Sarah Condran, Michael Bewong, Selasi Kwashie, Md Zahidul Islam, Irfan Altas, Joshua Condran
The automated detection of false information has become a fundamental task in combating the spread of "fake news" on online social media networks (OSMN) as it reduces the need for manual discernment by individuals. In the literature, leveraging various content or context features of OSMN documents have been found useful. However, most of the existing detection models often utilise these features in isolation without regard to the temporal and dynamic changes oft-seen in reality, thus, limiting the robustness of the models. Furthermore, there has been little to no consideration of the impact of the quality of documents' features on the trustworthiness of the final prediction. In this paper, we introduce a novel model-agnostic framework, called MAPX, which allows evidence based aggregation of predictions from existing models in an explainable manner. Indeed, the developed aggregation method is adaptive, dynamic and considers the quality of OSMN document features. Further, we perform extensive experiments on benchmarked fake news datasets to demonstrate the effectiveness of MAPX using various real-world data quality scenarios. Our empirical results show that the proposed framework consistently outperforms all state-of-the-art models evaluated. For reproducibility, a demo of MAPX is available at href{https://github.com/SCondran/MAPX_framework}{this link}
{"title":"MAPX: An explainable model-agnostic framework for the detection of false information on social media networks","authors":"Sarah Condran, Michael Bewong, Selasi Kwashie, Md Zahidul Islam, Irfan Altas, Joshua Condran","doi":"arxiv-2409.08522","DOIUrl":"https://doi.org/arxiv-2409.08522","url":null,"abstract":"The automated detection of false information has become a fundamental task in\u0000combating the spread of \"fake news\" on online social media networks (OSMN) as\u0000it reduces the need for manual discernment by individuals. In the literature,\u0000leveraging various content or context features of OSMN documents have been\u0000found useful. However, most of the existing detection models often utilise\u0000these features in isolation without regard to the temporal and dynamic changes\u0000oft-seen in reality, thus, limiting the robustness of the models. Furthermore,\u0000there has been little to no consideration of the impact of the quality of\u0000documents' features on the trustworthiness of the final prediction. In this\u0000paper, we introduce a novel model-agnostic framework, called MAPX, which allows\u0000evidence based aggregation of predictions from existing models in an\u0000explainable manner. Indeed, the developed aggregation method is adaptive,\u0000dynamic and considers the quality of OSMN document features. Further, we\u0000perform extensive experiments on benchmarked fake news datasets to demonstrate\u0000the effectiveness of MAPX using various real-world data quality scenarios. Our\u0000empirical results show that the proposed framework consistently outperforms all\u0000state-of-the-art models evaluated. For reproducibility, a demo of MAPX is\u0000available at href{https://github.com/SCondran/MAPX_framework}{this link}","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142263483","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}
Agnik Saha, Mohammad Shahidul Kader, Mohammad Masum
Stack Exchange, a question-and-answer(Q&A) platform, has exhibited signs of a declining user engagement. This paper investigates user engagement dynamics across various Stack Exchange communities including Data science, AI, software engineering, project management, and GenAI. We propose a network graph representing users as nodes and their interactions as edges. We explore engagement patterns through key network metrics including Degree Centerality, Betweenness Centrality, and PageRank. The study findings reveal distinct community dynamics across these platforms, with smaller communities demonstrating more concentrated user influence, while larger platforms showcase more distributed engagement. Besides, the results showed insights into user roles, influence, and potential strategies for enhancing engagement. This research contributes to understanding of online community behavior and provides a framework for future studies to improve the Stack Exchange user experience.
{"title":"Unveiling User Engagement Patterns on Stack Exchange Through Network Analysis","authors":"Agnik Saha, Mohammad Shahidul Kader, Mohammad Masum","doi":"arxiv-2409.08944","DOIUrl":"https://doi.org/arxiv-2409.08944","url":null,"abstract":"Stack Exchange, a question-and-answer(Q&A) platform, has exhibited signs of a\u0000declining user engagement. This paper investigates user engagement dynamics\u0000across various Stack Exchange communities including Data science, AI, software\u0000engineering, project management, and GenAI. We propose a network graph\u0000representing users as nodes and their interactions as edges. We explore\u0000engagement patterns through key network metrics including Degree Centerality,\u0000Betweenness Centrality, and PageRank. The study findings reveal distinct\u0000community dynamics across these platforms, with smaller communities\u0000demonstrating more concentrated user influence, while larger platforms showcase\u0000more distributed engagement. Besides, the results showed insights into user\u0000roles, influence, and potential strategies for enhancing engagement. This\u0000research contributes to understanding of online community behavior and provides\u0000a framework for future studies to improve the Stack Exchange user experience.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142263476","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}
This paper presents SYBILGAT, a novel approach to Sybil detection in social networks using Graph Attention Networks (GATs). Traditional methods for Sybil detection primarily leverage structural properties of networks; however, they tend to struggle with a large number of attack edges and are often unable to simultaneously utilize both known Sybil and honest nodes. Our proposed method addresses these limitations by dynamically assigning attention weights to different nodes during aggregations, enhancing detection performance. We conducted extensive experiments in various scenarios, including pretraining in sampled subgraphs, synthetic networks, and networks under targeted attacks. The results show that SYBILGAT significantly outperforms the state-of-the-art algorithms, particularly in scenarios with high attack complexity and when the number of attack edges increases. Our approach shows robust performance across different network models and sizes, even as the detection task becomes more challenging. We successfully applied the model to a real-world Twitter graph with more than 269k nodes and 6.8M edges. The flexibility and generalizability of SYBILGAT make it a promising tool to defend against Sybil attacks in online social networks with only structural information.
{"title":"Sybil Detection using Graph Neural Networks","authors":"Stuart Heeb, Andreas Plesner, Roger Wattenhofer","doi":"arxiv-2409.08631","DOIUrl":"https://doi.org/arxiv-2409.08631","url":null,"abstract":"This paper presents SYBILGAT, a novel approach to Sybil detection in social\u0000networks using Graph Attention Networks (GATs). Traditional methods for Sybil\u0000detection primarily leverage structural properties of networks; however, they\u0000tend to struggle with a large number of attack edges and are often unable to\u0000simultaneously utilize both known Sybil and honest nodes. Our proposed method\u0000addresses these limitations by dynamically assigning attention weights to\u0000different nodes during aggregations, enhancing detection performance. We\u0000conducted extensive experiments in various scenarios, including pretraining in\u0000sampled subgraphs, synthetic networks, and networks under targeted attacks. The\u0000results show that SYBILGAT significantly outperforms the state-of-the-art\u0000algorithms, particularly in scenarios with high attack complexity and when the\u0000number of attack edges increases. Our approach shows robust performance across\u0000different network models and sizes, even as the detection task becomes more\u0000challenging. We successfully applied the model to a real-world Twitter graph\u0000with more than 269k nodes and 6.8M edges. The flexibility and generalizability\u0000of SYBILGAT make it a promising tool to defend against Sybil attacks in online\u0000social networks with only structural information.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142263478","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}
In the context where social media is increasingly becoming a significant platform for social movements and the formation of public opinion, accurately simulating and predicting the dynamics of user opinions is of great importance for understanding social phenomena, policy making, and guiding public opinion. However, existing simulation methods face challenges in capturing the complexity and dynamics of user behavior. Addressing this issue, this paper proposes an innovative simulation method for the dynamics of social media user opinions, the FDE-LLM algorithm, which incorporates opinion dynamics and epidemic model. This effectively constrains the actions and opinion evolution process of large language models (LLM), making them more aligned with the real cyber world. In particular, the FDE-LLM categorizes users into opinion leaders and followers. Opinion leaders are based on LLM role-playing and are constrained by the CA model, while opinion followers are integrated into a dynamic system that combines the CA model with the SIR model. This innovative design significantly improves the accuracy and efficiency of the simulation. Experiments were conducted on four real Weibo datasets and validated using the open-source model ChatGLM. The results show that, compared to traditional agent-based modeling (ABM) opinion dynamics algorithms and LLM-based opinion diffusion algorithms, our FDE-LLM algorithm demonstrates higher accuracy and interpretability.
在社交媒体日益成为社会运动和舆论形成的重要平台的背景下，准确模拟和预测用户意见的动态变化对于理解社会现象、制定政策和引导舆论具有重要意义。然而，现有的模拟方法在捕捉用户行为的复杂性和动态性方面面临挑战。针对这一问题，本文提出了一种创新的社交媒体用户舆论动态模拟方法--FDE-LLM 算法，该算法结合了舆论动态和流行病模型。这有效地约束了大型语言模型（LLM）的行动和观点演变过程，使其更加贴近真实的网络世界。其中，FDE-LLM 将用户分为意见领袖和追随者。意见领袖以 LLM 角色扮演为基础，受到 CA 模型的约束，而意见追随者则被整合到结合了 CA 模型和 SIR 模型的动态系统中。我们在四个真实微博数据集上进行了实验，并使用开源模型 ChatGLM 进行了验证。实验结果表明，与传统的基于代理建模（ABM）的舆情动态算法和基于 LLM 的舆情扩散算法相比，我们的 FDE-LLM 算法具有更高的准确性和可解释性。
{"title":"Fusing Dynamics Equation: A Social Opinions Prediction Algorithm with LLM-based Agents","authors":"Junchi Yao, Hongjie Zhang, Jie Ou, Dingyi Zuo, Zheng Yang, Zhicheng Dong","doi":"arxiv-2409.08717","DOIUrl":"https://doi.org/arxiv-2409.08717","url":null,"abstract":"In the context where social media is increasingly becoming a significant\u0000platform for social movements and the formation of public opinion, accurately\u0000simulating and predicting the dynamics of user opinions is of great importance\u0000for understanding social phenomena, policy making, and guiding public opinion.\u0000However, existing simulation methods face challenges in capturing the\u0000complexity and dynamics of user behavior. Addressing this issue, this paper\u0000proposes an innovative simulation method for the dynamics of social media user\u0000opinions, the FDE-LLM algorithm, which incorporates opinion dynamics and\u0000epidemic model. This effectively constrains the actions and opinion evolution\u0000process of large language models (LLM), making them more aligned with the real\u0000cyber world. In particular, the FDE-LLM categorizes users into opinion leaders\u0000and followers. Opinion leaders are based on LLM role-playing and are\u0000constrained by the CA model, while opinion followers are integrated into a\u0000dynamic system that combines the CA model with the SIR model. This innovative\u0000design significantly improves the accuracy and efficiency of the simulation.\u0000Experiments were conducted on four real Weibo datasets and validated using the\u0000open-source model ChatGLM. The results show that, compared to traditional\u0000agent-based modeling (ABM) opinion dynamics algorithms and LLM-based opinion\u0000diffusion algorithms, our FDE-LLM algorithm demonstrates higher accuracy and\u0000interpretability.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142263479","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}
Yuwei Chuai, Anastasia Sergeeva, Gabriele Lenzini, Nicolas Pröllochs
Displaying community fact-checks is a promising approach to reduce engagement with misinformation on social media. However, how users respond to misleading content emotionally after community fact-checks are displayed on posts is unclear. Here, we employ quasi-experimental methods to causally analyze changes in sentiments and (moral) emotions in replies to misleading posts following the display of community fact-checks. Our evaluation is based on a large-scale panel dataset comprising N=2,225,260 replies across 1841 source posts from X's Community Notes platform. We find that informing users about falsehoods through community fact-checks significantly increases negativity (by 7.3%), anger (by 13.2%), disgust (by 4.7%), and moral outrage (by 16.0%) in the corresponding replies. These results indicate that users perceive spreading misinformation as a violation of social norms and that those who spread misinformation should expect negative reactions once their content is debunked. We derive important implications for the design of community-based fact-checking systems.
{"title":"Community Fact-Checks Trigger Moral Outrage in Replies to Misleading Posts on Social Media","authors":"Yuwei Chuai, Anastasia Sergeeva, Gabriele Lenzini, Nicolas Pröllochs","doi":"arxiv-2409.08829","DOIUrl":"https://doi.org/arxiv-2409.08829","url":null,"abstract":"Displaying community fact-checks is a promising approach to reduce engagement\u0000with misinformation on social media. However, how users respond to misleading\u0000content emotionally after community fact-checks are displayed on posts is\u0000unclear. Here, we employ quasi-experimental methods to causally analyze changes\u0000in sentiments and (moral) emotions in replies to misleading posts following the\u0000display of community fact-checks. Our evaluation is based on a large-scale\u0000panel dataset comprising N=2,225,260 replies across 1841 source posts from X's\u0000Community Notes platform. We find that informing users about falsehoods through\u0000community fact-checks significantly increases negativity (by 7.3%), anger (by\u000013.2%), disgust (by 4.7%), and moral outrage (by 16.0%) in the corresponding\u0000replies. These results indicate that users perceive spreading misinformation as\u0000a violation of social norms and that those who spread misinformation should\u0000expect negative reactions once their content is debunked. We derive important\u0000implications for the design of community-based fact-checking systems.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142263477","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}
Yuwei Chuai, Moritz Pilarski, Thomas Renault, David Restrepo-Amariles, Aurore Troussel-Clément, Gabriele Lenzini, Nicolas Pröllochs
Community-based fact-checking is a promising approach to verify social media content and correct misleading posts at scale. Yet, causal evidence regarding its effectiveness in reducing the spread of misinformation on social media is missing. Here, we performed a large-scale empirical study to analyze whether community notes reduce the spread of misleading posts on X. Using a Difference-in-Differences design and repost time series data for N=237,677 (community fact-checked) cascades that had been reposted more than 431 million times, we found that exposing users to community notes reduced the spread of misleading posts by, on average, 62.0%. Furthermore, community notes increased the odds that users delete their misleading posts by 103.4%. However, our findings also suggest that community notes might be too slow to intervene in the early (and most viral) stage of the diffusion. Our work offers important implications to enhance the effectiveness of community-based fact-checking approaches on social media.
基于社区的事实核查是验证社交媒体内容和大规模纠正误导性帖子的一种很有前途的方法。然而，有关其在减少社交媒体上错误信息传播方面的有效性的因果证据还很缺乏。在此，我们进行了一项大规模的实证研究，分析社区注释是否减少了 X 上误导性帖子的传播。我们使用了差分法设计和 N=237,677 个（社区事实核查）级联的转贴时间序列数据，这些级联的转贴次数超过了 4.31 亿次，我们发现，让用户接触社区注释平均减少了 62.0% 的误导性帖子的传播。此外，社区注释还使用户删除其误导性帖子的几率提高了 103.4%。然而，我们的研究结果也表明，社区注释可能过于缓慢，无法在传播的早期（也是病毒最猖獗的阶段）进行干预。我们的工作为提高社交媒体上基于社区的事实核查方法的有效性提供了重要启示。
{"title":"Community-based fact-checking reduces the spread of misleading posts on social media","authors":"Yuwei Chuai, Moritz Pilarski, Thomas Renault, David Restrepo-Amariles, Aurore Troussel-Clément, Gabriele Lenzini, Nicolas Pröllochs","doi":"arxiv-2409.08781","DOIUrl":"https://doi.org/arxiv-2409.08781","url":null,"abstract":"Community-based fact-checking is a promising approach to verify social media\u0000content and correct misleading posts at scale. Yet, causal evidence regarding\u0000its effectiveness in reducing the spread of misinformation on social media is\u0000missing. Here, we performed a large-scale empirical study to analyze whether\u0000community notes reduce the spread of misleading posts on X. Using a\u0000Difference-in-Differences design and repost time series data for N=237,677\u0000(community fact-checked) cascades that had been reposted more than 431 million\u0000times, we found that exposing users to community notes reduced the spread of\u0000misleading posts by, on average, 62.0%. Furthermore, community notes increased\u0000the odds that users delete their misleading posts by 103.4%. However, our\u0000findings also suggest that community notes might be too slow to intervene in\u0000the early (and most viral) stage of the diffusion. Our work offers important\u0000implications to enhance the effectiveness of community-based fact-checking\u0000approaches on social media.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142263482","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}
Using random walks for sampling has proven advantageous in assessing the characteristics of large and unknown social networks. Several algorithms based on random walks have been introduced in recent years. In the practical application of social network sampling, there is a recurrent reliance on an application programming interface (API) for obtaining adjacent nodes. However, owing to constraints related to query frequency and associated API expenses, it is preferable to minimize API calls during the feature estimation process. In this study, considering the acquisition of neighboring nodes as a cost factor, we introduce a feature estimation algorithm that outperforms existing algorithms in terms of accuracy. Through experiments that simulate sampling on known graphs, we demonstrate the superior accuracy of our proposed algorithm when compared to existing alternatives.
事实证明，使用随机游走进行抽样在评估大型未知社交网络的特征方面具有优势。近年来，已经推出了几种基于随机游走的算法。在社交网络采样的实际应用中，人们经常依赖应用编程接口（API）来获取相邻节点。然而，由于查询频率和相关 API 费用的限制，在特征估计过程中最好尽量减少 API 调用。在本研究中，考虑到获取相邻节点的成本因素，我们引入了一种在准确性方面优于现有算法的特征估计算法。通过在已知图上模拟采样的实验，我们证明了与现有算法相比，我们提出的算法具有更高的准确性。
{"title":"Estimation of Graph Features Based on Random Walks Using Neighbors' Properties","authors":"Tsuyoshi Hasegawa, Shiori Hironaka, Kazuyuki Shudo","doi":"arxiv-2409.08599","DOIUrl":"https://doi.org/arxiv-2409.08599","url":null,"abstract":"Using random walks for sampling has proven advantageous in assessing the\u0000characteristics of large and unknown social networks. Several algorithms based\u0000on random walks have been introduced in recent years. In the practical\u0000application of social network sampling, there is a recurrent reliance on an\u0000application programming interface (API) for obtaining adjacent nodes. However,\u0000owing to constraints related to query frequency and associated API expenses, it\u0000is preferable to minimize API calls during the feature estimation process. In\u0000this study, considering the acquisition of neighboring nodes as a cost factor,\u0000we introduce a feature estimation algorithm that outperforms existing\u0000algorithms in terms of accuracy. Through experiments that simulate sampling on\u0000known graphs, we demonstrate the superior accuracy of our proposed algorithm\u0000when compared to existing alternatives.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142263480","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}
Pengyun Wang, Yadi Cao, Chris Russell, Siyu Heng, Junyu Luo, Yanxin Shen, Xiao Luo
Graph domain adaptation has recently enabled knowledge transfer across different graphs. However, without the semantic information on target graphs, the performance on target graphs is still far from satisfactory. To address the issue, we study the problem of active graph domain adaptation, which selects a small quantitative of informative nodes on the target graph for extra annotation. This problem is highly challenging due to the complicated topological relationships and the distribution discrepancy across graphs. In this paper, we propose a novel approach named Dual Consistency Delving with Topological Uncertainty (DELTA) for active graph domain adaptation. Our DELTA consists of an edge-oriented graph subnetwork and a path-oriented graph subnetwork, which can explore topological semantics from complementary perspectives. In particular, our edge-oriented graph subnetwork utilizes the message passing mechanism to learn neighborhood information, while our path-oriented graph subnetwork explores high-order relationships from substructures. To jointly learn from two subnetworks, we roughly select informative candidate nodes with the consideration of consistency across two subnetworks. Then, we aggregate local semantics from its K-hop subgraph based on node degrees for topological uncertainty estimation. To overcome potential distribution shifts, we compare target nodes and their corresponding source nodes for discrepancy scores as an additional component for fine selection. Extensive experiments on benchmark datasets demonstrate that DELTA outperforms various state-of-the-art approaches.
最近，图域适应技术实现了跨不同图的知识转移。然而，如果没有目标图的语义信息，在目标图上的性能仍然远远不能令人满意。为了解决这个问题，我们研究了主动图域适配问题，即选择目标图上的少量信息节点进行额外标注。由于图之间存在复杂的拓扑关系和分布差异，这个问题极具挑战性。在本文中，我们提出了一种名为 "带拓扑不确定性的双一致性掘取（Dual Consistency Delving withTopological Uncertainty，DELTA）"的主动图域适应新方法。我们的 DELTA 由面向边缘的图子网络和面向路径的图子网络组成，可以从互补的角度探索拓扑语义。其中，面向边缘的图子网络利用消息传递机制学习邻域信息，而面向路径的图子网络则从子结构中探索高阶关系。为了从两个子网络中联合学习，我们在考虑两个子网络一致性的基础上，粗略地选择有信息的候选节点。然后，我们根据节点度从其 K 跳子图中汇总局部语义，以进行拓扑不确定性估计。为了克服潜在的分布偏移，我们比较了目标节点和其相应来源节点的差异分数，作为精细选择的额外组成部分。
{"title":"DELTA: Dual Consistency Delving with Topological Uncertainty for Active Graph Domain Adaptation","authors":"Pengyun Wang, Yadi Cao, Chris Russell, Siyu Heng, Junyu Luo, Yanxin Shen, Xiao Luo","doi":"arxiv-2409.08946","DOIUrl":"https://doi.org/arxiv-2409.08946","url":null,"abstract":"Graph domain adaptation has recently enabled knowledge transfer across\u0000different graphs. However, without the semantic information on target graphs,\u0000the performance on target graphs is still far from satisfactory. To address the\u0000issue, we study the problem of active graph domain adaptation, which selects a\u0000small quantitative of informative nodes on the target graph for extra\u0000annotation. This problem is highly challenging due to the complicated\u0000topological relationships and the distribution discrepancy across graphs. In\u0000this paper, we propose a novel approach named Dual Consistency Delving with\u0000Topological Uncertainty (DELTA) for active graph domain adaptation. Our DELTA\u0000consists of an edge-oriented graph subnetwork and a path-oriented graph\u0000subnetwork, which can explore topological semantics from complementary\u0000perspectives. In particular, our edge-oriented graph subnetwork utilizes the\u0000message passing mechanism to learn neighborhood information, while our\u0000path-oriented graph subnetwork explores high-order relationships from\u0000substructures. To jointly learn from two subnetworks, we roughly select\u0000informative candidate nodes with the consideration of consistency across two\u0000subnetworks. Then, we aggregate local semantics from its K-hop subgraph based\u0000on node degrees for topological uncertainty estimation. To overcome potential\u0000distribution shifts, we compare target nodes and their corresponding source\u0000nodes for discrepancy scores as an additional component for fine selection.\u0000Extensive experiments on benchmark datasets demonstrate that DELTA outperforms\u0000various state-of-the-art approaches.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142263486","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}
Yunjie Pan, Omkar Bhalerao, C. Seshadhri, Nishil Talati
Counting the number of small subgraphs, called motifs, is a fundamental problem in social network analysis and graph mining. Many real-world networks are directed and temporal, where edges have timestamps. Motif counting in directed, temporal graphs is especially challenging because there are a plethora of different kinds of patterns. Temporal motif counts reveal much richer information and there is a need for scalable algorithms for motif counting. A major challenge in counting is that there can be trillions of temporal motif matches even with a graph with only millions of vertices. Both the motifs and the input graphs can have multiple edges between two vertices, leading to a combinatorial explosion problem. Counting temporal motifs involving just four vertices is not feasible with current state-of-the-art algorithms. We design an algorithm, TEACUPS, that addresses this problem using a novel technique of temporal path sampling. We combine a path sampling method with carefully designed temporal data structures, to propose an efficient approximate algorithm for temporal motif counting. TEACUPS is an unbiased estimator with provable concentration behavior, which can be used to bound the estimation error. For a Bitcoin graph with hundreds of millions of edges, TEACUPS runs in less than 1 minute, while the exact counting algorithm takes more than a day. We empirically demonstrate the accuracy of TEACUPS on large datasets, showing an average of 30$times$ speedup (up to 2000$times$ speedup) compared to existing GPU-based exact counting methods while preserving high count estimation accuracy.
{"title":"Accurate and Fast Estimation of Temporal Motifs using Path Sampling","authors":"Yunjie Pan, Omkar Bhalerao, C. Seshadhri, Nishil Talati","doi":"arxiv-2409.08975","DOIUrl":"https://doi.org/arxiv-2409.08975","url":null,"abstract":"Counting the number of small subgraphs, called motifs, is a fundamental\u0000problem in social network analysis and graph mining. Many real-world networks\u0000are directed and temporal, where edges have timestamps. Motif counting in\u0000directed, temporal graphs is especially challenging because there are a\u0000plethora of different kinds of patterns. Temporal motif counts reveal much\u0000richer information and there is a need for scalable algorithms for motif\u0000counting. A major challenge in counting is that there can be trillions of temporal\u0000motif matches even with a graph with only millions of vertices. Both the motifs\u0000and the input graphs can have multiple edges between two vertices, leading to a\u0000combinatorial explosion problem. Counting temporal motifs involving just four\u0000vertices is not feasible with current state-of-the-art algorithms. We design an algorithm, TEACUPS, that addresses this problem using a novel\u0000technique of temporal path sampling. We combine a path sampling method with\u0000carefully designed temporal data structures, to propose an efficient\u0000approximate algorithm for temporal motif counting. TEACUPS is an unbiased\u0000estimator with provable concentration behavior, which can be used to bound the\u0000estimation error. For a Bitcoin graph with hundreds of millions of edges,\u0000TEACUPS runs in less than 1 minute, while the exact counting algorithm takes\u0000more than a day. We empirically demonstrate the accuracy of TEACUPS on large\u0000datasets, showing an average of 30$times$ speedup (up to 2000$times$ speedup)\u0000compared to existing GPU-based exact counting methods while preserving high\u0000count estimation accuracy.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142263474","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}
Patrick Gerard, Svitlana Volkova, Louis Penafiel, Kristina Lerman, Tim Weninger
Following the Russian Federation's full-scale invasion of Ukraine in February 2022, a multitude of information narratives emerged within both pro-Russian and pro-Ukrainian communities online. As the conflict progresses, so too do the information narratives, constantly adapting and influencing local and global community perceptions and attitudes. This dynamic nature of the evolving information environment (IE) underscores a critical need to fully discern how narratives evolve and affect online communities. Existing research, however, often fails to capture information narrative evolution, overlooking both the fluid nature of narratives and the internal mechanisms that drive their evolution. Recognizing this, we introduce a novel approach designed to both model narrative evolution and uncover the underlying mechanisms driving them. In this work we perform a comparative discourse analysis across communities on Telegram covering the initial three months following the invasion. First, we uncover substantial disparities in narratives and perceptions between pro-Russian and pro-Ukrainian communities. Then, we probe deeper into prevalent narratives of each group, identifying key themes and examining the underlying mechanisms fueling their evolution. Finally, we explore influences and factors that may shape the development and spread of narratives.
{"title":"Modeling Information Narrative Detection and Evolution on Telegram during the Russia-Ukraine War","authors":"Patrick Gerard, Svitlana Volkova, Louis Penafiel, Kristina Lerman, Tim Weninger","doi":"arxiv-2409.07684","DOIUrl":"https://doi.org/arxiv-2409.07684","url":null,"abstract":"Following the Russian Federation's full-scale invasion of Ukraine in February\u00002022, a multitude of information narratives emerged within both pro-Russian and\u0000pro-Ukrainian communities online. As the conflict progresses, so too do the\u0000information narratives, constantly adapting and influencing local and global\u0000community perceptions and attitudes. This dynamic nature of the evolving\u0000information environment (IE) underscores a critical need to fully discern how\u0000narratives evolve and affect online communities. Existing research, however,\u0000often fails to capture information narrative evolution, overlooking both the\u0000fluid nature of narratives and the internal mechanisms that drive their\u0000evolution. Recognizing this, we introduce a novel approach designed to both\u0000model narrative evolution and uncover the underlying mechanisms driving them.\u0000In this work we perform a comparative discourse analysis across communities on\u0000Telegram covering the initial three months following the invasion. First, we\u0000uncover substantial disparities in narratives and perceptions between\u0000pro-Russian and pro-Ukrainian communities. Then, we probe deeper into prevalent\u0000narratives of each group, identifying key themes and examining the underlying\u0000mechanisms fueling their evolution. Finally, we explore influences and factors\u0000that may shape the development and spread of narratives.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142226899","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：