← Back to all news
arXiv Machine Learning By Sammuel R. Silva, Vander L. S. Freitas, Gladston Moreira, Eduardo J. S. Luz, Rodrigo Silva

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

Read the original on arXiv Machine Learning →

HCPN-GCN is a graph-aware extension of Hierarchical Prototype Networks that replaces linear feature extractors with Graph Convolutional Networks and introduces cone-based prototypes with a diversity regularization objective. This design yields richer graph-aware representations, reduces prototype proliferation, and maintains near-zero forgetting. Experiments on six continual graph learning benchmarks show consistent accuracy improvements over the original HPN and other baselines while using roughly 30× fewer atomic prototypes.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

Hugging Face Trending Papers
Aug 3

CoRe-GNN: Multilevel Message passing on Coarsened graphs

Training Graph Neural Networks on large graphs is challenged by the memory cost of storing all node representations across layers. We show that several existing scalable approaches can be written as structured modifications of the GNN propagation matrix, providing a unified perspective that exposes their respective limitations.

benchmarks
More like this →
arXiv Machine Learning
6d ago

HERO: Preserving Structure and Semantics in Heterogeneous Continual Graph Learning

HERO is a heterogeneous continual graph learning framework that preserves historical knowledge at both structural and semantic levels while adapting to new tasks. It uses DiSCo to select representative target nodes and reconstruct compact heterogeneous contexts, and applies multi-level knowledge distillation to align task-conditioned predictions with semantic responses. Experiments on four datasets with three HGNN backbones show HERO achieves best or tied-best average performance while maintaining competitive forgetting.

By Guiquan Sun, Xikun Zhang, Jingchao Ni, Dongjin Song
efficiencybenchmarks
More like this →