With the growing number of machine learning (ML) algorithms, selecting the top-performing algorithms for a given dataset, task, and evaluation measure is known to be a challenging task. The human expertise required for this task has fueled the demand for automated solutions. Meta-learning is a popular approach for automatic algorithm selection based on dataset characterization. Existing meta-learning methods often represent the datasets using predefined features and thus cannot be generalized for various ML tasks, or alternatively, learn their representations in a supervised fashion, and thus cannot address unsupervised tasks. We first propose a novel learning-based task-agnostic method for dataset representation in this talk. Second, we present TRIO, a meta-learning approach based on the proposed dataset representation, which can accurately recommend top-performing algorithms for unseen datasets. TRIO first learns graphical representations from the datasets and then utilizes a graph convolutional neural network technique to extract their latent representations. An extensive evaluation of 337 datasets and 195 ML algorithms demonstrates the effectiveness of our approach over state-of-the-art methods for algorithm selection for both supervised (classification and regression) and unsupervised (clustering) tasks.