首页/论文/2102.10403

arXiv 2102.104032021-02-20cs.LG

GLAM: Graph Learning by Modeling Affinity to Labeled Nodes for Graph Neural Networks

Microsoft Research India（微软研究院印度分部）

Vijay Lingam, Arun Iyer, Rahul Ragesh

备注：: 11 pages, 4 figures

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Graph Neural Networks have shown excellent performance on semi-supervised classification tasks. However, they assume access to a graph that may not be often available in practice. In the absence of any graph, constructing k-Nearest Neighbor (kNN) graphs from the given data have shown to give improvements when used with GNNs over other semi-supervised methods. This paper proposes a semi-supervised graph learning method for cases when there are no graphs available. This method learns a graph as a convex combination of the unsupervised kNN graph and a supervised label-affinity graph. The label-affinity graph directly captures all the nodes' label-affinity with the labeled nodes, i.e., how likely a node has the same label as the labeled nodes. This affinity measure contrasts with the kNN graph where the metric measures closeness in the feature space. Our experiments suggest that this approach gives close to or better performance (up to 1.5%), while being simpler and faster (up to 70x) to train, than state-of-the-art graph learning methods. We also conduct several experiments to highlight the importance of individual components and contrast them with state-of-the-art methods.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Affinity Mixup for Weakly Supervised Sound Event Detection

The weakly supervised sound event detection problem is the task of predicting the presence of sound events and their corresponding starting and ending points in a weakly labeled dataset. A weak dataset associates each training sample (a short recording) to one or more present sources. Networks that solely rely on convolutional and recurrent layers cannot directly relate multiple frames in a recording. Motivated by attention and graph neural networks, we introduce the concept of an affinity mixup to incorporate time-level similarities and make a connection between frames. This regularization te…

2021-06-21cs.LGcs.SDeess.AS

Semi-supervised Data Representation via Affinity Graph Learning

National University of Defense Technology（国防科技大学）

We consider the general problem of utilizing both labeled and unlabeled data to improve data representation performance. A new semi-supervised learning framework is proposed by combing manifold regularization and data representation methods such as Non negative matrix factorization and sparse coding. We adopt unsupervised data representation methods as the learning machines because they do not depend on the labeled data, which can improve machine's generation ability as much as possible. The proposed framework forms the Laplacian regularizer through learning the affinity graph. We incorporate …

2015-02-13cs.CVcs.LG

DualBind：用于蛋白质-配体结合亲和力预测的双损失框架

DualBind: A Dual-Loss Framework for Protein-Ligand Binding Affinity Prediction

NVIDIA（英伟达）

本文提出 DualBind 双损失框架，融合监督 MSE 与无监督 DSM 学习结合能函数，以减少标注依赖并提升亲和力预测精度与泛化性。

2024-06-11cs.AIcs.LGq-bio.QM

DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networks

Texas A&M University（得克萨斯农工大学）

Motivation: Drug discovery demands rapid quantification of compound-protein interaction (CPI). However, there is a lack of methods that can predict compound-protein affinity from sequences alone with high applicability, accuracy, and interpretability. Results: We present a seamless integration of domain knowledges and learning-based approaches. Under novel representations of structurally-annotated protein sequences, a semi-supervised deep learning model that unifies recurrent and convolutional neural networks has been proposed to exploit both unlabeled and labeled data, for jointly encoding mo…

2018-12-08cs.LGq-bio.BMstat.ML

DecoyDB：用于蛋白质-配体结合亲和力预测的图对比学习数据集

DecoyDB: A Dataset for Graph Contrastive Learning in Protein-Ligand Binding Affinity Prediction

Department of CISE, University of Florida（计算机与信息科学系，佛罗里达大学）

针对蛋白质-配体结合亲和力预测中标签稀缺问题，提出大规模结构感知数据集DecoyDB及定制图对比学习框架，预训练后微调显著提升准确性、标签效率和泛化性。

2025-07-08cs.LGq-bio.BM

HeMeNet：用于蛋白质多任务学习的异构多通道等变网络

HeMeNet: Heterogeneous Multichannel Equivariant Network for Protein Multitask Learning

Tsinghua University（清华大学）；Renmin University of China（中国人民大学）；Ant Group（蚂蚁集团）

本文提出HeMeNet，一种E(3)等变的异构多通道图神经网络，并构建Protein-MT多任务基准，通过联合学习6个蛋白质任务提升性能并超越现有方法。

2024-04-02cs.LG

更多相关论文收起更多论文

Cross-Domain Label Propagation for Domain Adaptation with Discriminative Graph Self-Learning

Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Nanjing University of Science and Technology（南京理工大学）

Domain adaptation manages to transfer the knowledge of well-labeled source data to unlabeled target data. Many recent efforts focus on improving the prediction accuracy of target pseudo-labels to reduce conditional distribution shift. In this paper, we propose a novel domain adaptation method, which infers target pseudo-labels through cross-domain label propagation, such that the underlying manifold structure of two domain data can be explored. Unlike existing cross-domain label propagation methods that separate domain-invariant feature learning, affinity matrix constructing and target labels …

2023-02-17cs.LG

Efficient Distributed Semi-Supervised Learning using Stochastic Regularization over Affinity Graphs

Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）；University of Washington（华盛顿大学）

We describe a computationally efficient, stochastic graph-regularization technique that can be utilized for the semi-supervised training of deep neural networks in a parallel or distributed setting. We utilize a technique, first described in [13] for the construction of mini-batches for stochastic gradient descent (SGD) based on synthesized partitions of an affinity graph that are consistent with the graph structure, but also preserve enough stochasticity for convergence of SGD to good local minima. We show how our technique allows a graph-based semi-supervised loss function to be decomposed i…

2018-05-30cs.DCcs.LGstat.ML

T3R：通过梯度旋转实现图神经网络的更深层测试时自适应

T3R: Deeper Test-Time Adaptation for Graph Neural Networks via Gradient Rotation

Bernoulli Institute, University of Groningen（Groningen大学伯努利研究所）；Informatics Institute, University of Amsterdam（阿姆斯特丹大学信息学院）

提出T3R方法，利用多个Rotograd矩阵提升目标与辅助任务的任务亲和度，并通过梯度旋转技术实现几乎整个架构的深层自适应，在回归和分类任务上显著提升性能。

2026-06-29cs.AIcs.LG

无标签数据上深度神经网络的特征亲和性辅助知识蒸馏与量化

Feature Affinity Assisted Knowledge Distillation and Quantization of Deep Neural Networks on Label-Free Data

University of California, Irvine（加州大学欧文分校）；State University of New York at Albany（纽约州立大学奥尔巴尼分校）

提出 FAQD 方法，用中间特征图的特征亲和性结合 logit 蒸馏，在无标签数据上增强量化学生网络的训练，并以低复杂度 FFA 损失加速高分辨率训练。

2023-08-18cs.AIcs.ITcs.LG

Semi-Supervised Learning on Graphs through Reach and Distance Diffusion

Google Research（谷歌研究院）

Semi-supervised learning (SSL) is an indispensable tool when there are few labeled entities and many unlabeled entities for which we want to predict labels. With graph-based methods, entities correspond to nodes in a graph and edges represent strong relations. At the heart of SSL algorithms is the specification of a dense {\em kernel} of pairwise affinity values from the graph structure. A learning algorithm is then trained on the kernel together with labeled entities. The most popular kernels are {\em spectral} and include the highly scalable "symmetric" Laplacian methods, that compute a soft…

2017-01-20cs.LG

Label Propagation Through Optimal Transport

Université Sorbonne Paris Nord（索邦巴黎北大学）；Université Clermont Auvergne（克莱蒙奥弗涅大学）

In this paper, we tackle the transductive semi-supervised learning problem that aims to obtain label predictions for the given unlabeled data points according to Vapnik's principle. Our proposed approach is based on optimal transport, a mathematical theory that has been successfully used to address various machine learning problems, and is starting to attract renewed interest in semi-supervised learning community. The proposed approach, Optimal Transport Propagation (OTP), performs in an incremental process, label propagation through the edges of a complete bipartite edge-weighted graph, whose…

2021-10-01cs.LG

S-MolSearch：面向生物活性分子搜索的3D半监督对比学习

S-MolSearch: 3D Semi-supervised Contrastive Learning for Bioactive Molecule Search

Renmin University of China（中国人民大学）；DP Technology（DP科技）

本文提出S-MolSearch框架，首次将分子3D信息与亲和力信息结合用于半监督对比学习，通过逆最优传输利用无标签数据，在LIT-PCBA和DUD-E基准上超越现有虚拟筛选方法。

2024-11-21cs.LGq-bio.BM

Adversarial Deep Network Embedding for Cross-network Node Classification

The Hong Kong Polytechnic University（香港理工大学）；University of Electronic Science and Technology of China（电子科技大学）

In this paper, the task of cross-network node classification, which leverages the abundant labeled nodes from a source network to help classify unlabeled nodes in a target network, is studied. The existing domain adaptation algorithms generally fail to model the network structural information, and the current network embedding models mainly focus on single-network applications. Thus, both of them cannot be directly applied to solve the cross-network node classification problem. This motivates us to propose an adversarial cross-network deep network embedding (ACDNE) model to integrate adversari…

2020-02-18cs.LGcs.SI

通过同质性引导自监督测试时训练实现跨域图异常检测

Cross-Domain Graph Anomaly Detection via Test-Time Training with Homophily-Guided Self-Supervision

Rice University（里士大学）

针对跨图域GAD中的分布偏移、异构特征与异常标签稀缺问题，提出GADT3测试时训练框架，通过同质性引导自监督及四项创新实现域适应，并显著提升AUROC与AUPRC。

2025-10-19cs.AIcs.LGcs.SI