检索结果-内蒙古大学图书馆

proceedings of the 37th International Conference on Neural Information processing Systems

作者： Yanchao Tan Zihao Zhou Hang Lv Weiming Liu Carl Yang College of Computer and Data Science Fuzhou University Fuzhou China College of Computer Science Zhejiang University Hangzhou China Department of Computer Science Emory University Atlanta

graphs are widely used to model interconnected entities and improve downstream predictions in various real-world applications. However, real-world graphs nowadays are often associated with complex attributes on multiple types of nodes and even links that are hard to model uniformly, while the widely used graph neural networks (GNNs) often require sufficient training toward specific downstream predictions to achieve strong performance. In this work, we take a fundamentally different approach than GNNs, to simultaneously achieve deep joint modeling of complex attributes and flexible structures of real-world graphs and obtain unsupervised generic graph representations that are not limited to specific downstream predictions. Our framework, built on a natural integration of language models (LMs) and random walks (RWs), is straightforward, powerful and data-efficient. Specifically, we first perform attributed RWs on the graph and design an automated program to compose roughly meaningful textual sequences directly from the attributed RWs; then we fine-tune an LM using the RW-based textual sequences and extract embedding vectors from the LM, which encapsulates both attribute semantics and graph structures. In our experiments, we evaluate the learned node embeddings towards different downstream prediction tasks on multiple real-world attributed graph datasets and observe significant improvements over a comprehensive set of state-of-the-art unsupervised node embedding methods. We believe this work opens a door for more sophisticated technical designs and empirical evaluations toward the leverage of LMs for the modeling of real-world graphs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Referring Expression Comprehension: A Survey of methods and Datasets

arXiv

引用

arXiv 2020年

作者： Qiao, Yanyuan Deng, Chaorui Wu, Qi Australian Centre for Visual Technologies School of Computer Science University of Adelaide AdelaideSA5005 Australia

Referring expression comprehension (REC) aims to localize a target object in an image described by a referring expression phrased in natural language. Different from the object detection task that queried object labels have been pre-defined, the REC problem only can observe the queries during the test. It thus more challenging than a conventional computer vision problem. This task has attracted a lot of attention from both computer vision and natural language processing community, and several lines of work have been proposed, from CNN-RNN model, modular network to complex graph-based model. In this survey, we first examine the state of the art by comparing modern approaches to the problem. We classify methods by their mechanism to encode the visual and textual modalities. In particular, we examine the common approach of joint embedding images and expressions to a common feature space. We also discuss modular architectures and graph-based models that interface with structured graph representation. In the second part of this survey, we review the datasets available for training and evaluating REC systems. We then group results according to the datasets, backbone models, settings so that they can be fairly compared. Finally, we discuss promising future directions for the field, in particular the compositional referring expression comprehension that requires longer reasoning chain to address. Copyright © 2020, The Authors. All rights reserved.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Lang3DSG: language-based contrastive pre-training for 3D Scene graph prediction

Lang3DSG: Language-based contrastive pre-training for 3D Sce...

引用

International Conference on 3D Imaging, Modeling, processing, Visualization and Transmission (3DIMPVT)

作者： Sebastian Koch Pedro Hermosilla Narunas Vaskevicius Mirco Colosi Timo Ropinski Bosch Center for Artificial Intelligence Robert Bosch Corporate Research University of Ulm TU Vienna

ISBN: (数字)9798350362459

ISBN: (纸本)9798350362466

3D scene graphs are an emerging 3D scene representation, that models both the objects present in the scene as well as their relationships. However, learning 3D scene graphs is a challenging task because it requires not only object labels but also relationship annotations, which are very scarce in datasets. While it is widely accepted that pre-training is an effective approach to improve model performance in low data regimes, in this paper, we find that existing pre-training methods are ill-suited for 3D scene graphs. To solve this issue, we present the first language-based pre-training approach for 3D scene graphs, whereby we exploit the strong relationship between scene graphs and language. To this end, we leverage the language encoder of CLIP, a popular vision-language model, to distill its knowledge into our graph-based network. We formulate a contrastive pre-training, which aligns text embeddings of relationships (subject-predicate-object triplets) and predicted 3D graph features. Our method achieves state-of-the-art results on the main semantic 3D scene graph benchmark by showing improved effectiveness over pre-training baselines and outperforming all the existing fully supervised scene graph prediction methods by a significant margin. Furthermore, since our scene graph features are language-aligned, it allows us to query the language space of the features in a zero-shot manner. In this paper, we show an example of utilizing this property of the features to predict the room type of a scene without further training.

关键词： Training Point cloud compression Knowledge engineering Solid modeling Three-dimensional displays Semantics natural languages

来源：评论

学校读者我要写书评

暂无评论

Improving Generation of Sentiment Commonsense by Bias Mitigation

Improving Generation of Sentiment Commonsense by Bias Mitiga...

引用

International Conference on Big Data and Smart Computing (BIGCOMP)

作者： JinKyu Lee Jihie Kim Department of Artificial Intelligence Dongguk University Seoul Korea

Commonsense knowledge graphs (CSKG) are crucial for artificial intelligence systems to understand natural language. Recently, with the construction of COMET (Commonsense Transformer) and ATOMIC2020, a comprehensive coverage commonsense reasoning knowledge graph, CSKG research is increasingly vital in natural language understanding and reasoning. Since sentiment commonsense knowledge is understudied yet, our work focuses on improving the generation of sentiment commonsense in ATOMIC2020. We first show a problem in natural language generation that degrades the accuracy due to the unbalanced sentiment distribution in the dataset. Next, we propose the EDA (Easy Data Augmentation) and UDA(Unsupervised Data Augmentation) based methods that improve the accuracy through biased mitigation of the unbalanced dataset. Our experimental results show that EDA method has little effect on the accuracy, while UDA-based method has some accuracy improvements in ROUGE-I, ROUGE-2, and ROUGE-L.

关键词： Comets Tail Knowledge graphs Big Data Transformers natural language processing Task analysis

来源：评论

学校读者我要写书评

暂无评论

graph language Model (GLM): A new graph-based approach to detect social instabilities

arXiv

引用

arXiv 2024年

作者： de Oliveira, Wallyson Lemes Shamsaddini, Vahid Ghofrani, Ali Inda, Rahul Singh Veeramaneni, Jithendra Sai Voutaz, Étienne Giotto.ai SA Place de la Gare 4 Lausanne1004 Switzerland Armasuisse Feuerwerkerstrasse 39 Thun3602 Switzerland

This scientific report presents a novel methodology for the early prediction of important political events using News datasets. The methodology leverages natural language processing, graph theory, clique analysis, and semantic relationships to uncover hidden predictive signals within the data. Initially, we designed a preliminary version of the method and tested it on a few events. This analysis revealed limitations in the initial research phase. We then enhanced the model in two key ways: first, we added a filtration step to only consider politically relevant news before further processing;second, we adjusted the input features to make the alert system more sensitive to significant spikes in the data. After finalizing the improved methodology, we tested it on eleven events including US protests, the Ukraine war, and French protests. Results demonstrate the superiority of our approach compared to baseline methods. Through targeted refinements, our model can now provide earlier and more accurate predictions of major political events based on subtle patterns in news data. © 2024, CC BY-NC-ND.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Large language Models as Topological Structure Enhancers for Text-Attributed graphs

arXiv

引用

arXiv 2023年

作者： Sun, Shengyin Ren, Yuxiang Chen, Jiehao Ma, Chen Department of Computer Science City University of Hong Kong Hong Kong Advance Computing and Storage Lab Huawei Technologies Shanghai China China Academy of Industrial Internet Beijing China

Inspired by the success of Large language Models (LLMs) in natural language processing (NLP), recent works have begun investigating the potential of applying LLMs in graph learning. However, most existing work focuses on utilizing LLMs as node feature augmenters, leaving employing LLMs to enhance topological structures an understudied problem. In this paper, we are dedicated to leveraging LLMs’ text comprehension capability to enhance the topological structure of text-attributed graphs (TAGs). first, we propose using LLMs to help remove/add edges in the TAG. Specifically, we first let the LLM output the semantic similarity between nodes through delicate prompt designs, and then perform edge deletion/addition based on the similarity. Second, we propose using pseudo-labels generated by the LLM to improve graph topology;we introduce pseudo-label propagation as a regularization to guide the graph neural network (GNN) in learning proper edge weights. Finally, we incorporate the two aforementioned graph topological refinements into the GNN training, theoretically justify the benefits of the proposed topology refinements, and perform extensive experiments on real-world datasets to demonstrate the effectiveness of the proposed methods. Code available at https://***/sunshy-1/LLM4graphTopology. Copyright © 2023, The Authors. All rights reserved.

关键词： graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Every document owns its structure: Inductive text classification via graph neural networks

arXiv

引用

arXiv 2020年

作者： Zhang, Yufeng Yu, Xueli Cui, Zeyu Wu, Shu Wen, Zhongzhen Wang, Liang Institute of Automation Chinese Academy of Sciences Xi’an Jiaotong University

Text classification is fundamental in natural language processing (NLP), and graph Neural Networks (GNN) are recently applied in this task. However, the existing graph-based works can neither capture the contextual word relationships within each document nor fulfil the inductive learning of new words. In this work, to overcome such problems, we propose TextING1 for inductive text classification via GNN. We first build individual graphs for each document and then use GNN to learn the fine-grained word representations based on their local structures, which can also effectively produce embeddings for unseen words in the new document. Finally, the word nodes are incorporated as the document embedding. Extensive experiments on four benchmark datasets show that our method outperforms state-of-the-art text classification methods. Copyright © 2020, The Authors. All rights reserved.

关键词： graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Contextualized Knowledge-aware Attentive Neural Network: Enhancing Answer Selection with Knowledge

引用

ACM TRANSACTIONS ON INFORMATION SYSTEMS 2022年第1期40卷 2-2页

作者： Deng, Yang Xie, Yuexiang Li, Yaliang Yang, Min Lam, Wai Shen, Ying Chinese Univ Hong Kong Dept Syst Engn & Engn Management Hong Kong Peoples R China Alibaba Grp Hangzhou Peoples R China Alibaba Grp Bellevue WA USA Chinese Acad Sci SIAT Shenzhen Peoples R China Sun Yat Sen Univ Sch Intelligent Syst Engn Guangzhou Peoples R China

Answer selection, which is involved in many natural language processing applications, such as dialog systems and question answering (QA), is an important yet challenging task in practice, since conventional methods typically suffer from the issues of ignoring diverse real-world background knowledge. In this article, we extensively investigate approaches to enhancing the answer selection model with external knowledge from knowledge graph (KG). first, we present a context-knowledge interaction learning framework, Knowledge-aware Neural Network, which learns the QA sentence representations by considering a tight interaction with the external knowledge from KG and the textual information. Then, we develop two kinds of knowledge-aware attention mechanism to summarize both the context-based and knowledge-based interactions between questions and answers. To handle the diversity and complexity of KG information, we further propose a Contextualized Knowledge-aware Attentive Neural Network, which improves the knowledge representation learning with structure information via a customized graph Convolutional Network and comprehensively learns context-based and knowledge-based sentence representation via the multi-view knowledge-aware attention mechanism. We evaluate our method on four widely used benchmark QA datasets, including WikiQA, TREC QA, InsuranceQA, and Yahoo QA. Results verify the benefits of incorporating external knowledge from KG and show the robust superiority and extensive applicability of our method.

关键词： Answer selection knowledge graph attention mechanism graph convolutional network

来源：评论

学校读者我要写书评

暂无评论

EXECUTABLE first-ORDER QUERIES IN THE LOGIC OF INFORMATION FLOWS ∗

引用

LOGICAL methods IN COMPUTER SCIENCE 2024年第2期20卷

作者： Aamer, Heba A. Bogaerts, Bart Surinx, Dimitri Ternovska, Eugenia Van Den Bussche, Jan Vrije Univ Brussel Brussels Belgium Hasselt Univ Hasselt Belgium Simon Fraser Univ Burnaby BC Canada

. The logic of information flows (LIF) has recently been proposed as a general framework in the field of knowledge representation. In this framework, tasks of procedural nature can still be modeled in a declarative, logic-based fashion. In this paper, we focus on the task of query processing under limited access patterns, a well-studied problem in the database literature. We show that LIF is well-suited for modeling this task. Toward this goal, we introduce a variant of LIF called "forward" LIF (FLIF), in a first-order setting. FLIF takes a novel graph-navigational approach;it is an XPath-like language that nevertheless turns out to be equivalent to the "executable" fragment of first-order logic defined by Nash and Lud & acirc;scher. One can also classify the variables in FLIF expressions as inputs and outputs. Expressions where inputs and outputs are disjoint, referred to as iodisjoint FLIF expressions, allow a particularly transparent translation into algebraic query plans that respect the access limitations. Finally, we show that general FLIF expressions can always be put into io-disjoint form.

关键词： Limited access pattern expressive power variable substitution composition.

来源：评论

学校读者我要写书评

暂无评论

Knowledge graph Enhanced Large language Model Editing

arXiv

引用

arXiv 2024年

作者： Zhang, Mengqi Ye, Xiaotian Liu, Qiang Ren, Pengjie Wu, Shu Chen, Zhumin School of Computer Science and Technology Shandong University China School of Computer Science Beijing University of Posts and Telecommunications China Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China

Large language models (LLMs) are pivotal in advancing natural language processing (NLP) tasks, yet their efficacy is hampered by inaccuracies and outdated knowledge. Model editing emerges as a promising solution to address these challenges. However, existing editing methods struggle to track and incorporate changes in knowledge associated with edits, which limits the generalization ability of post-edit LLMs in processing edited knowledge. To tackle these problems, we propose a novel model editing method that leverages knowledge graphs for enhancing LLM editing, namely GLAME. Specifically, we first utilize a knowledge graph augmentation module to uncover associated knowledge that has changed due to editing, obtaining its internal representations within LLMs. This approach allows knowledge alterations within LLMs to be reflected through an external graph structure. Subsequently, we design a graph-based knowledge edit module to integrate structured knowledge into the model editing. This ensures that the updated parameters reflect not only the modifications of the edited knowledge but also the changes in other associated knowledge resulting from the editing process. Comprehensive experiments conducted on GPT-J and GPT-2 XL demonstrate that GLAME significantly improves the generalization capabilities of post-edit LLMs in employing edited knowledge. Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：