Abstract
Pre-training GNNs to extract transferable knowledge and apply it to downstream tasks has become the de facto standard of graph representation learning. Recent works focused on designing self-supervised pre-training tasks to extract useful and universal transferable knowledge from large-scale unlabeled data. However, they have to face an inevitable question: traditional pre-training strategies that aim at extracting useful information about pre-training tasks, may not extract all useful information about the downstream task. In this paper, we reexamine the pre-training process within traditional pre-training and fine-tuning frameworks from the perspective of Information Bottleneck (IB) and confirm that the forgetting phenomenon in pre-training phase may cause detrimental effects on downstream tasks. Therefore, we propose a novel \underline{D}elayed \underline{B}ottlenecking \underline{P}re-training (DBP) framework which maintains as much as possible mutual information between latent representations and training data during pre-training phase by suppressing the compression operation and delays the compression operation to fine-tuning phase to make sure the compression can be guided with labeled fine-tuning data and downstream tasks. To achieve this, we design two information control objectives that can be directly optimized and further integrate them into the actual model design. Extensive experiments on both chemistry and biology domains demonstrate the effectiveness of DBP.
Abstract (translated)
将预训练的图神经网络提取可转移知识并将其应用于下游任务的实际标准已经成为了图形表示学习的事实标准。 最近的工作集中在设计自监督的预训练任务,以从大规模未标注数据中提取有用的和通用的可转移知识。 然而,他们必须面对一个不可避免的质疑: 旨在提取预训练任务的有用信息的传统预训练策略,可能无法提取下游任务的全部有用信息。 在本文中,我们重新审视了传统预训练和微调框架中的预训练过程,从信息瓶颈(IB)的角度出发,证实了预训练阶段遗忘现象可能会对下游任务造成严重损害。 因此,我们提出了一个新颖的 \underline{D}elayed \underline{B}ottlenecking \underline{P}re-training (DBP)框架,该框架在预训练阶段通过抑制压缩操作来尽可能保持潜在表示和训练数据之间的互信息,并将压缩操作延迟到微调阶段,以确保压缩可以引导有标签的微调数据和下游任务。 为了实现这一目标,我们设计了一个可以直接优化且可以进一步集成到实际模型设计中的两个信息控制目标。 在化学和生物学领域进行的大量实验证明DBP的有效性。
URL
https://arxiv.org/abs/2404.14941