Papers with Code · CC BY-SA 4.0

Chameleon

아카이브 평가 61건 · 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
DJ-GNN	Accuracy 80.48±1.46	Diffusion-Jump GNNs: Homophiliation via Learnable Metric Filters 2023-06-29	코드 1
FaberNet	Accuracy 80.33±1.19	HoloNets: Spectral Convolutions do extend to Directed Graphs 2023-10-03	코드 1
Dir-GNN	Accuracy 79.71±1.26	Edge Directionality Improves Learning on Heterophilic Graphs 2023-05-17	코드 1
CoED	Accuracy 79.69±1.35	Improving Graph Neural Networks by Learning Continuous Edge Directions 2024-10-18	코드 1
FSGNN (8-hop)	Accuracy 78.27±1.28	Improving Graph Neural Networks with Simple Architecture Design 2021-05-17	코드 1
FSGNN (3-hop)	Accuracy 78.14±1.25	Improving Graph Neural Networks with Simple Architecture Design 2021-05-17	코드 1
HLP Concat	Accuracy 77.48±0.80	Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs 2021-06-24	연결 없음
Graph ESN	Accuracy 76.2±1.2	Beyond Homophily with Graph Echo State Networks 2022-10-27	연결 없음
SADE-GCN	Accuracy 75.57±1.57	Self-attention Dual Embedding for Graphs with Heterophily 2023-05-28	연결 없음
M2M-GNN	Accuracy 75.20 ± 2.3	Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs 2024-05-31	코드 1
RDGNN-I	Accuracy 74.79 ± 2.14	Graph Neural Reaction Diffusion Models 2024-06-16	연결 없음
ACMII-GCN++	Accuracy 74.76 ± 2.2	Revisiting Heterophily For Graph Neural Networks 2022-10-14	코드 1
GCNII+DHGR	Accuracy 74.57±2.56	Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approach 2022-09-17	연결 없음
ACMII-GCN+	Accuracy 74.56 ± 2.08	Revisiting Heterophily For Graph Neural Networks 2022-10-14	코드 1
UDGNN (GCN)	Accuracy 74.53±1.19	Universal Deep GNNs: Rethinking Residual Connection in GNNs from a Path Decomposition Perspective for Preventing the Over-smoothing 2022-05-30	연결 없음
ACM-GCN+	Accuracy 74.47 ± 1.84	Revisiting Heterophily For Graph Neural Networks 2022-10-14	코드 1
ACM-GCN++	Accuracy 74.41 ± 1.49	Revisiting Heterophily For Graph Neural Networks 2022-10-14	코드 1
LW-GCN	Accuracy 74.4±1.4	Label-Wise Graph Convolutional Network for Heterophilic Graphs 2021-10-15	코드 1
SignGT	Accuracy 74.31±1.24	SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning 2023-10-17	연결 없음
CNMPGNN	Accuracy 73.29±1.29	CN-Motifs Perceptive Graph Neural Networks 2021-11-15	연결 없음
LHS	Accuracy 72.31±1.6	Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks 2023-12-27	연결 없음
Ordered GNN	Accuracy 72.28±2.29	Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing 2023-02-03	코드 1
IIE-GNN	Accuracy 72.13±2.11	Enhancing Intra-class Information Extraction for Heterophilous Graphs: One Neural Architecture Search Approach 2022-11-20	연결 없음
GCNH	Accuracy 71.56±1.86	GCNH: A Simple Method For Representation Learning On Heterophilous Graphs 2023-04-21	코드 1
GloGNN++	Accuracy 71.21±1.84	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily 2022-05-15	코드 1
GGCN	Accuracy 71.14 ± 1.84	Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks 2021-02-12	코드 1
TE-GCNN	Accuracy 71.14 ± 1.84	Transfer Entropy in Graph Convolutional Neural Networks 2024-06-08	코드 1
JKNet + Hetero-S (8 layers)	Accuracy 70.18	The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs 2024-06-18	코드 1
NLGCN	Accuracy 70.1 ± 2.9	Non-Local Graph Neural Networks 2020-05-29	코드 1
CATv3-sup	Accuracy 69.9±1.0	CAT: A Causally Graph Attention Network for Trimming Heterophilic Graph 2023-12-14	코드 1