ProtoGuide: Prototype-Driven Guidance for Class-Conditional Graph Generation
cs.LG, cs.AI, physics.soc-ph
Submitted: 2026-09-14
Updated: 2026-09-14
Comments: Preprint. Submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence. 35 pages, 2 figures, 33 tables
License: http://creativecommons.org/licenses/by/4.0/
The gist: Discrete diffusion models are a prominent family for graph generation, but standard class-conditional mechanisms embed the class signal in the denoiser during training, tying the conditioning
Terminology
Abstract
Discrete diffusion models are a prominent family for graph generation, but standard class-conditional mechanisms embed the class signal in the denoiser during training, tying the conditioning mechanism to the trained model. Classifier guidance avoids this coupling in continuous domains by steering a frozen model with a classifier's gradient, but discrete graph diffusion samples discrete edge states, so gradients cannot propagate through the sampled graph. We introduce ProtoGuide, a post-hoc, backbone-agnostic framework that recovers an analogous mechanism. At each reverse step the denoiser's per-edge output is relaxed into a differentiable soft adjacency, embedded by a frozen Siamese graph neural network, and scored against a target-class prototype and its nearest competitor; the resulting per-edge gradient, damped by a cosine schedule, is injected back into the denoiser output. All components stay frozen, so guidance is retargeted by supplying a different prototype. On five classes of real-world networks and two architecturally different backbones, EDGE and DiGress, ProtoGuide raises macro classification accuracy from 50.7% to 73.5% and from 73.6% to 83.8%, and outperforms DiGress's built-in conditional training under our configuration. Gains are largest where the unguided models are weakest, and are not uniform across classes. Per-graph coverage remains high in most settings, while distributional effects are class-dependent. A Best-of-N selection baseline matches this accuracy given enough oversampling, but at a substantial cost in graph diversity. An independently initialized classifier, a directionality test, and a few-shot analysis support target-directed steering and robustness to very small support sets.
Sources
- Diffusion Models for Graphs Benefit From Discrete State Spaces
- Beyond MMD: Evaluating Graph Generative Models with Geometric Deep Learning
- Solving the Problem of the K Parameter in the KNN Classifier Using an Ensemble Learning Approach
- Variational Graph Auto-Encoders
- GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders
- Classifier-Free Diffusion Guidance
- Graph Guided Diffusion: Unified Guidance for Conditional Graph Generation
- Semi-Supervised Classification with Graph Convolutional Networks
- Graph Attention Networks
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks