Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks
Recent years have witnessed the great success of graph pre-training for graph representation learning. With hundreds of graph pre-training tasks proposed, integrating knowledge acquired from multiple pre-training tasks has become a popular research topic. In this paper, we identify two important collaborative processes for this topic: (1) select: how to select an optimal task combination from a given task pool based on their compatibility, and (2) weigh: how to weigh the selected tasks based on their importance. While there currently has been a lot of work focused on weighing, comparatively little effort has been devoted to selecting. This paper proposes a novel instance-level framework for integrating multiple graph pre-training tasks, Weigh And Select (WAS), where the two collaborative processes, weighing and selecting, are combined by decoupled siamese networks. Specifically, it first adaptively learns an optimal combination of tasks for each instance from a given task pool, based on which a customized instance-level task weighing strategy is learned. Extensive experiments on 16 graph datasets across node-level and graph-level downstream tasks have demonstrated that by combining a few simple but classical tasks, WAS can achieve comparable performance to other leading counterparts. The code is available at https://github.com/TianyuFan0504/WAS.
Code (1)
Tasks
Graph Representation LearningRepresentation LearningSimilar Papers 제목 키워드 기반
MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry
We propose the MAC-VO, a novel learning-based stereo VO that leverages the learned metrics-aware matching uncertainty for dual purposes: selecting keypoint and weighing the residual in pose graph optimization. Compared t…
Decision MakingPose EstimationVisual OdometryLearning to Restore Multi-Degraded Images via Ingredient Decoupling and Task-Aware Path Adaptation
Image restoration (IR) aims to recover clean images from degraded observations. Despite remarkable progress, most existing methods focus on a single degradation type, whereas real-world images often suffer from multiple …
Image RestorationA matrix pencil approach to the Morgan's problem
The problem of decoupling a nonsquare state space system by state feedback with singular input transformation is considered. The problem is solved by conducting a finite search for decouplable square systems, appropriate…
Surface Form Competition: Why the Highest Probability Answer Isn’t Always Right
Large language models have shown promising results in zero-shot settings. For example, they can perform multiple choice tasks simply by conditioning on a question and selecting the answer with the highest probability. Ho…
FormMultiple-choicevalidBoosting Fair Classifier Generalization through Adaptive Priority Reweighing
With the increasing penetration of machine learning applications in critical decision-making areas, calls for algorithmic fairness are more prominent. Although there have been various modalities to improve algorithmic fa…
Decision MakingFairness