Topology Adaptive Graph Convolutional Networks
read the original abstract
Spectral graph convolutional neural networks (CNNs) require approximation to the convolution to alleviate the computational complexity, resulting in performance loss. This paper proposes the topology adaptive graph convolutional network (TAGCN), a novel graph convolutional network defined in the vertex domain. We provide a systematic way to design a set of fixed-size learnable filters to perform convolutions on graphs. The topologies of these filters are adaptive to the topology of the graph when they scan the graph to perform convolution. The TAGCN not only inherits the properties of convolutions in CNN for grid-structured data, but it is also consistent with convolution as defined in graph signal processing. Since no approximation to the convolution is needed, TAGCN exhibits better performance than existing spectral CNNs on a number of data sets and is also computationally simpler than other recent methods.
This paper has not been read by Pith yet.
Forward citations
Cited by 7 Pith papers
-
Collapsed Effective Operators for Higher-order Structures
Collapsed Effective Operators use Schur complement on graded Laplacians to create vertex-level operators that encode higher-order topology, preserve PSD, and improve spectral clustering and smoothing.
-
Learning Dynamic Stability Landscapes in Synchronization Networks
Introduces graph-to-image prediction of per-node dynamic stability landscapes in oscillator networks from topology, releases two 10k-graph datasets, and shows GNN-CNN models achieve good accuracy with cross-size gener...
-
Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation
GaRA generates task-specific LoRA weight updates conditioned on graph structures to enable better whole-graph encoding in LLMs for zero-shot graph learning.
-
PF$\Delta$: A Benchmark Dataset for Power Flow under Load, Generation, and Topology Variations
PFΔ is a benchmark dataset of 859,800 power flow solutions across six bus system sizes with N/N-1/N-2 contingencies and close-to-infeasible cases to evaluate traditional solvers and GNN methods.
-
scKDGM: KAN-guided Dynamic Graph Masked Learning for Single-Cell RNA-seq Clustering
scKDGM proposes a KAN-guided dynamic graph masked learning framework with GDP-Mask, TAKGCN encoder, mask-guided recovery, cross-view contrastive learning and ZINB loss that outperforms 10 baselines on 12 scRNA-seq dat...
-
A Triple-Modal Contrastive Learning Framework with Sequence, Graph, and 3D Features for Drug-Target Interaction Prediction
TriMod-DTI uses contrastive learning across 1D sequences, 2D graphs, and 3D structures to outperform prior DTI methods on three benchmarks.
-
Confident Learning-based Network for Detecting Bug-Inducing Commits on SZZ with Noisy Labels
BIC-Hunter combines confident learning for label denoising and GCNs on homogeneous graphs to identify bug-inducing commits, reporting gains of 6.16-7.13% on Recall@K and 8.43-32.82% on MFR over prior methods.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.