Papers with Code · CC BY-SA 4.0

Squirrel

아카이브 평가 59건 · 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
FaberNet	Accuracy 76.71±1.92	HoloNets: Spectral Convolutions do extend to Directed Graphs 2023-10-03	코드 1
CoED	Accuracy 75.32±1.82	Improving Graph Neural Networks by Learning Continuous Edge Directions 2024-10-18	코드 1
Dir-GNN	Accuracy 75.31±1.92	Edge Directionality Improves Learning on Heterophilic Graphs 2023-05-17	코드 1
HLP Concat	Accuracy 74.17±1.83	Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs 2021-06-24	연결 없음
FSGNN (8-hop)	Accuracy 74.10±1.89	Improving Graph Neural Networks with Simple Architecture Design 2021-05-17	코드 1
DJ-GNN	Accuracy 73.48±1.59	Diffusion-Jump GNNs: Homophiliation via Learnable Metric Filters 2023-06-29	코드 1
H2GCN+DHGR	Accuracy 72.24±1.52	Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approach 2022-09-17	연결 없음
Graph ESN	Accuracy 71.2±1.5	Beyond Homophily with Graph Echo State Networks 2022-10-27	연결 없음
SADE-GCN	Accuracy 68.20±1.57	Self-attention Dual Embedding for Graphs with Heterophily 2023-05-28	연결 없음
UDGNN (GCN)	Accuracy 68.13±2.59	Universal Deep GNNs: Rethinking Residual Connection in GNNs from a Path Decomposition Perspective for Preventing the Over-smoothing 2022-05-30	연결 없음
ACMII-GCN++	Accuracy 67.4 ± 2.21	Revisiting Heterophily For Graph Neural Networks 2022-10-14	코드 1
ACMII-GCN+	Accuracy 67.07 ± 1.65	Revisiting Heterophily For Graph Neural Networks 2022-10-14	코드 1
ACM-GCN++	Accuracy 67.06 ± 1.66	Revisiting Heterophily For Graph Neural Networks 2022-10-14	코드 1
ACM-GCN+	Accuracy 66.98 ± 1.71	Revisiting Heterophily For Graph Neural Networks 2022-10-14	코드 1
UGT	Accuracy 66.96 ±2.49	Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity 2023-08-18	코드 1 · 코드 2 · 코드 3
RDGNN-I	Accuracy 65.62 ± 2.33	Graph Neural Reaction Diffusion Models 2024-06-16	연결 없음
SignGT	Accuracy 64.25±1.48	SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning 2023-10-17	연결 없음
CNMPGNN	Accuracy 63.60±1.96	CN-Motifs Perceptive Graph Neural Networks 2021-11-15	연결 없음
M2M-GNN	Accuracy 63.60 ± 1.7	Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs 2024-05-31	코드 1
LW-GCN	Accuracy 62.6±1.6	Label-Wise Graph Convolutional Network for Heterophilic Graphs 2021-10-15	코드 1
Ordered GNN	Accuracy 62.44±1.96	Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing 2023-02-03	코드 1
HDP	Accuracy 62.07 ± 1.57	Heterophilous Distribution Propagation for Graph Neural Networks 2024-05-31	연결 없음
GCNH	Accuracy 61.85±1.54	GCNH: A Simple Method For Representation Learning On Heterophilous Graphs 2023-04-21	코드 1
LINKX	Accuracy 61.81 ± 1.80	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
LHS	Accuracy 60.27±1.2	Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks 2023-12-27	연결 없음
CATv3-sup	Accuracy 59.3±1.8	CAT: A Causally Graph Attention Network for Trimming Heterophilic Graph 2023-12-14	코드 1
NLGCN	Accuracy 59.0 ± 1.2	Non-Local Graph Neural Networks 2020-05-29	코드 1
GloGNN++	Accuracy 57.88±1.76–	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily 2022-05-15	코드 1
JKNet + Hetero-S (8 layers)	Accuracy 57.83	The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs 2024-06-18	코드 1
GloGNN	Accuracy 57.54±1.39	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily 2022-05-15	코드 1