中文
相关论文

相关论文: Towards Precise Prediction Uncertainty in GNNs: Re…

200 篇论文

Graph neural networks (GNNs) have exhibited impressive performance in modeling graph data as exemplified in various applications. Recently, the GNN calibration problem has attracted increasing attention, especially in cost-sensitive…

机器学习 · 计算机科学 2023-12-20 Boshi Tang , Zhiyong Wu , Xixin Wu , Qiaochu Huang , Jun Chen , Shun Lei , Helen Meng

Despite Graph Neural Networks (GNNs) have achieved remarkable accuracy, whether the results are trustworthy is still unexplored. Previous studies suggest that many modern neural networks are over-confident on the predictions, however,…

机器学习 · 计算机科学 2022-01-05 Xiao Wang , Hongrui Liu , Chuan Shi , Cheng Yang

Graph Neural Networks deliver strong classification results but often suffer from poor calibration performance, leading to overconfidence or underconfidence. This is particularly problematic in high stakes applications where accurate…

机器学习 · 计算机科学 2025-03-03 Dingyi Zhuang , Chonghe Jiang , Yunhan Zheng , Shenhao Wang , Jinhua Zhao

Given the importance of getting calibrated predictions and reliable uncertainty estimations, various post-hoc calibration methods have been developed for neural networks on standard multi-class classification tasks. However, these methods…

机器学习 · 计算机科学 2022-10-13 Hans Hao-Hsun Hsu , Yuesong Shen , Christian Tomani , Daniel Cremers

Graph Neural Networks (GNNs) have demonstrated remarkable effectiveness on graph-based tasks. However, their predictive confidence is often miscalibrated, typically exhibiting under-confidence, which harms the reliability of their…

机器学习 · 计算机科学 2025-09-30 Jincheng Huang , Jie Xu , Xiaoshuang Shi , Ping Hu , Lei Feng , Xiaofeng Zhu

Despite their impressive predictive performance, GNNs often exhibit poor confidence calibration, i.e., their predicted confidence scores do not accurately reflect true correctness likelihood. This issue raises concerns about their…

机器学习 · 计算机科学 2025-03-25 Yilong Wang , Jiahao Zhang , Tianxiang Zhao , Suhang Wang

Graphs can model real-world, complex systems by representing entities and their interactions in terms of nodes and edges. To better exploit the graph structure, graph neural networks have been developed, which learn entity and edge…

机器学习 · 计算机科学 2022-06-06 Tong Liu , Yushan Liu , Marcel Hildebrandt , Mitchell Joblin , Hang Li , Volker Tresp

Deep neural networks are notoriously miscalibrated, i.e., their outputs do not reflect the true probability of the event we aim to predict. While networks for tabular or image data are usually overconfident, recent works have shown that…

机器学习 · 计算机科学 2024-03-11 Erik Nascimento , Diego Mesquita , Samuel Kaski , Amauri H Souza

Confidence calibration -- the problem of predicting probability estimates representative of the true correctness likelihood -- is important for classification models in many applications. We discover that modern neural networks, unlike…

机器学习 · 计算机科学 2017-08-04 Chuan Guo , Geoff Pleiss , Yu Sun , Kilian Q. Weinberger

Accurate uncertainty quantification in graph neural networks (GNNs) is essential, especially in high-stakes domains where GNNs are frequently employed. Conformal prediction (CP) offers a promising framework for quantifying uncertainty by…

机器学习 · 计算机科学 2023-12-06 Seohyeon Cha , Honggu Kang , Joonhyuk Kang

Graph Neural Networks (GNNs) have proven to be successful in many classification tasks, outperforming previous state-of-the-art methods in terms of accuracy. However, accuracy alone is not enough for high-stakes decision making. Decision…

机器学习 · 计算机科学 2019-06-04 Leonardo Teixeira , Brian Jalaian , Bruno Ribeiro

The prediction reliability of neural networks is important in many applications. Specifically, in safety-critical domains, such as cancer prediction or autonomous driving, a reliable confidence of model's prediction is critical for the…

计算机视觉与模式识别 · 计算机科学 2019-09-24 Byeongmoon Ji , Hyemin Jung , Jihyeun Yoon , Kyungyul Kim , Younghak Shin

Graph Neural Networks (GNNs) have shown great promise in learning node embeddings for link prediction (LP). While numerous studies aim to improve the overall LP performance of GNNs, none have explored its varying performance across…

机器学习 · 计算机科学 2023-10-10 Yu Wang , Tong Zhao , Yuying Zhao , Yunchao Liu , Xueqi Cheng , Neil Shah , Tyler Derr

Albeit achieving high predictive accuracy across many challenging computer vision problems, recent studies suggest that deep neural networks (DNNs) tend to make overconfident predictions, rendering them poorly calibrated. Most of the…

计算机视觉与模式识别 · 计算机科学 2023-06-16 Bimsara Pathiraja , Malitha Gunawardhana , Muhammad Haris Khan

Recommender systems based on graph neural networks perform well in tasks such as rating and ranking. However, in real-world recommendation scenarios, noise such as user misuse and malicious advertisement gradually accumulates through the…

信息检索 · 计算机科学 2025-05-23 Meng Yan , Cai Xu , Xujing Wang , Ziyu Guan , Wei Zhao , Yuhang Zhou

Generating confidence calibrated outputs is of utmost importance for the applications of deep neural networks in safety-critical decision-making systems. The output of a neural network is a probability distribution where the scores are…

机器学习 · 计算机科学 2021-09-17 Chihuang Liu , Joseph JaJa

Consistency training is a popular method to improve deep learning models in computer vision and natural language processing. Graph neural networks (GNNs) have achieved remarkable performance in a variety of network science learning tasks,…

机器学习 · 计算机科学 2021-10-14 Cole Hawkins , Vassilis N. Ioannidis , Soji Adeshina , George Karypis

Graph Neural Networks (GNNs) have emerged as powerful tools for predicting outcomes in graph-structured data. However, a notable limitation of GNNs is their inability to provide robust uncertainty estimates, which undermines their…

机器学习 · 计算机科学 2024-10-10 S. Akansha

Well-calibrated predictions of user preferences are essential for many applications. Since recommender systems typically select the top-N items for users, calibration for those top-N items, rather than for all items, is important. We show…

信息检索 · 计算机科学 2024-08-22 Masahiro Sato

Graph Neural Networks (GNNs) have proven to be powerful in many graph-based applications. However, they fail to generalize well under heterophilic setups, where neighbor nodes have different labels. To address this challenge, we employ a…

机器学习 · 计算机科学 2023-04-13 Yoonhyuk Choi , Jiho Choi , Taewook Ko , Chong-Kwon Kim
‹ 上一页 1 2 3 10 下一页 ›