Text-attributed graphs (TAGs) have become a key form of graph-structured data in modern data management and analytics, combining structural relationships with rich textual semantics for diverse applications. However, the effectiveness of analytical models, particularly graph neural networks (GNNs), is highly sensitive to data quality. Our empirical analysis shows that both conventional and LLM-enhanced GNNs degrade notably under textual, structural, and label imperfections, underscoring TAG quality as a key bottleneck for reliable analytics. Existing studies have explored data-level optimization for TAGs, but most focus on specific degradation types and target a single aspect like structure or label, lacking a systematic and comprehensive perspective on data quality improvement. To address this gap, we propose LAGA (Large Language and Graph Agent), a unified multi-agent framework for comprehensive TAG quality optimization. LAGA formulates graph quality control as a data-centric process, integrating detection, planning, action, and evaluation agents into an automated loop. It holistically enhances textual, structural, and label aspects through coordinated multi-modal optimization. Extensive experiments on 5 datasets and 16 baselines across 9 scenarios demonstrate the effectiveness, robustness and scalability of LAGA, confirming the importance of data-centric quality optimization for reliable TAG analytics.
用有限的人力分析更好的时间序列是学术界和工业界感兴趣的。在业务场景的驱动下,我们为WSDM Cup 2020组织了第一次自动时间序列回归挑战赛(AutoSeries)。我们提出了它的设计,分析和事后实验。代码提交要求排除了参与者在硬件和时间限制下跨许多数据集进行任何手动干预、测试解决方案的自动化机器学习功能的可能性。我们准备了来自不同应用领域(销售、电力消耗、空气质量、交通和停车)的10个数据集,其中包括缺失数据、混合连续变量和分类变量以及各种采样率。每个数据集都被分成训练序列和测试序列(这是流式的,允许模型不断适应)。时间序列回归的设定与经典预测的不同之处在于,当前时间的协变量是已知的。参与者在解决这个AutoSeries问题方面取得了很大的进步,从样本提交的性能跳跃以及与AutoGluon的事后比较可以看出。使用了简单而有效的方法,基于特征工程,LightGBM和随机搜索超参数调整,解决了挑战的各个方面。我们的事后分析显示,提供额外的时间并没有产生显着的改善。获奖者的代码是开源的https://github.com/NehzUx/AutoSeries。
Lean Meets Theoretical Computer Science: Scalable Synthesis of Theorem Proving Challenges in Formal-Informal Pairs
D-CHAB, ETH Zurich, Zurich, Switzerland.;D-INFK, ETH Zurich, Zurich, Switzerland.;ETH AI Center, Zurich, Switzerland.;University of Pennsylvania, PA, USA.;Independent Researcher.
Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models
School of Cyber Science and Technology, Shandong University(山东大学网络科学与技术学院);Netflix Eyeline Studios;State Key Laboratory of Cryptography and Digital Economy Security, Shandong University(山东大学密码与数字经济安全国家重点实验室);Shandong Key Laboratory of Artificial Intelligence Security, Shandong University(山东省人工智能安全重点实验室)
When Wireless Security Meets Machine Learning: Motivation, Challenges, and Research Directions
Intelligent Automation, Inc.(智能自动化公司);Virginia Tech(弗吉尼亚理工大学);University of California, San Diego(加利福尼亚大学圣地亚哥分校);Naval Research Laboratory(海军研究实验室);University of South Florida(南佛罗里达大学)
Active Learning for Automated Visual Inspection of Manufactured Products
University of Ljubljana(卢布尔雅那大学);Jožef Stefan International Postgraduate School(约热夫·斯特凡国际研究生院);Philips Consumer Lifestyle BV(飞利浦消费生活方式有限公司);Qlector d.o.o.(Qlector有限责任公司);Jožef Stefan Institute(约热夫·斯特凡研究所)
Using External Off-Policy Speech-To-Text Mappings in Contextual End-To-End Automated Speech Recognition
University of California, Berkeley(加州大学伯克利分校);Amazon Alexa AI(亚马逊Alexa人工智能部门)
尽管自动语音识别(ASR)模型的泛化性能有所改进,但针对下游任务的专用ASR模型仍然是一项具有挑战性的任务,这主要是由于数据可用性降低(需要增加数据收集)和数据分布快速变化(需要更频繁的模型微调)。在这项工作中,我们研究了利用外部知识的潜力,特别是通过使用文本到语音方法生成的非策略键值存储,以允许灵活的训练后适应新的数据分布。在我们的方法中,从文本到语音捕获的音频嵌入,以及语义文本嵌入,用于通过基于近似k-最近邻(KNN)的专注融合步骤来偏置ASR。我们在LibiriSpeech和内部语音助手/搜索数据集上的实验表明,与微调基线相比,所提出的方法可以将域适应时间减少多达1 K GPU小时,同时提供高达3%的WER改进,这表明在具有挑战性的零和Few-Shot场景中适应生产ASR系统的方法很有前途。