The paper introduces three distance‑based graph autoencoder variants that add structural penalties to the reconstruction loss. All models use a two‑layer Graph Convolutional Network encoder and a Euclidean‑distance decoder, with two node‑level regularizers: a hub penalty based on degree centrality and a penalty based on Natural Community Local Intrinsic Dimensionality (NC‑LID). Experiments on multiple dynamic graph datasets show that incorporating NC‑LID regularization consistently improves reconstruction performance compared to baselines without structural regularization and to the hub‑aware variant.
By Aleksandar Tom\v{c}i\'c, Milo\v{s} Savi\'c, Milo\v{s} Radovanovi\'c
arXiv:2607. 24338v1 Announce Type: new Abstract: Unsupervised graph representation learning aims to derive meaningful node embeddings by capturing both structural and attribute information without relying on labeled data.
By Zengyi Wo, Shiyu Zhang, Qiyao Peng, Tianpeng Li, Xuan Guo
arXiv:2607. 00052v1 Announce Type: cross Abstract: GraphRAG is an extension of retrieval-augmented generation (RAG) that supports large language models (LLMs) by referring to graph-structured data as external knowledge.
By Bao Long Nguyen Huu, Atsushi Hashimoto
The paper introduces an unsupervised framework that merges manifold learning with rank‑based interpretable graph embeddings to address the Geometric and Interpretability Gaps in visual representation learning. By first analyzing contextual information on the dataset manifold and then producing sparse, self‑explainable embeddings, the method achieves dimensionality reduction while preserving or improving performance in image retrieval and semi‑supervised Graph Convolutional Network classification. Experiments across varied datasets confirm that these context‑aware representations maintain high downstream effectiveness.
By Thiago C\'esar Castilho Almeida, Gustavo Rosseto Let\'icio, Vinicius Atsushi Sato Kawai, Daniel Carlos Guimar\~aes Pedronette
The paper introduces a compositional graph embedding framework based on Aitchison geometry, where nodes are represented as simplex-valued mixtures over latent archetypal factors. By embedding these mixtures using isometric log-ratio coordinates, the method preserves Aitchison distances while allowing unconstrained optimization in Euclidean space, yielding intrinsically interpretable embeddings. The approach achieves competitive performance on node classification and link prediction tasks and enables principled component restriction through subcompositional coherence, allowing analysis of how archetype groups influence representations and predictions.
By Nikolaos Nakis, Chrysoula Kosma, Panagiotis Promponas, Michail Chatzianastasis, Giannis Nikolentzos
arXiv:2608. 04381v1 Announce Type: cross Abstract: Self-supervised learning on graphs is largely shaped by contrastive methods that depend on carefully designed augmentations, and by generative methods that reconstruct node attributes in the input space.
By Tinghe Zhang, Jian Xu, Jiaheng Chen, Jiaxing Li, Yucheng Xiao, Qiang Wang
arXiv:2607.11577v2 Announce Type: replace-cross
Abstract: Conventional Graph Neural Networks (GNNs) couple feature transformation and neighborhood aggregation, which often renders them vulnerable to...
By Chengcheng Yan, Feifei Zhao, Dai Zhu, Wei Liu, Qingsong Wang
arXiv:2508. 06588v3 Announce Type: replace-cross Abstract: Vector Quantization (VQ) has recently emerged as a promising approach for learning compressed and discrete representations for graph-structured data.
By Zian Zhai, Fan Li, Xingyu Tan, Xiaoyang Wang, Wenjie Zhang
arXiv:2607. 03587v1 Announce Type: new Abstract: We propose NetinfoGC, a framework for graph classification that extends the Network Usable Information (NUI) paradigm to graph-level learning.
By Abdullah Shaik, Anwar Said
arXiv:2601. 22107v2 Announce Type: replace Abstract: We introduce \textit{Prior-Informed Flow Matching (PIFM)}, a conditional flow model for graph reconstruction.
By Harvey Chen, Nicolas Zilberstein, Santiago Segarra
GraphK introduces an encoder‑sampler‑decoder framework that generates variable‑size graphs efficiently. It learns permutation‑invariant latent representations and samples new node embeddings via maximum likelihood, enabling both upscaling and downscaling of graph size. Edge construction uses KDTree‑based top‑k neighbor search in latent space, reducing computational cost while capturing graph properties.
By Resul Tugay, Eren Olu\u{g}, Elif Ak, Sule Gunduz Oguducu
arXiv:2606. 24997v1 Announce Type: new Abstract: Geographic implicit neural representations (INRs) learn to map any coordinate on Earth to a location embedding, implicitly encoding geospatial data into the weights of a neural network.
By Livia Betti, Sebastian Ricke, Ivica Obadic, Adam J. Stewart, Esther Rolf