# RIM: Reliable Influence-based Active Learning on Graphs

arXiv: https://arxiv.org/abs/2110.14854 · HTML: https://mlsanity.com/paper/2110.14854/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 59 references that are in the map.
- First posted on arXiv 28 Oct 2021.

## Builds on (most cited first, 19 of 19)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Representation Learning on Graphs with Jumping Knowledge Networks](https://mlsanity.com/paper/1806.03536/) (2018)
- [GraphSAINT: Graph Sampling Based Inductive Learning Method](https://mlsanity.com/paper/1907.04931/) (2019)
- [Graph Neural Networks in Recommender Systems: A Survey](https://mlsanity.com/paper/2011.02260/) (2020)
- [Deep Learning on Graphs: A Survey](https://mlsanity.com/paper/1812.04202/) (2018)
- [A Survey of Label-noise Representation Learning: Past, Present and Future](https://mlsanity.com/paper/2011.04406/) (2020)
- [Unifying Graph Convolutional Neural Networks and Label Propagation](https://mlsanity.com/paper/2002.06755/) (2020)
- [Active Learning for Graph Embedding](https://mlsanity.com/paper/1705.05085/) (2017)
- [Graph Policy Network for Transferable Active Learning on Graphs](https://mlsanity.com/paper/2006.13463/) (2020)
- [On the Equivalence of Decoupled Graph Convolution Network and Label Propagation](https://mlsanity.com/paper/2010.12408/) (2020)
- [OpenBox: A Generalized Black-box Optimization Service](https://mlsanity.com/paper/2106.00421/) (2021)
- [Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization](https://mlsanity.com/paper/2108.00219/) (2021)
- [Active Learning from Weak and Strong Labelers](https://mlsanity.com/paper/1510.02847/) (2015)
- [S2: An Efficient Graph Based Active Learning Algorithm with Application to Nonparametric Classification](https://mlsanity.com/paper/1506.08760/) (2015)
- [Exploiting Context for Robustness to Label Noise in Active Learning](https://mlsanity.com/paper/2010.09066/) (2020)

## Built on by (most cited first, 23 of 23)

- [Training Data Influence Analysis and Estimation: A Survey](https://mlsanity.com/paper/2212.04612/) (2022)
- [Label-free Node Classification on Graphs with Large Language Models (LLMS)](https://mlsanity.com/paper/2310.04668/) (2023)
- [Information Gain Propagation: a new way to Graph Active Learning with Soft Labels](https://mlsanity.com/paper/2203.01093/) (2022)
- [Towards Data-centric Graph Machine Learning: Review and Outlook](https://mlsanity.com/paper/2309.10979/) (2023)
- [Semantic-aware Node Synthesis for Imbalanced Heterogeneous Information Networks](https://mlsanity.com/paper/2302.14061/) (2023)
- [Model Generalization on Text Attribute Graphs: Principles with Large Language Models](https://mlsanity.com/paper/2502.11836/) (2025)
- [Leveraging Large Language Models for Effective Label-free Node Classification in Text-Attributed Graphs](https://mlsanity.com/paper/2412.11983/) (2024)
- [GNN-as-Judge: Unleashing the Power of LLMs for Graph Learning with GNN Feedback](https://mlsanity.com/paper/2604.08553/) (2026)
- [Generative Flow Networks for Precise Reward-Oriented Active Learning on Graphs](https://mlsanity.com/paper/2304.11989/) (2023)
- [Mitigating Semantic Confusion from Hostile Neighborhood for Graph Active Learning](https://mlsanity.com/paper/2308.08823/) (2023)
- [Robust Offline Active Learning on Graphs](https://mlsanity.com/paper/2408.07941/) (2024)
- [Toward Scalable Graph Unlearning: A Node Influence Maximization based Approach](https://mlsanity.com/paper/2501.11823/) (2025)
- [Language Models as Messengers: Enhancing Message Passing in Heterophilic Graph Learning](https://mlsanity.com/paper/2505.19762/) (2025)
- [Active Learning for Graphs with Noisy Structures](https://mlsanity.com/paper/2402.02321/) (2024)
- [Shapley-Guided Utility Learning for Effective Graph Inference Data Valuation](https://mlsanity.com/paper/2503.18195/) (2025)
- [InfGraND: An Influence-Guided GNN-to-MLP Knowledge Distillation](https://mlsanity.com/paper/2601.08033/) (2026)
- [K-Core Decomposition on Super Large Graphs with Limited Resources](https://mlsanity.com/paper/2112.14840/) (2021)
- [Perturbation-based Graph Active Learning for Weakly-Supervised Belief Representation Learning](https://mlsanity.com/paper/2410.19176/) (2024)
- [Efficient Data Selection for Training Genomic Perturbation Models](https://mlsanity.com/paper/2503.14571/) (2025)
- [HIAL: A New Paradigm for Hypergraph Active Learning via Influence Maximization](https://mlsanity.com/paper/2507.20490/) (2025)
- [RANA: Robust Active Learning for Noisy Network Alignment](https://mlsanity.com/paper/2507.22434/) (2025)
- [Where LLM Annotators Fail: Label-Free Learning on Graphs with LLMs](https://mlsanity.com/paper/2605.27913/) (2026)
- [Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching](https://mlsanity.com/paper/2606.11583/) (2026)

## Abstract (arXiv)

Message passing is the core of most graph models such as Graph Convolutional Network (GCN) and Label Propagation (LP), which usually require a large number of clean labeled data to smooth out the neighborhood over the graph. However, the labeling process can be tedious, costly, and error-prone in practice. In this paper, we propose to unify active learning (AL) and message passing towards minimizing labeling costs, e.g., making use of few and unreliable labels that can be obtained cheaply. We make two contributions towards that end. First, we open up a perspective by drawing a connection between AL enforcing message passing and social influence maximization, ensuring that the selected samples effectively improve the model performance. Second, we propose an extension to the influence model that incorporates an explicit quality factor to model label noise. In this way, we derive a fundamentally new AL selection criterion for GCN and LP--reliable influence maximization (RIM)--by considering quantity and quality of influence simultaneously. Empirical studies on public datasets show that RIM significantly outperforms current AL methods in terms of accuracy and efficiency.