Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Zheng, Qinghua"'
Federated learning (FL) is an emerging technique that trains massive and geographically distributed edge data while maintaining privacy. However, FL has inherent challenges in terms of fairness and computational efficiency due to the rising heterogen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::29514b88979bb9dbc533239a5001179d
http://arxiv.org/abs/2302.04464
http://arxiv.org/abs/2302.04464
Autor:
Wang, Yingchun, Guo, Jingcai, Liu, Yi, Guo, Song, Zhang, Weizhan, Cao, Xiangyong, Zheng, Qinghua
Model substructure learning aims to find an invariant network substructure that can have better out-of-distribution (OOD) generalization than the original full structure. Existing works usually search the invariant substructure using modular risk min
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4c0c4e68061f32d4532baa6574ebc4f1
Novel category discovery aims at adapting models trained on known categories to novel categories. Previous works only focus on the scenario where known and novel categories are of the same granularity. In this paper, we investigate a new practical sc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cf0a05a1812280add4f1646996d4024c
http://arxiv.org/abs/2210.07733
http://arxiv.org/abs/2210.07733
Autor:
Yang, Shujie, Zhang, Binchi, Feng, Shangbin, Tan, Zhaoxuan, Zheng, Qinghua, Zhou, Jun, Luo, Minnan
Graph anomaly detection on attributed networks has become a prevalent research topic due to its broad applications in many influential domains. In real-world scenarios, nodes and edges in attributed networks usually display distinct heterogeneity, i.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4e76ad5200f900227d79ece8c7c7a1ad
http://arxiv.org/abs/2208.08200
http://arxiv.org/abs/2208.08200
Recent studies have revealed that GNNs are vulnerable to adversarial attacks. Most existing robust graph learning methods measure model robustness based on label information, rendering them infeasible when label information is not available. A straig
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::daaf9a693fe10c63a9043d921bf6e89a
Graph convolutional networks (GCNs) have been widely adopted for graph representation learning and achieved impressive performance. For larger graphs stored separately on different clients, distributed GCN training algorithms were proposed to improve
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::781a553d19b3df3a2775371fdd054f85
http://arxiv.org/abs/2110.12906
http://arxiv.org/abs/2110.12906
Knowledge transfer from a source domain to a different but semantically related target domain has long been an important topic in the context of unsupervised domain adaptation (UDA). A key challenge in this field is establishing a metric that can exa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::98f6513be42d84c441664ea6c08406fe
http://arxiv.org/abs/2007.09312
http://arxiv.org/abs/2007.09312
To take full advantage of fast-growing unlabeled networked data, this paper introduces a novel self-supervised strategy for graph representation learning by exploiting natural supervision provided by the data itself. Inspired by human social behavior
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1c5be0959fa910408d7723a4946c520d
Autor:
Tian, Feng, Yue, Jia, Chao, Kuo-ming, Qian, Buyue, Shah, Nazaraf, Li, Longzhuang, Zhu, Haiping, Chen, Yan, Zeng, Bin, Zheng, Qinghua
Cognitive and metacognitive strategy had demonstrated a significant role in self-regulated learning (SRL), and an appropriate use of strategies is beneficial to effective learning or question-solving tasks during a human-computer interaction process.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6ad3ea158e936e59a106a992761ffcd9
In this paper we describe an algorithm for estimating the provenance of hacks on websites. That is, given properties of sites and the temporal occurrence of attacks, we are able to attribute individual attacks to joint causes and vulnerabilities, as
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1d3d893082362ab38ffb2e3041cc05d6
http://arxiv.org/abs/1611.03021
http://arxiv.org/abs/1611.03021