# NetworkNet: A Deep Neural Network Approach for Random Networks with Sparse Nodal Attributes and Complex Nodal Heterogeneity

arXiv: https://arxiv.org/abs/2604.11673 · HTML: https://mlsanity.com/paper/2604.11673/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 65 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 25 of 25)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [Nonparametric regression using deep neural networks with ReLU activation function](https://mlsanity.com/paper/1708.06633/) (2017)
- [Adversarial Attacks on Neural Networks for Graph Data](https://mlsanity.com/paper/1805.07984/) (2018)
- [Community Detection and Stochastic Block Models](https://mlsanity.com/paper/1703.10146/) (2017)
- [PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks](https://mlsanity.com/paper/2010.05788/) (2020)
- [Consistency of spectral clustering in stochastic block models](https://mlsanity.com/paper/1312.2050/) (2013)
- [LassoNet: A Neural Network with Feature Sparsity](https://mlsanity.com/paper/1907.12207/) (2019)
- [On the Complexity of SHAP-Score-Based Explanations: Tractability via Knowledge Compilation and Non-Approximability Results](https://mlsanity.com/paper/2104.08015/) (2021)
- [Uncertainty in Graph Neural Networks: A Survey](https://mlsanity.com/paper/2403.07185/) (2024)
- [Coauthorship and Citation Networks for Statisticians](https://mlsanity.com/paper/1410.2840/) (2014)
- [On Deep Instrumental Variables Estimate](https://mlsanity.com/paper/2004.14954/) (2020)
- [Co-citation and Co-authorship Networks of Statisticians](https://mlsanity.com/paper/2204.11194/) (2022)
- [Adjusted chi-square test for degree-corrected block models](https://mlsanity.com/paper/2012.15047/) (2020)
- [A Sparse Beta Regression Model for Network Analysis](https://mlsanity.com/paper/2010.13604/) (2020)
- [Quasi-uniform designs with optimal and near-optimal uniformity constant](https://mlsanity.com/paper/2112.10401/) (2021)
- [Exponential-Family Models of Random Graphs: Inference in Finite-, Super-, and Infinite Population Scenarios](https://mlsanity.com/paper/1707.04800/) (2017)
- [Parameter Estimation Procedures for Exponential-Family Random Graph Models on Count-Valued Networks: A Comparative Simulation Study](https://mlsanity.com/paper/2111.02372/) (2021)
- [High-order joint embedding for multi-level link prediction](https://mlsanity.com/paper/2111.05265/) (2021)
- [Co-factor analysis of citation networks](https://mlsanity.com/paper/2408.14604/) (2024)
- [Supervised centrality via sparse network influence regression: an application to the 2021 Henan floods' social network](https://mlsanity.com/paper/2412.18145/) (2024)
- [Regularization and Selection in A Directed Network Model with Nodal Homophily and Nodal Effects](https://mlsanity.com/paper/2504.04622/) (2025)
- [FLAT: Fused Lasso Regression with Adaptive Minimum Spanning Tree with Applications on Thermohaline Circulation](https://mlsanity.com/paper/2507.09800/) (2025)

## Abstract (arXiv)

Heterogeneous network data with rich nodal information become increasingly prevalent across multidisciplinary research, yet accurately modeling complex nodal heterogeneity and simultaneously selecting influential nodal attributes remains an open challenge. This problem is central to many applications in economics and sociology, when both nodal heterogeneity and high-dimensional individual characteristics highly affect network formation. We propose a statistically grounded, unified deep neural network approach for modeling nodal heterogeneity in random networks with high-dimensional nodal attributes, namely ``NetworkNet''. A key innovation of NetworkNet lies in a tailored neural architecture that explicitly parameterizes attribute-driven heterogeneity, and at the same time, embeds a scalable attribute selection mechanism. NetworkNet consistently estimates two types of latent heterogeneity functions, i.e., nodal expansiveness and popularity, while simultaneously performing data-driven attribute selection to extract influential nodal attributes. By unifying classical statistical network modeling with deep learning, NetworkNet delivers the expressive power of DNNs with methodological interpretability, algorithmic scalability, and statistical rigor with a non-asymptotic approximation error bound. Empirically, simulations demonstrate strong performance in both heterogeneity estimation and high-dimensional attribute selection. We further apply NetworkNet to a large-scale author-citation network among statisticians, revealing new insights into the dynamic evolution of research fields and scholarly impact.