Chameleon (48%/32%/20% fixed splits)

아카이브 평가 29건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
ScaleNet	1:1 Accuracy 80.1±1.5	Scale Invariance of Graph Neural Networks 2024-11-28	코드 1
Dir-GNN	1:1 Accuracy 79.71±1.26	Edge Directionality Improves Learning on Heterophilic Graphs 2023-05-17	코드 1
GESN	1:1 Accuracy 77.05 ± 1.24	Addressing Heterophily in Node Classification with Graph Echo State Networks 2023-05-14	코드 1
ACMII-GCN++	1:1 Accuracy 74.76 ± 2.2	Revisiting Heterophily For Graph Neural Networks 2022-10-14	코드 1
ACMII-GCN+	1:1 Accuracy 74.56 ± 2.08	Revisiting Heterophily For Graph Neural Networks 2022-10-14	코드 1
ACM-GCN+	1:1 Accuracy 74.47 ± 1.84	Revisiting Heterophily For Graph Neural Networks 2022-10-14	코드 1
ACM-GCN++	1:1 Accuracy 74.41 ± 1.49	Revisiting Heterophily For Graph Neural Networks 2022-10-14	코드 1
GloGNN++	1:1 Accuracy 71.21 ± 1.84	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily 2022-05-15	코드 1
GGCN	1:1 Accuracy 71.14 ±1.84	Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks 2021-02-12	코드 1
Deformable GCN	1:1 Accuracy 70.90 ±1.12	Deformable Graph Convolutional Networks 2021-12-29	코드 1
NLGCN	1:1 Accuracy 70.1 ± 2.9	Non-Local Graph Neural Networks 2020-05-29	코드 1
GloGNN	1:1 Accuracy 69.78 ± 2.42	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily 2022-05-15	코드 1
ACM-GCN	1:1 Accuracy 69.14 ± 1.91	Revisiting Heterophily For Graph Neural Networks 2022-10-14	코드 1
Diag-NSD	1:1 Accuracy 68.68 ± 1.73	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs 2022-02-09	코드 1
ACMII-GCN	1:1 Accuracy 68.46 ± 1.7	Revisiting Heterophily For Graph Neural Networks 2022-10-14	코드 1
LINKX	1:1 Accuracy 68.42 ± 1.38	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods 2021-10-27	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
O(d)-NSD	1:1 Accuracy 68.04 ± 1.58	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs 2022-02-09	코드 1
Gen-NSD	1:1 Accuracy 67.93 ± 1.58	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs 2022-02-09	코드 1
NLGAT	1:1 Accuracy 65.7 ± 1.4	Non-Local Graph Neural Networks 2020-05-29	코드 1
WRGAT	1:1 Accuracy 65.24 ± 0.87	Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns 2021-06-11	코드 1
ACM-SGC-1	1:1 Accuracy 63.99 ± 1.66	Revisiting Heterophily For Graph Neural Networks 2022-10-14	코드 1
GCNII	1:1 Accuracy 63.86 ± 3.04	Simple and Deep Graph Convolutional Networks 2020-07-04	코드 1 · 코드 2 · 코드 3 · 코드 4
GPRGCN	1:1 Accuracy 62.59 ± 2.04	Adaptive Universal Generalized PageRank Graph Neural Network 2020-06-14	코드 1
MixHop	1:1 Accuracy 60.50 ± 2.53	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing 2019-04-30	코드 1 · 코드 2 · 코드 3
H2GCN	1:1 Accuracy 60.11 ± 2.15	Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs 2020-06-20	코드 1 · 코드 2 · 코드 3 · 코드 4
Geom-GCN	1:1 Accuracy 60.00 ± 2.81	Geom-GCN: Geometric Graph Convolutional Networks 2020-02-13	코드 1 · 코드 2 · 코드 3 · 코드 4
ACM-SGC-2	1:1 Accuracy 59.21 ± 2.22	Revisiting Heterophily For Graph Neural Networks 2022-10-14	코드 1
NLMLP	1:1 Accuracy 50.7 ± 2.2	Non-Local Graph Neural Networks 2020-05-29	코드 1
FAGCN	1:1 Accuracy 46.07 ± 2.11	Beyond Low-frequency Information in Graph Convolutional Networks 2021-01-04	코드 1