Face clustering can provide pseudo-labels to the massive unlabeled face data
and improve the performance of different face recognition models. The existing
clustering methods generally aggregate the features within subgraphs that are
often implemented based on a uniform threshold or a learned cutoff position.
This may reduce the recall of subgraphs and hence degrade the clustering
performance. This work proposed an efficient neighborhood-aware subgraph
adjustment method that can significantly reduce the noise and improve the
recall of the subgraphs, and hence can drive the distant nodes to converge
towards the same centers. More specifically, the proposed method consists of
two components, i.e. face embeddings enhancement using the embeddings from
neighbors, and enclosed subgraph construction of node pairs for structural
information extraction. The embeddings are combined to predict the linkage
probabilities for all node pairs to replace the cosine similarities to produce
new subgraphs that can be further used for aggregation of GCNs or other
clustering methods. The proposed method is validated through extensive
experiments against a range of clustering solutions using three benchmark
datasets and numerical results confirm that it outperforms the SOTA solutions
in terms of generalization capability.

本文提出了一种高效的邻域感知子图调整方法，可以显著减少噪声并提高子图召回率，从而驱动远程节点收敛到同一中心。该方法包括提取嵌入向量和构建节点对封闭子图两个部分，结合预测链路概率来产生新的子图用于图卷积网络或其他聚类方法的聚合。实验结果表明，该方法在三个基准数据集上优于现有解决方案。

优化子图聚类算法用于人脸聚类

Learn to Cluster Faces with Better Subgraphs

Temporal networks have been widely used to model real-world complex systems
such as financial systems and e-commerce systems. In a temporal network, the
joint neighborhood of a set of nodes often provides crucial structural
information useful for predicting whether they may interact at a certain time.
However, recent representation learning methods for temporal networks often
fail to extract such information or depend on online construction of structural
features, which is time-consuming. To address the issue, this work proposes
Neighborhood-Aware Temporal network model (NAT). For each node in the network,
NAT abandons the commonly-used one-single-vector-based representation while
adopting a novel dictionary-type neighborhood representation. Such a dictionary
representation records a downsampled set of the neighboring nodes as keys, and
allows fast construction of structural features for a joint neighborhood of
multiple nodes. We also design a dedicated data structure termed N-cache to
support parallel access and update of those dictionary representations on GPUs.
NAT gets evaluated over seven real-world large-scale temporal networks. NAT not
only outperforms all cutting-edge baselines by averaged 1.2% and 4.2% in
transductive and inductive link prediction accuracy, respectively, but also
keeps scalable by achieving a speed-up of 4.1-76.7x against the baselines that
adopt joint structural features and achieves a speed-up of 1.6-4.0x against the
baselines that cannot adopt those features. The link to the code: https:
//github.com/Graph-COM/Neighborhood-Aware-Temporal-Network.

该研究提出一种邻域感知的时间网络模型，使用一种新颖的字典类型邻域表示方法，设计了一种数据结构支持字典表示在 GPU 上并行访问和更新，通过实验表明，该模型在节点链接预测准确性（对于在归纳和传递方式下）优于最先进的基线方法，可以实现该特征的速度提升，并可扩展到多个实际大规模时间网络中。