GraphECC: Enhancing GraphSMOTE with enhanced complementary classifier

分类器(UML) 计算机科学 人工智能
作者
Liwen Xu,Jiali Chen
出处
期刊:Journal of Intelligent and Fuzzy Systems [IOS Press]
卷期号:: 1-13
标识
DOI:10.3233/jifs-239663
摘要

Node classification in graph learning faces significant challenges due to imbalanced data, particularly for under-represented samples from minority classes. To address this issue, existing methods often rely on synthetic minority over-sampling techniques, introducing additional complexity during model training. In light of the challenges faced, we introduce GraphECC, an innovative approach that addresses numerical anomalies in large-scale datasets by supplanting the traditional CE loss function with an Enhanced Complementary Classifier (ECC) loss function’a novel modification to the CCE loss. This alteration ensures computational stability and mitigates potential numerical anomalies by incorporating a slight offset in the denominator during the computation of the complementary probability distribution. In this paper, we present a novel training paradigm, the Enhanced Complementary Classifier (ECC), which offers “imbalance defense for free” without the need for extra procedures to improve node classification accuracy.The ECC approach optimizes model probabilities for the ground-truth class, akin to the cross-entropy method. Additionally, it effectively neutralizes probabilities associated with incorrect classes through a “guided” term, achieving a balanced trade-off between the two aspects. Experimental results demonstrate that our proposed method not only enhances model robustness but also surpasses the widely used cross-entropy training objective.Moreover, we demonstrate the versatility of our method by seamlessly integrating it with various well-known adversarial training techniques, resulting in significant gains in robustness. Notably, our approach represents a breakthrough, as it enhances model robustness without compromising performance, distinguishing it from previous attempts.The code for GraphECC can be accessed from the following link:https://github.com/12chen20/GraphECC.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
2秒前
我嘞个豆完成签到,获得积分10
2秒前
爱笑晓曼发布了新的文献求助10
3秒前
wdy111应助sc采纳,获得20
3秒前
敏感初露发布了新的文献求助10
3秒前
隐形曼青应助机智思真采纳,获得10
6秒前
思源应助时尚俊驰采纳,获得10
6秒前
可爱的函函应助敏感初露采纳,获得10
6秒前
7秒前
爆米花应助橙子采纳,获得10
10秒前
量子星尘发布了新的文献求助10
12秒前
阿满完成签到 ,获得积分10
13秒前
王馨雨完成签到,获得积分10
14秒前
在水一方应助袁涛采纳,获得10
14秒前
爱笑晓曼完成签到,获得积分10
17秒前
18秒前
19秒前
nuoran发布了新的文献求助10
20秒前
20秒前
乐乐宝完成签到,获得积分10
21秒前
22秒前
彭于晏应助阿钉采纳,获得10
23秒前
孙燕应助阿钉采纳,获得10
23秒前
整齐小松鼠应助阿钉采纳,获得10
23秒前
jszhoucl发布了新的文献求助10
24秒前
一定行发布了新的文献求助10
24秒前
jxlu发布了新的文献求助10
25秒前
27秒前
橙子发布了新的文献求助10
27秒前
科研通AI5应助科研通管家采纳,获得10
28秒前
李健应助科研通管家采纳,获得10
28秒前
爆米花应助科研通管家采纳,获得10
28秒前
乐乐应助科研通管家采纳,获得10
28秒前
天天快乐应助科研通管家采纳,获得10
28秒前
科研通AI2S应助科研通管家采纳,获得10
28秒前
CipherSage应助科研通管家采纳,获得10
29秒前
科研通AI5应助科研通管家采纳,获得10
29秒前
29秒前
华仔应助科研通管家采纳,获得10
29秒前
29秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989378
求助须知:如何正确求助?哪些是违规求助? 3531442
关于积分的说明 11254002
捐赠科研通 3270126
什么是DOI,文献DOI怎么找? 1804887
邀请新用户注册赠送积分活动 882087
科研通“疑难数据库(出版商)”最低求助积分说明 809173