HAGGLE: Get a better deal using a Hierarchical Autoencoder for Graph Generation and Latent-space Expressivity

Audun Myers, Stephen J. Young, Tegan Emerson
Proceedings of the 1st Conference on Topology, Algebra, and Geometry in Data Science(TAG-DS 2025), PMLR 321:191-202, 2026.

Abstract

Generating realistic and diverse graph structures is a challenge with broad applications across various scientific and engineering disciplines. A common approach involves learning a compressed latent space where graphs are represented by a collection of node-level embeddings, often via methods such as a Graph Autoencoder (GAE). A fundamental challenge arises when we try to generate new graphs by sampling from this space. While many deep learning methods like Diffusion, Variational Autoencoders (VAEs), and Generative Adversarial Networks (GANs) can successfully generate new points in the latent space, they fail to capture the inherent relational dependencies between the node embeddings. This leads to decoded graphs that lack structural coherence and fail to replicate essential real-world properties. Alternatively, generating a single graph-level embedding and then decoding it to new node embeddings is also fundamentally limited, as pooling methods needed to create the graph level embedding are inherently lossy and discard crucial local structural information. We present a three-stage hierarchical framework called Hierarchical Autoencoder for Graph Generation and Latent-space Expressivity (HAGGLE) that addresses these limitations through systematic bridging of node-level representations with graph-level generation. The framework trains a Graph Autoencoder for node embeddings, employs a Pooling Autoencoder for graph-level compression, and utilizes a size-conditioned GAN for new graph generation. This approach generates structurally coherent graphs while providing useful graph-level embeddings for downstream tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v321-myers26a, title = {HAGGLE: Get a better deal using a Hierarchical Autoencoder for Graph Generation and Latent-space Expressivity}, author = {Myers, Audun and Young, Stephen J. and Emerson, Tegan}, booktitle = {Proceedings of the 1st Conference on Topology, Algebra, and Geometry in Data Science(TAG-DS 2025)}, pages = {191--202}, year = {2026}, editor = {Bernardez Gil, Guillermo and Black, Mitchell and Cloninger, Alexander and Doster, Timothy and Emerson, Tegan and Garcı́a-Rodondo, Ińes and Holtz, Chester and Kotak, Mit and Kvinge, Henry and Mishne, Gal and Papillon, Mathilde and Pouplin, Alison and Rainey, Katie and Rieck, Bastian and Telyatnikov, Lev and Yeats, Eric and Wang, Qingsong and Wang, Yusu and Wayland, Jeremy}, volume = {321}, series = {Proceedings of Machine Learning Research}, month = {01--02 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v321/main/assets/myers26a/myers26a.pdf}, url = {https://proceedings.mlr.press/v321/myers26a.html}, abstract = {Generating realistic and diverse graph structures is a challenge with broad applications across various scientific and engineering disciplines. A common approach involves learning a compressed latent space where graphs are represented by a collection of node-level embeddings, often via methods such as a Graph Autoencoder (GAE). A fundamental challenge arises when we try to generate new graphs by sampling from this space. While many deep learning methods like Diffusion, Variational Autoencoders (VAEs), and Generative Adversarial Networks (GANs) can successfully generate new points in the latent space, they fail to capture the inherent relational dependencies between the node embeddings. This leads to decoded graphs that lack structural coherence and fail to replicate essential real-world properties. Alternatively, generating a single graph-level embedding and then decoding it to new node embeddings is also fundamentally limited, as pooling methods needed to create the graph level embedding are inherently lossy and discard crucial local structural information. We present a three-stage hierarchical framework called Hierarchical Autoencoder for Graph Generation and Latent-space Expressivity (HAGGLE) that addresses these limitations through systematic bridging of node-level representations with graph-level generation. The framework trains a Graph Autoencoder for node embeddings, employs a Pooling Autoencoder for graph-level compression, and utilizes a size-conditioned GAN for new graph generation. This approach generates structurally coherent graphs while providing useful graph-level embeddings for downstream tasks.} }
Endnote
%0 Conference Paper %T HAGGLE: Get a better deal using a Hierarchical Autoencoder for Graph Generation and Latent-space Expressivity %A Audun Myers %A Stephen J. Young %A Tegan Emerson %B Proceedings of the 1st Conference on Topology, Algebra, and Geometry in Data Science(TAG-DS 2025) %C Proceedings of Machine Learning Research %D 2026 %E Guillermo Bernardez Gil %E Mitchell Black %E Alexander Cloninger %E Timothy Doster %E Tegan Emerson %E Ińes Garcı́a-Rodondo %E Chester Holtz %E Mit Kotak %E Henry Kvinge %E Gal Mishne %E Mathilde Papillon %E Alison Pouplin %E Katie Rainey %E Bastian Rieck %E Lev Telyatnikov %E Eric Yeats %E Qingsong Wang %E Yusu Wang %E Jeremy Wayland %F pmlr-v321-myers26a %I PMLR %P 191--202 %U https://proceedings.mlr.press/v321/myers26a.html %V 321 %X Generating realistic and diverse graph structures is a challenge with broad applications across various scientific and engineering disciplines. A common approach involves learning a compressed latent space where graphs are represented by a collection of node-level embeddings, often via methods such as a Graph Autoencoder (GAE). A fundamental challenge arises when we try to generate new graphs by sampling from this space. While many deep learning methods like Diffusion, Variational Autoencoders (VAEs), and Generative Adversarial Networks (GANs) can successfully generate new points in the latent space, they fail to capture the inherent relational dependencies between the node embeddings. This leads to decoded graphs that lack structural coherence and fail to replicate essential real-world properties. Alternatively, generating a single graph-level embedding and then decoding it to new node embeddings is also fundamentally limited, as pooling methods needed to create the graph level embedding are inherently lossy and discard crucial local structural information. We present a three-stage hierarchical framework called Hierarchical Autoencoder for Graph Generation and Latent-space Expressivity (HAGGLE) that addresses these limitations through systematic bridging of node-level representations with graph-level generation. The framework trains a Graph Autoencoder for node embeddings, employs a Pooling Autoencoder for graph-level compression, and utilizes a size-conditioned GAN for new graph generation. This approach generates structurally coherent graphs while providing useful graph-level embeddings for downstream tasks.
APA
Myers, A., Young, S.J. & Emerson, T.. (2026). HAGGLE: Get a better deal using a Hierarchical Autoencoder for Graph Generation and Latent-space Expressivity. Proceedings of the 1st Conference on Topology, Algebra, and Geometry in Data Science(TAG-DS 2025), in Proceedings of Machine Learning Research 321:191-202 Available from https://proceedings.mlr.press/v321/myers26a.html.

Related Material