GraphVAEBM is introduced, a framework that separates graph generation from property modeling, and a Graph Variational Autoencoder is first trained to learn a continuous graph manifold and then frozen, while independent Energy-Based Models are trained to represent specific graph properties.
Experiments on synthetic and real-world datasets show that GraphK outperforms existing methods, accurately learns graph structures, and generates synthetic graphs without explicit definitions.
Resul Tugay, Eren Olug, Elif Ak et al.· 0 citations
This study proposes a model called the Residual compensation graph Convolutional Generalized Extreme Learning Machine Autoencoder (RCGELM-AE), which is built on the Extreme Learning Machine Autoencoder (ELM-AE) and incorporates two key designs, and offers a novel, gradient-descent-free solution for achieving efficient...
This work shows that informative embeddings can be derived without complicated model design and gradient-based training, and suggests that informative graph embeddings can arise from carefully chosen topological transformations before any learning operation is applied.
Meng Qin, Jin-Qiang Cui, Hong-Wei Zheng et al.· 0 citations
ProtoGuide is introduced, a post-hoc, backbone-agnostic framework that recovers an analogous mechanism for discrete diffusion models and raises macro classification accuracy and outperforms DiGress's built-in conditional training under the authors' configuration.
Salvatore Romano, Marco Grassia, Pietro Liò et al.· 0 citations
A novel interpretation of sfGOT through the lens of the Hilbert-Schmidt Independence Criterion is provided, showing that minimizing the sfGOT distance between two graphs is equivalent to maximizing statistical dependence between the spectral embedding of their nodes.
Weight-space networks operate directly on parameters of other neural networks, enabling tasks such as predicting model properties, editing trained models, and generating weights. Weight-space symmetries such as neuron permutations make equivariance a key design principle. However, existing equivariant weight-space arch...
A. Dayan, Yam Eitan, Haggai Maron· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
