FiGURe: Simple and Efficient Unsupervised Node Representations with Filter Augmentations

TL;DR

FiGURe introduces a simple, filter-based augmentation technique for contrastive learning of node representations, improving performance and efficiency by capturing different eigen-spectrum parts and reducing computational costs.

Contribution

The paper proposes a novel filter augmentation method for unsupervised node representation learning that enhances performance and reduces computational load through shared weights and low-dimensional embeddings.

Findings

Achieves up to 4.4% performance gain over state-of-the-art.

Effective across both homophilic and heterophilic datasets.

Reduces computational costs with shared weights and low-dimensional embeddings.

Abstract

Unsupervised node representations learnt using contrastive learning-based methods have shown good performance on downstream tasks. However, these methods rely on augmentations that mimic low-pass filters, limiting their performance on tasks requiring different eigen-spectrum parts. This paper presents a simple filter-based augmentation method to capture different parts of the eigen-spectrum. We show significant improvements using these augmentations. Further, we show that sharing the same weights across these different filter augmentations is possible, reducing the computational load. In addition, previous works have shown that good performance on downstream tasks requires high dimensional representations. Working with high dimensions increases the computations, especially when multiple augmentations are involved. We mitigate this problem and recover good performance through lower dimensional embeddings using simple random Fourier feature projections. Our method, FiGURe achieves an average gain of up to 4.4%, compared to the state-of-the-art unsupervised models, across all datasets in consideration, both homophilic and heterophilic. Our code can be found at: https://github.com/microsoft/figure.