# DINE: Dimensional Interpretability of Node Embeddings

arXiv: https://arxiv.org/abs/2310.01162 · HTML: https://mlsanity.com/paper/2310.01162/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 90 references that are in the map.
- First posted on arXiv 2 Oct 2023.

## Builds on (most cited first, 30 of 35)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [Representation Learning on Graphs: Methods and Applications](https://mlsanity.com/paper/1709.05584/) (2017)
- [Explainability in Graph Neural Networks: A Taxonomic Survey](https://mlsanity.com/paper/2012.15445/) (2020)
- [Towards a Definition of Disentangled Representations](https://mlsanity.com/paper/1812.02230/) (2018)
- [Techniques for Interpretable Machine Learning](https://mlsanity.com/paper/1808.00033/) (2018)
- [Understanding Neural Networks through Representation Erasure](https://mlsanity.com/paper/1612.08220/) (2016)
- [PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks](https://mlsanity.com/paper/2010.05788/) (2020)
- [Explaining individual predictions when features are dependent: More accurate approximations to Shapley values](https://mlsanity.com/paper/1903.10464/) (2019)
- [Graph Clustering with Graph Neural Networks](https://mlsanity.com/paper/2006.16904/) (2020)
- [Principles and Practice of Explainable Machine Learning](https://mlsanity.com/paper/2009.11698/) (2020)
- [GEMSEC: Graph Embedding with Self Clustering](https://mlsanity.com/paper/1802.03997/) (2018)
- [SPINE: SParse Interpretable Neural Embeddings](https://mlsanity.com/paper/1711.08792/) (2017)
- [Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations](https://mlsanity.com/paper/1906.05017/) (2019)
- [Sparse Overcomplete Word Vector Representations](https://mlsanity.com/paper/1506.02004/) (2015)
- [The ground truth about metadata and community detection in networks](https://mlsanity.com/paper/1608.05878/) (2016)
- [Interaction Embeddings for Prediction and Explanation in Knowledge Graphs](https://mlsanity.com/paper/1903.04750/) (2019)
- [Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networks](https://mlsanity.com/paper/2105.08621/) (2021)
- [PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Prediction](https://mlsanity.com/paper/2302.12465/) (2023)
- [Modularity-Aware Graph Autoencoders for Joint Community Detection and Link Prediction](https://mlsanity.com/paper/2202.00961/) (2022)
- [Semantic Structure and Interpretability of Word Embeddings](https://mlsanity.com/paper/1711.00331/) (2017)
- [Can a Fruit Fly Learn Word Embeddings?](https://mlsanity.com/paper/2101.06887/) (2021)
- [Community detection in networks: Structural communities versus ground truth](https://mlsanity.com/paper/1406.0146/) (2014)
- [ExplaiNE: An Approach for Explaining Network Embedding-based Link Predictions](https://mlsanity.com/paper/1904.12694/) (2019)
- [Enhancing Decision Tree based Interpretation of Deep Neural Networks through L1-Orthogonal Regularization](https://mlsanity.com/paper/1904.05394/) (2019)
- [Finding Interpretable Concept Spaces in Node Embeddings using Knowledge Bases](https://mlsanity.com/paper/1910.05030/) (2019)

## Built on by (most cited first, 8 of 8)

- [Model Selection with Model Zoo via Graph Learning](https://mlsanity.com/paper/2404.03988/) (2024)
- [MoE-Enhanced Explainable Deep Manifold Transformation for Complex Data Embedding and Visualization](https://mlsanity.com/paper/2410.19504/) (2024)
- [Disentangled and Self-Explainable Node Representation Learning](https://mlsanity.com/paper/2410.21043/) (2024)
- [Explainable by-design Audio Segmentation through Non-Negative Matrix Factorization and Probing](https://mlsanity.com/paper/2406.13385/) (2024)
- [Sparse deepfake detection promotes better disentanglement](https://mlsanity.com/paper/2510.05696/) (2025)
- [TACENR: Task-Agnostic Contrastive Explanations for Node Representations](https://mlsanity.com/paper/2604.19372/) (2026)
- [Effective Graph and Rank-based Contextual Embeddings for Textual and Multimedia Data](https://mlsanity.com/paper/2608.29001/) (2026)
- [Context-Aware Interpretable Representations for Retrieval and Graph Convolutional Network Classification](https://mlsanity.com/paper/2608.29004/) (2026)

## Abstract (arXiv)

Graphs are ubiquitous due to their flexibility in representing social and technological systems as networks of interacting elements. Graph representation learning methods, such as node embeddings, are powerful approaches to map nodes into a latent vector space, allowing their use for various graph tasks. Despite their success, only few studies have focused on explaining node embeddings locally. Moreover, global explanations of node embeddings remain unexplored, limiting interpretability and debugging potentials. We address this gap by developing human-understandable explanations for dimensions in node embeddings. Towards that, we first develop new metrics that measure the global interpretability of embedding vectors based on the marginal contribution of the embedding dimensions to predicting graph structure. We say that an embedding dimension is more interpretable if it can faithfully map to an understandable sub-structure in the input graph - like community structure. Having observed that standard node embeddings have low interpretability, we then introduce DINE (Dimension-based Interpretable Node Embedding), a novel approach that can retrofit existing node embeddings by making them more interpretable without sacrificing their task performance. We conduct extensive experiments on synthetic and real-world graphs and show that we can simultaneously learn highly interpretable node embeddings with effective performance in link prediction.