Link prediction aims to infer the link existence between pairs of nodes in
networks/graphs. Despite their wide application, the success of traditional
link prediction algorithms is hindered by three major challenges -- link
sparsity, node attribute noise and dynamic changes -- that are faced by many
real-world networks. To address these challenges, we propose a Contextualized
Self-Supervised Learning (CSSL) framework that fully exploits structural
context prediction for link prediction. The proposed CSSL framework learns a
link encoder to infer the link existence probability from paired node
embeddings, which are constructed via a transformation on node attributes. To
generate informative node embeddings for link prediction, structural context
prediction is leveraged as a self-supervised learning task to boost the link
prediction performance. Two types of structural context are investigated, i.e.,
context nodes collected from random walks vs. context subgraphs. The CSSL
framework can be trained in an end-to-end manner, with the learning of model
parameters supervised by both the link prediction and self-supervised learning
tasks. The proposed CSSL is a generic and flexible framework in the sense that
it can handle both attributed and non-attributed networks, and operate under
both transductive and inductive link prediction settings. Extensive experiments
and ablation studies on seven real-world benchmark networks demonstrate the
superior performance of the proposed self-supervision based link prediction
algorithm over state-of-the-art baselines, on different types of networks under
both transductive and inductive settings. The proposed CSSL also yields
competitive performance in terms of its robustness to node attribute noise and
scalability over large-scale networks.

提出一种结构化上下文感知自监督学习（CSSL）的方法，通过两种不同结构上下文的预测，在端到端的训练中，构建一个链接编码器来推断链路存在概率。CSSL 可以处理有、无属性的网络，并且在诸如节点属性噪声鲁棒性和大规模网络的可扩展性方面具有竞争力。

上下文自监督下的链接预测

Link Prediction with Contextualized Self-Supervision

Classical non-neural dependency parsers put considerable effort on the design
of feature functions. Especially, they benefit from information coming from
structural features, such as features drawn from neighboring tokens in the
dependency tree. In contrast, their BiLSTM-based successors achieve
state-of-the-art performance without explicit information about the structural
context. In this paper we aim to answer the question: How much structural
context are the BiLSTM representations able to capture implicitly? We show that
features drawn from partial subtrees become redundant when the BiLSTMs are
used. We provide a deep insight into information flow in transition- and
graph-based neural architectures to demonstrate where the implicit information
comes from when the parsers make their decisions. Finally, with model ablations
we demonstrate that the structural context is not only present in the models,
but it significantly influences their performance.

本文比较了传统的非神经依存解析器和基于 BiLSTM 模型的依存解析器的结构特征，讨论了其决策过程中的隐含信息来源，并通过模型实验表明，结构上下文对模型有着显著的影响。