On the interpretability and evaluation of graph representation learning
Exploring methods for interpreting and evaluating graph representation learning algorithms.
With the rising interest in graph representation learning, a variety of approaches have been proposed to effectively capture a graph's properties. While these approaches have improved performance in graph machine learning tasks compared to traditional graph techniques, they are still perceived as techniques with limited insight into the information encoded in these representations. In this work, we explore methods to interpret node embeddings and propose the creation of a robust evaluation framework for comparing graph representation learning algorithms and hyperparameters. We test our methods on graphs with different properties and investigate the relationship between embedding training parameters and the ability of the produced embedding to recover the structure of the original graph in a downstream task.
Latest publications
Towards scalable meta-learning of near-optimal interpretable models via synthetic model generations
An efficient, scalable method for generating synthetic pre-training data to enable meta-learning of decision trees.
NeurIPSR3: robust rubric-agnostic reward models
A novel reward modeling framework that is rubric-agnostic, generalizable, and provides reasoned score assignments.
NeurIPSSearching for efficient linear layers over a continuous space of structured matrices
Searching for efficient linear operators with optimal scaling laws leading to the development of the BTT-MoE architecture.
NeurIPS