Iso-CapsNet: Isomorphic Capsule Network for Brain Graph Representation Learning

TL;DR

Iso-CapsNet introduces a novel capsule-based approach for brain graph representation learning, capturing sub-graph existence, position, size, and orientation, leading to improved brain disease diagnosis accuracy.

Contribution

The paper proposes Iso-CapsNet, a capsule network that effectively models sub-graph properties in brain graphs, surpassing existing methods in representation learning.

Findings

Iso-CapsNet outperforms baseline methods on four brain graph datasets.

It captures sub-graph orientation, size, and position, enhancing representation quality.

Significant improvements in brain disease classification accuracy.

Abstract

Brain graph representation learning serves as the fundamental technique for brain diseases diagnosis. Great efforts from both the academic and industrial communities have been devoted to brain graph representation learning in recent years. The isomorphic neural network (IsoNN) introduced recently can automatically learn the existence of sub-graph patterns in brain graphs, which is also the state-of-the-art brain graph representation learning method by this context so far. However, IsoNN fails to capture the orientations of sub-graph patterns, which may render the learned representations to be useless for many cases. In this paper, we propose a new Iso-CapsNet (Isomorphic Capsule Net) model by introducing the graph isomorphic capsules for effective brain graph representation learning. Based on the capsule dynamic routing, besides the subgraph pattern existence confidence scores, Iso-CapsNet can also learn other sub-graph rich properties, including position, size and orientation, for calculating the class-wise digit capsules. We have compared Iso-CapsNet with both classic and state-of-the-art brain graph representation approaches with extensive experiments on four brain graph benchmark datasets. The experimental results also demonstrate the effectiveness of Iso-CapsNet, which can out-perform the baseline methods with significant improvements.