions. However, the prevalent large-scale dialogue-based language models like ChatGPT still have room for improvement, such as unstable responses to questions and the inability to think cooperatively like humans. Considering the ability of dialogue-based language models in conversation and their inherent randomness in thinking, we propose ChatLLM network that allows multiple dialogue-based language models to interact, provide feedback, and think together. We design a network of ChatLLMs, consisting multiple layers of language models. Specifically, individual instances of language model may possess distinct perspectives towards the same problem, and by consolidating these diverse viewpoints via a separate language model, the ChatLLM network system can conduct decision-making more objectively and comprehensively. In addition, a language-based feedback mechanism comparable to backpropagation is devised to update the outputs of the language models within the network. This stratified system of interaction can be analogized to the relationship between leaders and employees in a social organization, where collective decision-making often yields superior judgments or resolutions. Experiments on datasets demonstrate that our network attains significant improvements in problem-solving, leading to observable progress amongst each member.</div></div>","PeriodicalId":100068,"journal":{"name":"AI Open","volume":"6 ","pages":"Pages 45-52"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143420049","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-scale texture loss for CT denoising with GANs","authors":"Francesco Di Feola ,&nbsp;Lorenzo Tronchin ,&nbsp;Valerio Guarrasi ,&nbsp;Paolo Soda","doi":"10.1016/j.aiopen.2025.09.001","DOIUrl":"10.1016/j.aiopen.2025.09.001","url":null,"abstract":"<div><div>Generative Adversarial Networks (GANs) have proved as a powerful framework for denoising applications in medical imaging. However, GAN-based denoising algorithms still suffer from limitations in capturing complex relationships within the images. In this regard, the loss function plays a crucial role in guiding the image generation process, encompassing how much a synthetic image differs from a real image. To grasp highly complex and non-linear textural relationships in the training process, this work presents a novel approach to capture and embed multi-scale texture information into the loss function. Our method introduces a differentiable multi-scale texture representation of the images dynamically aggregated by a self-attention layer, thus exploiting end-to-end gradient-based optimization. We validate our approach by carrying out extensive experiments in the context of low-dose CT denoising, a challenging application that aims to enhance the quality of noisy CT scans. We utilize three publicly available datasets, including one simulated and two real datasets. The results are promising as compared to other well-established loss functions, being also consistent across three different GAN architectures. The code is available at: <span><span>https://github.com/trainlab/MSTLF-TextureLoss</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":100068,"journal":{"name":"AI Open","volume":"6 ","pages":"Pages 142-154"},"PeriodicalIF":14.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145157276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Solving the enigma: Enhancing faithfulness and comprehensibility in explanations of deep networks","authors":"Michail Mamalakis ,&nbsp;Antonios Mamalakis ,&nbsp;Ingrid Agartz ,&nbsp;Lynn Egeland Mørch-Johnsen ,&nbsp;Graham K. Murray ,&nbsp;John Suckling ,&nbsp;Pietro Lio","doi":"10.1016/j.aiopen.2025.02.001","DOIUrl":"10.1016/j.aiopen.2025.02.001","url":null,"abstract":"<div><div>The accelerated progress of artificial intelligence (AI) has popularized deep learning models across various domains, yet their inherent opacity poses challenges, particularly in critical fields like healthcare, medicine, and the geosciences. Explainable AI (XAI) has emerged to shed light on these ’black box’ models, aiding in deciphering their decision-making processes. However, different XAI methods often produce significantly different explanations, leading to high inter-method variability that increases uncertainty and undermines trust in deep networks’ predictions. In this study, we address this challenge by introducing a novel framework designed to enhance the explainability of deep networks through a dual focus on maximizing both accuracy and comprehensibility in the explanations. Our framework integrates outputs from multiple established XAI methods and leverages a non-linear neural network model, termed the ‘Explanation optimizer,’ to construct a unified, optimal explanation. The optimizer uses two primary metrics — faithfulness and complexity — to evaluate the quality of the explanations. Faithfulness measures the accuracy with which the explanation reflects the network’s decision-making, while complexity assesses the comprehensibility of the explanation. By balancing these metrics, the optimizer provides explanations that are both accurate and accessible, addressing a central limitation in current XAI methods. Through experiments on multi-class and binary classification tasks in both 2D object and 3D neuroscience imaging, we validate the efficacy of our approach. Our explanation optimizer achieved superior faithfulness scores, averaging 155% and 63% higher than the best-performing individual XAI methods in the 3D and 2D applications, respectively, while also reducing complexity to enhance comprehensibility. These results demonstrate that optimal explanations based on specific quality criteria are achievable, offering a solution to the issue of inter-method variability in the current XAI literature and supporting more trustworthy deep network predictions.</div></div>","PeriodicalId":100068,"journal":{"name":"AI Open","volume":"6 ","pages":"Pages 70-81"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143628964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Scalable graph attention-based instance selection via mini-batch sampling and hierarchical hashing","authors":"Zahiriddin Rustamov ,&nbsp;Ayham Zaitouny ,&nbsp;Nazar Zaki","doi":"10.1016/j.aiopen.2025.08.004","DOIUrl":"10.1016/j.aiopen.2025.08.004","url":null,"abstract":"<div><div>Instance selection (IS) addresses the critical challenge of reducing dataset size while keeping informative characteristics, becoming increasingly important as datasets grow to millions of instances. Current IS methods often struggle with capturing complex relationships in high-dimensional spaces and scale with large datasets. This paper introduces a graph attention-based instance selection (GAIS) method that uses attention mechanisms to identify informative instances through their structural relationships in graph representations. We present two approaches for scalable graph construction: a distance-based mini-batch sampling technique that achieves dataset-size-independent complexity through strategic batch processing, and a hierarchical hashing approach that enables efficient similarity computation through random projections. The mini-batch approach keeps class distributions through stratified sampling, while the hierarchical hashing method captures relationships at multiple granularities through single-level, multi-level, and multi-view variants. Experiments across 39 datasets show that GAIS achieves reduction rates above 96% while maintaining or improving model performance relative to state-of-the-art IS methods. The findings show that the distance-based mini-batch approach offers an optimal efficiency for large-scale datasets, while multi-view variants excel on complex, high-dimensional data, demonstrating that attention-based importance scoring can effectively identify instances important for maintaining decision boundaries while avoiding computationally prohibitive pairwise comparisons. The code is publicly available at <span><span>https://github.com/zahiriddin-rustamov/gais</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":100068,"journal":{"name":"AI Open","volume":"6 ","pages":"Pages 167-182"},"PeriodicalIF":14.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Client: Cross-variable linear integrated enhanced transformer for multivariate long-term time series forecasting","authors":"Jiaxin Gao ,&nbsp;Wenbo Hu ,&nbsp;Dongxiao Zhang ,&nbsp;Yuntian Chen","doi":"10.1016/j.aiopen.2025.06.001","DOIUrl":"10.1016/j.aiopen.2025.06.001","url":null,"abstract":"<div><div>Long-term time series forecasting (LTSF) is crucial in modern society, playing a pivotal role in facilitating long-term planning and developing early warning systems. While many Transformer-based models have recently been introduced for LTSF, a doubt has been raised regarding the effectiveness of attention modules in capturing cross-time dependencies. In this study, we design a mask-series experiment to validate this assumption and subsequently propose the ”Cross-variable Linear Integrated ENhanced Transformer for Multivariate Long-Term Time Series Forecasting” (<em>Client</em>), an advanced model that outperforms both traditional Transformer-based models and linear models. <em>Client</em> employs the linear module to learn trend information and the enhanced Transformer module to capture cross-variable dependencies. Meanwhile, the cross-variable Transformer module in <em>Client</em> simplifies the embedding and position encoding layers and replaces the decoder module with a projection layer. Extensive experiments with nine real-world datasets have confirmed the SOTA performance of <em>Client</em> with the least computation time and memory consumption compared with the previous Transformer-based models. Our code is available at <span><span>https://github.com/daxin007/Client</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":100068,"journal":{"name":"AI Open","volume":"6 ","pages":"Pages 93-107"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144656936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}