1<!DOCTYPE html> 2<html> 3 4 <head> 5 <meta charset="utf-8"> 6 <meta http-equiv="X-UA-Compatible" content="IE=edge"> 7 <meta name="viewport" content="width=device-width, initial-scale=1"> 8 9 <title>Publications - Xingbo Fu</title> 10 <meta name="description" content="Personal homepage"> 11 <link rel="shortcut icon" type="image/png" href="/images/favicon.ico"> 12 <link rel="stylesheet" href="/css/main.css"> 13 <link rel="canonical" href="https://xbfu.github.io/publications/"> 14 <link rel="alternate" type="application/rss+xml" title="Owen" href="https://xbfu.github.io/feed.xml" /> 15<link rel='stylesheet' id='open-sans-css' href='//fonts.googleapis.com/css?family=Open+Sans%3A300italic%2C400italic%2C600italic%2C300%2C400%2C600&subset=latin%2Clatin-ext&ver=4.2.4' type='text/css' media='all' /> 16<link href='https://fonts.googleapis.com/css?family=Titillium+Web:600italic,600,400,400italic' rel='stylesheet' type='text/css'> 17</head> 18 19 20 <body> 21 22 <header class="site-header"> 23 24 <div class="wrapper"> 25 26 <a class="site-title" href="/">Home</a> 27 28 29 <nav class="site-nav"> 30 31 <a href="#" class="menu-icon menu.open"> 32 <svg viewBox="0 0 18 15"> 33 <path fill="#424242" d="M18,1.484c0,0.82-0.665,1.484-1.484,1.484H1.484C0.665,2.969,0,2.304,0,1.484l0,0C0,0.665,0.665,0,1.484,0 h15.031C17.335,0,18,0.665,18,1.484L18,1.484z"/> 34 <path fill="#424242" d="M18,7.516C18,8.335,17.335,9,16.516,9H1.484C0.665,9,0,8.335,0,7.516l0,0c0-0.82,0.665-1.484,1.484-1.484 h15.031C17.335,6.031,18,6.696,18,7.516L18,7.516z"/> 35 <path fill="#424242" d="M18,13.516C18,14.335,17.335,15,16.516,15H1.484C0.665,15,0,14.335,0,13.516l0,0 c0-0.82,0.665-1.484,1.484-1.484h15.031C17.335,12.031,18,12.696,18,13.516L18,13.516z"/> 36 </svg> 37 </a> 38 39 <div class="trigger"><h1>Navigation</h1> 40 41 <ul class="menu"> 42 43 44 45 <li><a href="/publications/" class="page-link">Publications</a> 46 47 </li> 48 49 50 <li><a href="/tutorials/" class="page-link">Tutorials</a> 51 52 </li> 53 54 55 <li><a href="/services/" class="page-link">Services</a> 56 57 </li> 58 59 60 <li><a href="/teaching/" class="page-link">Teaching</a> 61 62 </li> 63 64 65 <li><a href="/cv/" class="page-link">CV</a> 66 67 </li> 68 69</ul> 70 71 72 </div> 73 </nav> 74 75 </div> 76 77</header> 78 79 80 <style type="text/css"> 81 html,body { 82 margin: 0; 83 padding: 0; 84 } 85 86 .fixed-bottom {position: fixed;bottom: 0;width:100%;} 87 </style> 88 89
89<script src="https://libs.baidu.com/jquery/1.7.2/jquery.min.js"></script>
89 90
90<script type="text/javascript"> 91 $(function(){ 92 function footerPosition(){ 93 $("footer").removeClass("fixed-bottom"); 94 var contentHeight = document.body.scrollHeight, 95 winHeight = window.innerHeight; 96 if(!(contentHeight > winHeight)){ 97 $("footer").addClass("fixed-bottom"); 98 } else { 99 $("footer").removeClass("fixed-bottom"); 100 } 101 } 102 footerPosition(); 103 $(window).resize(footerPosition); 104 }); 105 </script>
105 106 107 <div class="page-content"> 108 <div class="wrapper"> 109 <div class="post"> 110 111 <header class="post-header"> 112 <style type="text/css"> 113 html,body { 114 margin: 0; 115 padding: 0; 116 } 117 118 .fixed-bottom {position: fixed;bottom: 0;width:100%;} 119 </style> 120 121
121<script src="http://libs.baidu.com/jquery/1.7.2/jquery.min.js"></script>
121 122
122<script type="text/javascript"> 123 $(function(){ 124 function footerPosition(){ 125 $("footer").removeClass("fixed-bottom"); 126 var contentHeight = document.body.scrollHeight, 127 winHeight = window.innerHeight; 128 if(!(contentHeight > winHeight)){ 129 $("footer").addClass("fixed-bottom"); 130 } else { 131 $("footer").removeClass("fixed-bottom"); 132 } 133 } 134 footerPosition(); 135 $(window).resize(footerPosition); 136 }); 137 </script>
137 138 139 140 <h1 class="post-title">Publications</h1> 141 </header> 142 143 <article class="post-content"> 144 <h2>2026</h2> 145<ul> 146 <li> 147 <b>A Survey of Scaling in Large Language Model Reasoning</b><br /> 148 <i>Zihan Chen, Song Wang, Zhen Tan, <b>Xingbo Fu</b>, Zhenyu Lei, Peng Wang, Huan Liu, Cong Shen, Jundong Li</i><br /> 149 ACM SIGKDD Explorations Newsletter 2026 <br /> 150 <a href="https://arxiv.org/abs/2504.02181"><div class="report">arXiv</div></a> 151 </li> 152 <li> 153 <b>Safety in Graph Machine Learning: Threats and Safeguards</b><br /> 154 <i>Song Wang, Yushun Dong, Binchi Zhang, Zihan Chen, <b>Xingbo Fu</b>, Yinhan He, Cong Shen, Chuxu Zhang, Nitesh V. Chawla, Jundong Li</i><br /> 155 IEEE Transactions on Knowledge and Data Engineering<br /> 156 <a href="https://ieeexplore.ieee.org/abstract/document/11372973"><div class="paper">Paper</div></a> 157 <a href="https://arxiv.org/abs/2405.11034"><div class="report">arXiv</div></a> 158 </li> 159 160</ul> 161 162<h2>2025</h2> 163<ul> 164 <li> 165 <b>GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks</b><br /> 166 <i><b>Xingbo Fu</b>, Zhenyu Lei, Zihan Chen, Binchi Zhang, Chuxu Zhang, Jundong Li</i><br /> 167 The 39th Annual Conference on Neural Information Processing Systems (NeurIPS 2025)<br /> 168 <a href="https://openreview.net/forum?id=N2f6N4jopz"><div class="paper">Paper</div></a> 169 <a href="https://arxiv.org/abs/2510.22451"><div class="report">arXiv</div></a> 170 <a href="https://github.com/xbfu/GraphTOP"><div class="code">Github</div></a> 171 </li> 172 <li> 173 <b>Graph Prompting for Graph Learning Models: Recent Advances and Future Directions</b><br /> 174 <i><b>Xingbo Fu</b>, Zehong Wang, Zihan Chen, Jiazheng Li, Yaochen Zhu, Zhenyu Lei, Cong Shen, Yanfang Ye, Chuxu Zhang, Jundong Li</i><br /> 175 ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2025 Tutorial/Survey Track)<br /> 176 <a href="https://dl.acm.org/doi/abs/10.1145/3711896.3736566"><div class="paper">Paper</div></a> 177 <a href="https://arxiv.org/abs/2506.08326"><div class="report">arXiv</div></a> 178 </li> 179 <li> 180 <b>Edge Prompt Tuning for Graph Neural Networks</b><br /> 181 <i><b>Xingbo Fu</b>, Yinhan He, Jundong Li</i><br /> 182 International Conference on Learning Representations (ICLR 2025)<br /> 183 <a href="https://openreview.net/forum?id=92vMaHotTM"><div class="paper">Paper</div></a> 184 <a href="https://arxiv.org/abs/2503.00750"><div class="report">arXiv</div></a> 185 <a href="https://github.com/xbfu/EdgePrompt"><div class="code">Github</div></a> 186 </li> 187 <li> 188 <b>Virtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learning</b><br /> 189 <i><b>Xingbo Fu</b>, Zihan Chen, Yinhan He, Song Wang, Binchi Zhang, Chen Chen, Jundong Li</i><br /> 190 AAAI Conference on Artificial Intelligence (AAAI 2025)<br /> 191 <a href="https://ojs.aaai.org/index.php/AAAI/article/view/33830"><div class="paper">Paper</div></a> 192 <a href="https://arxiv.org/abs/2412.19229"><div class="report">arXiv</div></a> 193 <a href="https://github.com/xbfu/FedVN"><div class="code">Github</div></a> 194 </li> 195 <li> 196 <b>From Cross-Task Examples to In-Task Prompts: A Graph-Based Pseudo-Labeling Framework for In-context Learning</b><br /> 197 <i>Zihan Chen, Song Wang, <b>Xingbo Fu</b>, Chengshuai Shi, Zhenyu Lei, Cong Shen, Jundong Li</i><br /> 198 The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025)<br /> 199 <a href="https://aclanthology.org/anthology-files/anthology-files/pdf/findings/2025.findings-emnlp.181.pdf"><div class="paper">Paper</div></a> 200 <a href="https://arxiv.org/abs/2510.24528"><div class="report">arXiv</div></a> 201 </li> 202 <li> 203 <b>Text-Attributed Graph Anomaly Detection via Multi-Scale Cross- and Uni-Modal Contrastive Learning</b><br /> 204 <i>Yiming Xu, Xu Hua, Zhen Peng, Bin Shi, Jiarun Chen, <b>Xingbo Fu</b>, Song Wang, Bo Dong</i><br /> 205 European Conference on Artificial Intelligence (ECAI 2025)<br /> 206 <a href="https://ebooks.iospress.nl/doi/10.3233/FAIA251124"><div class="paper">Paper</div></a> 207 <a href="https://arxiv.org/abs/2508.00513"><div class="report">arXiv</div></a> 208 </li> 209 <li> 210 <b>FedHERO: A Federated Learning Approach for Node Classification Task on Heterophilic Graphs</b><br /> 211 <i>Zihan Chen, <b>Xingbo Fu</b>, Yushun Dong, Jundong Li, Cong Shen</i><br /> 212 Transactions on Machine Learning Research (TMLR)<br /> 213 <a href="https://openreview.net/forum?id=pHii7cWco7"><div class="paper">Paper</div></a> 214 <a href="https://arxiv.org/abs/2504.21206"><div class="report">arXiv</div></a> 215 </li> 216 <li> 217 <b>Graph Foundation Models: A Comprehensive Survey</b><br /> 218 <i>Zehong Wang, Zheyuan Liu, Tianyi Ma, Jiazheng Li, Zheyuan Zhang, <b>Xingbo Fu</b>, Yiyang Li, Zhengqing Yuan, Wei Song, Yijun Ma, Qingkai Zeng, Xiusi Chen, Jianan Zhao, Jund
218ong Li, Meng Jiang, Pietro Lio, Nitesh Chawla, Chuxu Zhang, Yanfang Ye</i><br /> 219 Preprint<br /> 220 <a href="https://arxiv.org/abs/2505.15116"><div class="report">arXiv</div></a> 221 <a href="https://github.com/Zehong-Wang/Awesome-Foundation-Models-on-Graphs"><div class="code">Github</div></a> 222 </li> 223 224</ul> 225 226<h2>2024</h2> 227<ul> 228 <li> 229 <b>Federated Graph Learning with Structure Proxy Alignment</b><br /> 230 <i><b>Xingbo Fu</b>, Zihan Chen, Binchi Zhang, Chen Chen, Jundong Li</i><br /> 231 ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2024)<br /> 232 <a href="https://dl.acm.org/doi/abs/10.1145/3637528.3671717"><div class="paper">Paper</div></a> 233 <a href="https://arxiv.org/abs/2408.09393"><div class="report">arXiv</div></a> 234 <a href="https://github.com/xbfu/FedSpray"><div class="code">Github</div></a> 235 </li> 236 <li> 237 <b>Federated Graph Learning with Graphless Clients</b><br /> 238 <i><b>Xingbo Fu</b>, Song Wang, Yushun Dong, Binchi Zhang, Chen Chen, Jundong Li</i><br /> 239 Transactions on Machine Learning Research (TMLR)<br /> 240 <a href="https://openreview.net/forum?id=mVAp0eDfyR"><div class="paper">Paper</div></a> 241 <a href="https://arxiv.org/abs/2411.08374"><div class="report">arXiv</div></a> 242 </li> 243 244</ul> 245 246<h2>2023</h2> 247<ul> 248 <li> 249 <b>Federated Few-Shot Learning</b><br /> 250 <i>Song Wang, <b>Xingbo Fu</b>, Kaize Ding, Chen Chen, Huiyuan Chen, Jundong Li</i><br /> 251 ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023)<br /> 252 <a href="https://dl.acm.org/doi/abs/10.1145/3580305.3599347"><div class="paper">Paper</div></a> 253 <a href="https://arxiv.org/abs/2306.10234"><div class="report">arXiv</div></a> 254 <a href="https://github.com/SongW-SW/F2L"><div class="code">Github</div></a> 255 </li> 256 <li> 257 <b>Spatial-Temporal Networks for Antibiogram Pattern Prediction</b><br /> 258 <i><b>Xingbo Fu</b>, Chen Chen, Yushun Dong, Anil Vullikanti, Eili Klein, Gregory Madden, Jundong Li</i><br /> 259 IEEE International Conference on Healthcare Informatics (IEEE ICHI 2023)<br /> 260 <a href="https://ieeexplore.ieee.org/abstract/document/10337221"><div class="paper">Paper</div></a> 261 <a href="https://arxiv.org/abs/2305.01761"><div class="report">arXiv</div></a> 262 </li> 263 264</ul> 265 266<h2>2022</h2> 267<ul> 268 <li> 269 <b>Federated Graph Machine Learning: A Survey of Concepts, Techniques, and Applications</b><br /> 270 <i><b>Xingbo Fu</b>, Binchi Zhang, Yushun Dong, Chen Chen, Jundong Li</i><br /> 271 ACM SIGKDD Explorations Newsletter 2022 <br /> 272 A short version has been accepted to International Workshop on Federated Learning with Graph Data in Conjunction with CIKM 2022<br /> 273 <a href="https://dl.acm.org/doi/abs/10.1145/3575637.3575644"><div class="paper">Paper</div></a> 274 <a href="https://arxiv.org/abs/2207.11812"><div class="report">arXiv</div></a> 275 <a href="FGML.pdf"><div class="paper">Short version</div></a> 276 </li> 277</ul> 278 279<h2>2020</h2> 280<ul> 281 <li> 282 <b>Online Clustering based Fault Data Detection Method for Distributed PV Sites</b><br /> 283 <i>Shujie Wang, Feng Gao, Jiang Wu , Chao Zheng, <b>Xingbo Fu</b>, Fangwei Duan</i><br /> 284 Chinese Control Conference (CCC 2020)<br /> 285 <a href="https://ieeexplore.ieee.org/abstract/document/9188826"><div class="paper">Paper</div></a> 286 </li> 287 <li> 288 <b>When Do Drivers Concentrate? Attention-based Driver Behavior Modeling with Deep Reinforcement Learning</b><br /> 289 <i><b>Xingbo Fu</b>, Feng Gao, Jiang Wu</i><br /> 290 <a href="https://arxiv.org/abs/2002.11385"><div class="report">arXiv</div></a> 291 </li> 292</ul> 293 294<h2>2019</h2> 295<ul> 296 <li> 297 <b>Spatiotemporal Attention Networks for Wind Power Forecasting</b><br /> 298 <i><b>Xingbo Fu</b>, Feng Gao, Jiang Wu, Xinyu Wei, Fangwei Duan</i><br /> 299 International Conference on Data Mining Workshops (ICDM 2019 Workshops)<br /> 300 <a href="https://ieeexplore.ieee.org/abstract/document/8955569"><div class="paper">Paper</div></a> 301 <a href="https://arxiv.org/abs/1909.07369"><div class="report">arXiv</div></a> 302 <a href="https://github.com/xbfu/Spatiotemporal-Attention-Networks"><div class="code">Github</div></a> 303 </li> 304 <li> 305 <b>A Simulation Approach to Multi-station Solar Irradiance Data Considering Temporal Correlations</b><br /> 306 <i><b>Xingbo Fu</b>, Feng Gao, Jiang Wu, Ruanming Huang, Yichao Huang, Fei Fei</i><br /> 307 International Conference on Innovative Smart Grid Technologies (ISGT Asia 2019)<br /> 308 <a href="https://ieeexplore.ieee.org/abstract/document/8881133"><div class="paper">Paper</div></a> 309 <a href="https://arxiv.org/abs/1909.07765"><div class="report">arXiv</div></a> 310 </li> 311 <li> 312 <b>Wind Power Capacity Planning in Enterpriseâs Microgrid based on Approximation Expectation of Operation Cost</b><br /> 313 <i>Yuzhou Zhou, Qiaozhu Zhai, <b>Xingbo Fu</b>, Xiaohong Guan, Feng Gao, Jiang Wu, Zhanbo Xu</i><br /> 314 IEEE Power & Energy Society General Meeting (PESGM 2019)<br /> 315 <a href="https://ieeexplore.ieee.org/abstract/document/8974101"><div class="paper">Paper</div></a> 316 </li> 317</ul> 318 319<h2>2018</h2> 320<ul> 321 <li> 322 <b>A Simulation Method of Solar Irradiance Data Based on Feature Clustering and MTPM</b><br /> 323 <i><b>Xingbo Fu</b>, Feng Gao, Jiang Wu, Xiaohong Guan, Xuan Li, Pengyuan Liu, Pai Li</i><br /> 324 World Congress on Intelligent Control and Automation (WCICA 2018)<br /> 325 <a href="https://ieeexplore.ieee.org/abstract/document/8630379"><div class="paper">Paper</div></a> 326 </li> 327 <li> 328 <b>
328Hybrid Features based K-means Clustering Algorithm for use in Electricity Customer Load Pattern Analysis</b><br /> 329 <i>Pengyuan Liu, Chenye Yang, Jiang Wu, <b>Xingbo Fu</b>, Ruanming Huang, Yichao Huang, Fei Fei</i><br /> 330 Chinese Control Conference (CCC 2018)<br /> 331 <a href="https://ieeexplore.ieee.org/abstract/document/8483451"><div class="paper">Paper</div></a> 332 </li> 333</ul> 334 335 </article> 336 337</div> 338 339 </div> 340 </div> 341 342 <footer style="padding-top: 15px"> 343 <div class="wrapper" style="height: 35px"> 344 ©2026 Xingbo Fu, Powered by <a href="https://jekyllrb.com/" style="color: #828282">Jekyll</a> & <a href="https://github.com/ys1998/academic-portfolio" style="color: #828282">Academic Portfolio</a>. 345 </div> 346 </footer> 347 348 </body> 349 350</html>
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.