# CIMAGE: Exploiting the Conditional Independence in Masked Graph Auto-encoders

arXiv: https://arxiv.org/abs/2503.07852 · HTML: https://mlsanity.com/paper/2503.07852/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 61 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Builds on (most cited first, 30 of 32)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (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)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [Contrastive Multi-View Representation Learning on Graphs](https://mlsanity.com/paper/2006.05582/) (2020)
- [Deep Graph Contrastive Representation Learning](https://mlsanity.com/paper/2006.04131/) (2020)
- [InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization](https://mlsanity.com/paper/1908.01000/) (2019)
- [Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks](https://mlsanity.com/paper/2007.02901/) (2020)
- [Predicting What You Already Know Helps: Provable Self-Supervised Learning](https://mlsanity.com/paper/2008.01064/) (2020)
- [Contrastive learning, multi-view redundancy, and linear models](https://mlsanity.com/paper/2008.10150/) (2020)
- [From Canonical Correlation Analysis to Self-supervised Graph Neural Networks](https://mlsanity.com/paper/2106.12484/) (2021)
- [GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner](https://mlsanity.com/paper/2304.04779/) (2023)
- [Augmentation-Free Self-Supervised Learning on Graphs](https://mlsanity.com/paper/2112.02472/) (2021)
- [Inferring Networks of Substitutable and Complementary Products](https://mlsanity.com/paper/1506.08839/) (2015)
- [Adversarially Regularized Graph Autoencoder for Graph Embedding](https://mlsanity.com/paper/1802.04407/) (2018)
- [What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoders](https://mlsanity.com/paper/2205.10053/) (2022)
- [Cluster-guided Contrastive Graph Clustering Network](https://mlsanity.com/paper/2301.01098/) (2023)
- [Dink-Net: Neural Clustering on Large Graphs](https://mlsanity.com/paper/2305.18405/) (2023)
- [Rethinking Graph Auto-Encoder Models for Attributed Graph Clustering](https://mlsanity.com/paper/2107.08562/) (2021)
- [vGraph: A Generative Model for Joint Community Detection and Node Representation Learning](https://mlsanity.com/paper/1906.07159/) (2019)
- [Decomposed Mutual Information Estimation for Contrastive Representation Learning](https://mlsanity.com/paper/2106.13401/) (2021)
- [SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking](https://mlsanity.com/paper/2301.12458/) (2023)
- [Rethinking Graph Masked Autoencoders through Alignment and Uniformity](https://mlsanity.com/paper/2402.07225/) (2024)
- [GiGaMAE: Generalizable Graph Masked Autoencoder via Collaborative Latent Space Reconstruction](https://mlsanity.com/paper/2308.09663/) (2023)
- [GATE: Graph CCA for Temporal SElf-supervised Learning for Label-efficient fMRI Analysis](https://mlsanity.com/paper/2203.09034/) (2022)
- [ConTextual Masked Auto-Encoder for Dense Passage Retrieval](https://mlsanity.com/paper/2208.07670/) (2022)
- [Masked Graph Autoencoder with Non-discrete Bandwidths](https://mlsanity.com/paper/2402.03814/) (2024)

## Built on by (most cited first, 4 of 4)

- [Curriculum Guided Personalized Subgraph Federated Learning](https://mlsanity.com/paper/2509.00402/) (2025)
- [Balancing Graph Embedding Smoothness in Self-Supervised Learning via Information-Theoretic Decomposition](https://mlsanity.com/paper/2504.12011/) (2025)
- [Federated Recommender System with Data Valuation for E-commerce Platform](https://mlsanity.com/paper/2509.11196/) (2025)
- [Enhancing Contrastive Link Prediction With Edge Balancing Augmentation](https://mlsanity.com/paper/2508.14808/) (2025)

## Abstract (arXiv)

Recent Self-Supervised Learning (SSL) methods encapsulating relational information via masking in Graph Neural Networks (GNNs) have shown promising performance. However, most existing approaches rely on random masking strategies in either feature or graph space, which may fail to capture task-relevant information fully. We posit that this limitation stems from an inability to achieve minimum redundancy between masked and unmasked components while ensuring maximum relevance of both to potential downstream tasks. Conditional Independence (CI) inherently satisfies the minimum redundancy and maximum relevance criteria, but its application typically requires access to downstream labels. To address this challenge, we introduce CIMAGE, a novel approach that leverages Conditional Independence to guide an effective masking strategy within the latent space. CIMAGE utilizes CI-aware latent factor decomposition to generate two distinct contexts, leveraging high-confidence pseudo-labels derived from unsupervised graph clustering. In this framework, the pretext task involves reconstructing the masked second context solely from the information provided by the first context. Our theoretical analysis further supports the superiority of CIMAGE's novel CI-aware masking method by demonstrating that the learned embedding exhibits approximate linear separability, which enables accurate predictions for the downstream task. Comprehensive evaluations across diverse graph benchmarks illustrate the advantage of CIMAGE, with notably higher average rankings on node classification and link prediction tasks. Notably, our proposed model highlights the under-explored potential of CI in enhancing graph SSL methodologies and offers enriched insights for effective graph representation learning.