Delayed Bottlenecking: Alleviating Forgetting in Pre-trained Graph Neural Networks

• URL: http://arxiv.org/abs/2404.14941v1
• Date: Tue, 23 Apr 2024 11:35:35 GMT
• Title: Delayed Bottlenecking: Alleviating Forgetting in Pre-trained Graph Neural Networks
• Authors: Zhe Zhao, Pengkun Wang, Xu Wang, Haibin Wen, Xiaolong Xie, Zhengyang Zhou, Qingfu Zhang, Yang Wang,
• Abstract summary: We propose a novel underlineDelayed underlineBottlenecking underlinePre-training framework. It maintains as much as possible mutual information between latent representations and training data during pre-training phase.
• Score: 19.941727879841142
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Learning with Noisy Foundation Models [95.50968225050012]
  This paper is the first work to comprehensively understand and analyze the nature of noise in pre-training datasets. We propose a tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise and improve generalization.
  arXiv  Detail & Related papers  (2024-03-11T16:22:41Z)
• Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks [39.71761440499148]
  Pre-training on graph neural networks (GNNs) aims to learn transferable knowledge for downstream tasks with unlabeled data. We propose a better-with-less framework for graph pre-training: fewer, but carefully chosen data are fed into a GNN model. Experiment results show that the proposed APT is able to obtain an efficient pre-training model with fewer training data and better downstream performance.
  arXiv  Detail & Related papers  (2023-11-02T07:09:59Z)
• Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks [91.15120211190519]
  This paper aims to understand the nature of noise in pre-training datasets and to mitigate its impact on downstream tasks. We propose a light-weight black-box tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise.
  arXiv  Detail & Related papers  (2023-09-29T06:18:15Z)
• SPOT: Scalable 3D Pre-training via Occupancy Prediction for Learning Transferable 3D Representations [76.45009891152178]
  Pretraining-finetuning approach can alleviate the labeling burden by fine-tuning a pre-trained backbone across various downstream datasets as well as tasks. We show, for the first time, that general representations learning can be achieved through the task of occupancy prediction. Our findings will facilitate the understanding of LiDAR points and pave the way for future advancements in LiDAR pre-training.
  arXiv  Detail & Related papers  (2023-09-19T11:13:01Z)
• When to Pre-Train Graph Neural Networks? From Data Generation Perspective! [19.239863500722983]
  Graph pre-training aims to acquire transferable knowledge from unlabeled graph data to improve downstream performance. This paper introduces a generic framework W2PGNN to answer the question of when to pre-train. W2PGNN offers three broad applications: providing the application scope of graph pre-trained models, the feasibility of pre-training, and assistance in selecting pre-training data to enhance downstream performance.
  arXiv  Detail & Related papers  (2023-03-29T05:05:02Z)
• SGL-PT: A Strong Graph Learner with Graph Prompt Tuning [36.650472660276]
  We propose a novel framework named SGL-PT which follows the learning strategy Pre-train, Prompt, and Predict''. Specifically, we raise a strong and universal pre-training task coined as SGL that acquires the complementary merits of generative and contrastive self-supervised graph learning. And aiming for graph classification task, we unify pre-training and fine-tuning by designing a novel verbalizer-free prompting function, which reformulates the downstream task in a similar format as pretext task.
  arXiv  Detail & Related papers  (2023-02-24T04:31:18Z)
• Self-Distillation for Further Pre-training of Transformers [83.84227016847096]
  We propose self-distillation as a regularization for a further pre-training stage. We empirically validate the efficacy of self-distillation on a variety of benchmark datasets for image and text classification tasks.
  arXiv  Detail & Related papers  (2022-09-30T02:25:12Z)
• Consecutive Pretraining: A Knowledge Transfer Learning Strategy with Relevant Unlabeled Data for Remote Sensing Domain [25.84756140221655]
  ConSecutive PreTraining (CSPT) is proposed based on the idea of not stopping pretraining in natural language processing (NLP) The proposed CSPT also can release the huge potential of unlabeled data for task-aware model training. The results show that by utilizing the proposed CSPT for task-aware model training, almost all downstream tasks in RSD can outperform the previous method of supervised pretraining-then-fine-tuning.
  arXiv  Detail & Related papers  (2022-07-08T12:32:09Z)
• Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors [59.93972277761501]
  We show that we can learn highly informative posteriors from the source task, through supervised or self-supervised approaches. This simple modular approach enables significant performance gains and more data-efficient learning on a variety of downstream classification and segmentation tasks.
  arXiv  Detail & Related papers  (2022-05-20T16:19:30Z)
• Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability [53.27240222619834]
  Knowledge Distillation as Efficient Pre-training aims to efficiently transfer the learned feature representation from pre-trained models to new student models for future downstream tasks. Our method performs comparably with supervised pre-training counterparts in 3 downstream tasks and 9 downstream datasets requiring 10x less data and 5x less pre-training time.
  arXiv  Detail & Related papers  (2022-03-10T06:23:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.