arXiv Machine Learning
Jun 19
Prior-Informed Flow Matching for Graph Reconstruction
arXiv:2601. 22107v2 Announce Type: replace Abstract: We introduce \textit{Prior-Informed Flow Matching (PIFM)}, a conditional flow model for graph reconstruction.
Flowette: Flow Matching with Graphette Priors for Graph Generation
Related stories
arXiv Machine Learning
Sep 24
Variational Bayesian Flow Network for Graph Generation
The paper introduces Variational Bayesian Flow Network (VBFN), a graph generation model that lifts Bayesian updates to a joint Gaussian belief family with structured precisions, enabling coupled node and edge updates in a single fusion step. By constructing sample‑agnostic sparse precisions from a representation‑induced dependency graph, VBFN avoids label leakage while enforcing node‑edge consistency. Experiments on synthetic and molecular graph datasets show that VBFN improves fidelity and diversity over baseline methods.
arXiv Machine Learning
Sep 30
Alignment Matters Inside and Out in Equivariant Graph Flow Matching
The paper investigates how alignment—both outer (choosing which graphs to pair) and inner (aligning node representatives)—affects permutation-equivariant graph flow matching. It connects inner alignment to transport on the graph quotient space and shows that quotient couplings can be lifted to aligned representatives, while symmetrization yields equivariant flow‑matching minimizers. Experiments on continuous graph and molecular generation demonstrate that appropriate alignment can simplify trajectories and improve few‑step generation, though the benefits vary with the type of alignment and computational budget.
arXiv AI
Jun 11
From Uniform to Learned Graph Priors: Diffusion for Structure Discovery
arXiv:2606. 11831v1 Announce Type: cross Abstract: Neural relational inference (NRI) methods discover interaction graphs from trajectories through variational reasoning on discrete potential edges.
Hugging Face Trending Papers
Oct 24
Graph-dependent pooling: adaptive granularity in hierarchical graph neural networks
Graph Neural Networks are widely used to learn structural representations of relational data. Hierarchical graph pooling learns multi-level representations by progressively coarsening graphs; however,...
arXiv Machine Learning
Oct 2
RetroGEF: Dynamic Graph Edit Flow for Single-Step Retrosynthesis
RetroGEF is a flow-based generative model designed for single-step retrosynthesis, which constructs possible reactants by adding atoms and altering bonds directly from a target molecule’s graph. Unlike traditional methods that rely on a fixed-size canvas or a prescribed edit order, RetroGEF models both connectivity changes and graph size variations within a single generative process, learning directly from product–reactant pairs. Experiments on standard retrosynthesis benchmarks show that RetroGEF achieves state‑of‑the‑art performance.
arXiv AI
Oct 27
Graph-dependent pooling: adaptive granularity in hierarchical graph neural networks
Graph-Dependent Pooling (GDPool) introduces a dynamic approach to hierarchical graph pooling, allowing each graph to determine its own pooling granularity rather than relying on fixed cluster numbers or ratios. The method employs self-attention to select graph-specific anchors and uses soft node assignment to build coarser graphs, addressing optimization conflicts identified through gradient alignment analysis. Experiments on metal‑organic framework and molecular graph datasets demonstrate that GDPool outperforms existing methods in predictive accuracy, modularity, and exhibits stable behavior across various hyperparameters.
arXiv Machine Learning
Sep 7
Embedded Graph Flows for Categorical Graph Generation
Embedded Graph Flows (EGF) is a generative model for categorical graphs that learns continuous embeddings for node and unordered-edge categories and uses a permutation‑equivariant graph transformer to transport Gaussian noise toward these embeddings. A terminal readout then maps the embeddings back to discrete graph categories. EGF achieves competitive performance on molecular benchmarks, outperforming other methods on QM9 and maintaining low maximum mean discrepancy on ZINC250k.
arXiv AI
Jun 19
Protein Representation Learning with Secondary-Structure and Energy-Filtered Hydrogen-Bond Graphs
arXiv:2606. 19374v1 Announce Type: cross Abstract: Graph-based representations are widely used in protein modeling, yet many existing approaches rely primarily on sequence adjacency or geometric proximity, which only partially reflect the principles governing protein folding.
arXiv Machine Learning
Aug 26
MolGA: Molecular Graph Adaptation with Pre-trained 2D Graph Encoder
arXiv:2510.07289v2 Announce Type: replace Abstract: Molecular graph representation learning is widely used in chemical and biomedical research. While pre-trained 2D graph encoders have demonstrated s...
arXiv Machine Learning
Jun 2
From Moments to Models: Graphon-Mixture Learning for Mixup and Contrastive Learning
arXiv:2510. 03690v4 Announce Type: replace Abstract: Real-world graph datasets often arise from mixtures of populations, where graphs are generated by multiple distinct underlying distributions.
arXiv AI
Jun 4
Scaling Novel Graph Generation via Lightweight Structure-Guided Autoregressive Models
arXiv:2606. 04287v1 Announce Type: cross Abstract: Generating realistic and diverse graphs is a key problem in machine learning, with applications in molecular discovery, circuit design, cybersecurity, and beyond.