# Ftextsuperscript2LP-AP: Fast & Flexible Label Propagation with Adaptive Propagation Kernel

arXiv: https://arxiv.org/abs/2604.20736 · HTML: https://mlsanity.com/paper/2604.20736/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 40 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Builds on (most cited first, 30 of 30)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Adaptive Universal Generalized PageRank Graph Neural Network](https://mlsanity.com/paper/2006.07988/) (2020)
- [Towards Deeper Graph Neural Networks](https://mlsanity.com/paper/2007.09296/) (2020)
- [Combining Label Propagation and Simple Models Out-performs Graph Neural Networks](https://mlsanity.com/paper/2010.13993/) (2020)
- [BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation](https://mlsanity.com/paper/2106.10994/) (2021)
- [Deep Multimodal Fusion by Channel Exchanging](https://mlsanity.com/paper/2011.05005/) (2020)
- [Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification](https://mlsanity.com/paper/2406.08993/) (2024)
- [Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond](https://mlsanity.com/paper/2209.06177/) (2022)
- [Progressive Graph Learning for Open-Set Domain Adaptation](https://mlsanity.com/paper/2006.12087/) (2020)
- [GraphFM: Improving Large-Scale GNN Training via Feature Momentum](https://mlsanity.com/paper/2206.07161/) (2022)
- [OpenGSL: A Comprehensive Benchmark for Graph Structure Learning](https://mlsanity.com/paper/2306.10280/) (2023)
- [Resurrecting Label Propagation for Graphs with Heterophily and Label Noise](https://mlsanity.com/paper/2310.16560/) (2023)
- [Towards Dynamic Message Passing on Graphs](https://mlsanity.com/paper/2410.23686/) (2024)
- [DPAR: Decoupled Graph Neural Networks with Node-Level Differential Privacy](https://mlsanity.com/paper/2210.04442/) (2022)
- [FreeGAD: A Training-Free yet Effective Approach for Graph Anomaly Detection](https://mlsanity.com/paper/2508.10594/) (2025)
- [What Is Missing In Homophily? Disentangling Graph Homophily For Graph Neural Networks](https://mlsanity.com/paper/2406.18854/) (2024)
- [Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention](https://mlsanity.com/paper/2410.06746/) (2024)
- [Training-free Graph Neural Networks and the Power of Labels as Features](https://mlsanity.com/paper/2404.19288/) (2024)
- [Revealing the Pitfalls and Re-Evaluating the Advancement of Heterophilic Graph Learning](https://mlsanity.com/paper/2409.05755/) (2024)
- [Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification](https://mlsanity.com/paper/2412.08193/) (2024)
- [Mind the Gap Between Prototypes and Images in Cross-domain Finetuning](https://mlsanity.com/paper/2410.12474/) (2024)
- [ADMP-GNN: Adaptive Depth Message Passing GNN](https://mlsanity.com/paper/2509.01170/) (2025)
- [HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations](https://mlsanity.com/paper/2510.10864/) (2025)
- [Re-understanding Graph Unlearning through Memorization](https://mlsanity.com/paper/2601.14694/) (2026)

## Abstract (arXiv)

Semi-supervised node classification is a foundational task in graph machine learning, yet state-of-the-art Graph Neural Networks (GNNs) are hindered by significant computational overhead and reliance on strong homophily assumptions. Traditional GNNs require expensive iterative training and multi-layer message passing, while existing training-free methods, such as Label Propagation, lack adaptability to heterophilo-us graph structures. This paper presents F2LP-AP (Fast and Flexible Label Propagation with Adaptive Propagation Kernel), a training-free, computationally efficient framework that adapts to local graph topology. Our method constructs robust class prototypes via the geometric median and dynamically adjusts propagation parameters based on the Local Clustering Coefficient (LCC), enabling effective modeling of both homophilous and heterophilous graphs without gradient-based training. Extensive experiments across diverse benchmark datasets demonstrate that F2LP-AP achieves competitive or superior accuracy compared to trained GNNs, while significantly outperforming existing baselines in computational efficiency.