Search

Graph contrastive learning (GCL) has been successfully used to solve the problem of the huge cost of graph data annotation, such as labor cost, time cost, and professional knowledge cost. Recent works have focused on improving the generalization performance of GCL with automated data augmentation. However, GCL methods with automated data augmentation encode the graph representation using fixed graph encoders, which will result in performance loss. To overcome this limitation, we propose Adaptive graph contrastive learning with joint optimization of data Augmentation and graph Encoder (AdaAE). AdaAE is the first method to learn to adapt the graph encoder for each dataset for GCL with automated data augmentation. Specifically, we design a unified GCL search space, which means that we treat both data augmentation and graph encoder as architecture components. AdaAE employs the adaptive architecture optimizer based on a differentiable search method to learn the sample probability distribution of each architecture component. The adaptive architecture optimizer generates an operation of each architecture component based on the sample probability distribution to construct the GCL model. Then, the validation results of the GCL model are used as the feedback signal of the adaptive architecture optimizer to optimize the sample probability distribution of each architecture component. Extensive experiments demonstrate that AdaAE performs more superior than the state-of-the-art baselines. Furthermore, the visualization results confirm that AdaAE can clearly distinguish different classes in the projection space. [ABSTRACT FROM AUTHOR]

Graph Neural Architecture Search (Graph-NAS) methods have shown great potential in finding better graph neural network designs compared to handcrafted designs. However, existing Graph-NAS frameworks are based on complex algorithms and fail to maintain low costs for high scalability with high performance. They require full training of thousands of graph neural networks to inform the search process, resulting in a prohibitive computational cost, which is not necessarily affordable for the users interested. Due to the computation cost, many researchers have limited the search space exploration ability, which may lead to a local optimum solution. In this paper, we propose a performance predictor-based graph neural architecture search (PGNAS) framework. The proposed approach consists of three conceptually much simpler and basic phases, and can broadly explore a search space with a much cheaper computation cost. We train n sampled architectures from a search space to generate n (architecture, validation accuracy) pairs used to train a performance distributions learner where the features are represented by the architecture description and the validation accuracy denotes the target. Next, we use this performance distribution learner to predict the validation accuracies of architectures in the search space. Finally, we train the top-K predicted architectures and choose the architecture with the best validation result. Although our approach seems simple, it is efficient and scalable; experiment results show that PGNAS outperforms existing both handcrafted and Graph-NAS models on four benchmark datasets. [ABSTRACT FROM AUTHOR]

Graph neural networks (GNNs) have received much attention as GNNs have recently been successfully applied on non-euclidean data. However, artificially designed graph neural networks often fail to get satisfactory model performance for a given graph data. Graph neural architecture search effectively constructs the GNNs that achieve the expected model performance with the rise of automatic machine learning. The challenge is efficiently and automatically getting the optimal GNN architecture in a vast search space. Existing search methods serially evaluate the GNN architectures, severely limiting system efficiency. To solve these problems, we develop an Automatic Graph Neural Architecture Search framework (Auto-GNAS) with parallel estimation to implement an automatic graph neural search process that requires almost no manual intervention. In Auto-GNAS, we design the search algorithm with multiple genetic searchers. Each searcher can simultaneously use evaluation feedback information, information entropy, and search results from other searchers based on sharing mechanism to improve the search efficiency. As far as we know, this is the first work using parallel computing to improve the system efficiency of graph neural architecture search. According to the experiment on the real datasets, Auto-GNAS obtain competitive model performance and better search efficiency than other search algorithms. Since the parallel estimation ability of Auto-GNAS is independent of search algorithms, we expand different search algorithms based on Auto-GNAS for scalability experiments. The results show that Auto-GNAS with varying search algorithms can achieve nearly linear acceleration with the increase of computing resources. [ABSTRACT FROM AUTHOR]