Node Classification On Texas

المقاييس

Accuracy

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	Accuracy	Paper Title	Repository
2-HiGCN	92.45±0.73	Higher-order Graph Convolutional Network with Flower-Petals Laplacians on Simplicial Complexes	-
HLP Concat	87.57 ± 5.44	Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs	-
MGNN + Hetero-S (8 layers)	93.09	The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs	-
Diag-NSD	85.67 ± 6.95	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs	-
GGCN	84.86 ± 4.55	Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks	-
MixHop	77.84 ± 7.73	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing	-
ACM-GCN+	88.38 ± 3.64	Revisiting Heterophily For Graph Neural Networks	-
UniG-Encoder	85.40±5.3	UniG-Encoder: A Universal Feature Encoder for Graph and Hypergraph Node Classification	-
ACM-SGC-2	81.89 ± 4.53	Revisiting Heterophily For Graph Neural Networks	-
SADE-GCN	86.49±5.12	Self-attention Dual Embedding for Graphs with Heterophily	-
Geom-GCN-S	59.73	Geom-GCN: Geometric Graph Convolutional Networks	-
GloGNN++	84.05±4.90	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily	-
Gen-NSD	82.97 ± 5.13	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs	-
LINKX+CausalMP	57.36±0.60	Heterophilic Graph Neural Networks Optimization with Causal Message-passing	-
IIE-GNN	85.84±4.23	Enhancing Intra-class Information Extraction for Heterophilous Graphs: One Neural Architecture Search Approach	-
M2M-GNN	89.19 ± 4.5	Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs	-
DeltaGNN constant	74.05±3.08	DeltaGNN: Graph Neural Network with Information Flow Control	-
LINKX	74.60 ± 8.37	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods	-
NLMLP	85.4 ± 3.8	Non-Local Graph Neural Networks	-
FSGNN	87.30 ± 5.55	Improving Graph Neural Networks with Simple Architecture Design	-

0 of 62 row(s) selected.