arXiv:2607. 10074v1 Announce Type: new Abstract: Graph machine learning provides powerful tools for understanding complex networks and learning meaningful node representations.
arXiv:2609.08152v1 Announce Type: new Abstract: Graph representation learning has largely focused on designing increasingly sophisticated models to transform graph topology into vector representation...
arXiv:2509. 24256v2 Announce Type: replace-cross Abstract: The pretrain-transfer paradigm, which underpins the success of large language models (LLMs), has demonstrated the immense power of creating foundation models that learn generalizable representations from vast datasets.
arXiv:2506. 22271v3 Announce Type: replace Abstract: Neural networks often map low-dimensional embeddings to high-dimensional output spaces.
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.
The paper demonstrates that high‑quality graph embeddings can be produced without complex models or training by propagating random features through topological structures derived from random walks and anonymous walks. These training‑free embeddings capture node proximity and structural roles, respectively, and perform competitively on node, edge, and graph tasks while often requiring less computation. Combining the two embedding types further improves inference quality for some tasks.
arXiv:2602. 01553v3 Announce Type: replace-cross Abstract: Link prediction is a core challenge in graph machine learning, demanding models that capture rich and complex topological dependencies.
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.
DeltaGNN introduces an information flow control mechanism that uses a new connectivity measure, the information flow score, to mitigate over‑smoothing and over‑squashing in Graph Neural Networks. This approach enables linear computational and memory overhead while effectively capturing both short‑range and long‑range node interactions. Experiments on ten diverse real‑world datasets demonstrate superior performance with limited computational complexity.
Message-passing Graph Neural Networks (GNNs) iteratively propagate and aggregate local neighborhood information followed by global readout to learn graph representations. However, their discriminative...
arXiv:2608. 09031v1 Announce Type: new Abstract: Graph neural networks typically propagate information through repeated message-passing layers, coupling the distance over which information travels with the number of nonlinear transformations applied.
arXiv:2505. 13087v2 Announce Type: replace-cross Abstract: We propose a novel benchmarking methodology for graph neural networks (GNNs) based on the graph alignment problem, a combinatorial optimization task that generalizes graph isomorphism by aligning two unlabeled graphs to maximize overlapping edges.
arXiv:2607. 11374v1 Announce Type: new Abstract: Graph Foundation Models (GFMs) have emerged as a promising paradigm for learning transferable representations across diverse graph domains.