# HCPN-GCN: Scaling Hierarchical Prototype Networks with Cone Geometry for Continual Graph Learning

arXiv: https://arxiv.org/abs/2610.08823 · HTML: https://mlsanity.com/paper/2610.08823/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 17 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 12 of 12)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Overcoming Catastrophic Forgetting in Graph Neural Networks](https://mlsanity.com/paper/2012.06002/) (2020)
- [Streaming Graph Neural Networks via Continual Learning](https://mlsanity.com/paper/2009.10951/) (2020)
- [CaT: Balanced Continual Graph Learning with Graph Condensation](https://mlsanity.com/paper/2309.09455/) (2023)
- [Continual Learning on Dynamic Graphs via Parameter Isolation](https://mlsanity.com/paper/2305.13825/) (2023)
- [Continual Learning on Graphs: Challenges, Solutions, and Opportunities](https://mlsanity.com/paper/2402.11565/) (2024)
- [Forget Forgetting: Continual Learning in a World of Abundant Memory](https://mlsanity.com/paper/2502.07274/) (2025)
- [On the Cross-type Homophily of Heterogeneous Graphs: Understanding and Unleashing](https://mlsanity.com/paper/2501.14600/) (2025)

## Abstract (arXiv)

Continual Graph Learning (CGL) aims to incrementally learn from graph-structured data while preserving knowledge acquired from previous tasks. A major challenge in this setting is catastrophic forgetting, where learning new tasks degrades performance on previously learned ones. Hierarchical Prototype Networks (HPNs) address this problem through a prototype-based memory mechanism that avoids storing historical data, but their reliance on linear feature extractors limits their ability to exploit graph topology, while point-based prototypes often lead to inefficient prototype growth on structurally diverse graphs. In this work, we propose HCPN-GCN, a graph-aware extension of HPN that replaces the original linear feature extractors with Graph Convolutional Networks (GCNs) and introduces cone-based prototypes with a diversity regularization objective. The proposed design produces richer graph-aware representations while compactly modeling the embedding space, reducing prototype proliferation without sacrificing discriminability. Experimental results on six continual graph learning benchmarks demonstrate that HCPN-GCN consistently improves average classification accuracy over the original HPN and representative continual learning baselines while maintaining near-zero forgetting. Furthermore, our analysis shows that the proposed model learns substantially richer class-level prototype hierarchies using approximately 30× fewer atomic prototypes than the original HPN, providing a more compact and effective memory representation for continual graph learning.