# Draw a Portrait of Your Graph Data: An Instance-Level Profiling Framework for Graph-Structured Data

arXiv: https://arxiv.org/abs/2509.12094 · HTML: https://mlsanity.com/paper/2509.12094/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 15 Sep 2025.

## Builds on (most cited first, 11 of 11)

- [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)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [SSD: A Unified Framework for Self-Supervised Outlier Detection](https://mlsanity.com/paper/2103.12051/) (2021)
- [The Principles of Data-Centric AI (DCAI)](https://mlsanity.com/paper/2211.14611/) (2022)
- [Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data](https://mlsanity.com/paper/2210.13043/) (2022)
- [Data-centric Graph Learning: A Survey](https://mlsanity.com/paper/2310.04987/) (2023)
- [Private Graph Extraction via Feature Explanations](https://mlsanity.com/paper/2206.14724/) (2022)
- [Dissecting Sample Hardness: A Fine-Grained Analysis of Hardness Characterization Methods for Data-Centric AI](https://mlsanity.com/paper/2403.04551/) (2024)
- [Towards Data-centric Machine Learning on Directed Graphs: a Survey](https://mlsanity.com/paper/2412.01849/) (2024)

## Abstract (arXiv)

Graph machine learning models often achieve similar overall performance yet behave differently at the node level, failing on different subsets of nodes with varying reliability. Standard evaluation metrics such as accuracy obscure these fine grained differences, making it difficult to diagnose when and where models fail. We introduce NodePro, a node profiling framework that enables fine-grained diagnosis of model behavior by assigning interpretable profile scores to individual nodes. These scores combine data-centric signals, such as feature dissimilarity, label uncertainty, and structural ambiguity, with model-centric measures of prediction confidence and consistency during training. By aligning model behavior with these profiles, NodePro reveals systematic differences between models, even when aggregate metrics are indistinguishable. We show that node profiles generalize to unseen nodes, supporting prediction reliability without ground-truth labels. Finally, we demonstrate the utility of NodePro in identifying semantically inconsistent or corrupted nodes in a structured knowledge graph, illustrating its effectiveness in real-world settings.