ML: Graph nn

Machine-learning ideas tagged Graph nn in the ML taxonomy of the Math2NN corpus.

516 ideas found

Unverified 2026

Fractional Nonlocal-Gradient Residual Block

Augment a local convolutional block with a fractional nonlocal-gradient branch that aggregates directional feature differences over multiple spatial scales. The residual branch gives each location access to long-range variation while preserving the property that constant feature fields produce zero response. A learnable residual gate allows the network to suppress the branch if nonlocal interactions are unhelpful.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: A Lusin theorem for nonlocal gradients arXiv:2607.25621
Unverified 2026

Continuous Edge Prototypes

Replace node-restricted graph prototypes by centers that may lie at arbitrary coordinates on graph edges. For each prototype, hold its assigned points and shortest-path branches fixed, then update its edge coordinate by an exact clipped weighted least-squares formula; recompute branch changes only at arc bottleneck points. This creates a graph-aware vector-quantization or retrieval module that can represent semantic locations between existing nodes.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: A Foundational Perspective for Partitional Clustering on Networks arXiv:2607.25144
Unverified 2026

Linear-budget graph-cover attention

Construct a graph on tokens using a cheap similarity or k-nearest-neighbor rule, partition it into small-radius pieces, and use one pooled state per piece for cross-piece communication. The paper's bound guarantees that the total number of vertices exposed by all one-hop piece neighborhoods is at most 4n, so the routing graph can have linear rather than quadratic communication budget. The approximation is controlled by increasing the number of within-piece basis summaries rather than making…

Useful6/10
Difficulty5/10
Novelty7/10
Paper: On efficient graph covers and steered random walks arXiv:2607.25016
Unverified 2026

Period-Resolvent Recurrent Layer

Construct a recurrent or graph-neural layer on a finite state space with a known bijection T, such as a modular cat map, and use the diagonal resolvent gain (1 − α^kx)^−1 as a state-dependent self-return or memory coefficient. States on short periodic orbits receive larger amplification, while long-period states receive weaker amplification, producing deterministic localization without learned disorder.

Useful6/10
Difficulty5/10
Novelty8/10
Paper: Arithmetic Landscape Functions of a Discrete Cat Map arXiv:2607.24857
Unverified 2026

Hypertree-Sparse Tensor Initialization

Replace a dense order-p tensorized neural layer with a sparse random hypergraph tensor whose support probability is alpha = c/N^{p-1}. Assign independent zero-mean marks to active hyperedges, so every tensor moment scales as N^{-(p-1)} while the total variance entering each output remains controlled. The resulting locally tree-like computation graph should reduce parameters and multiply-adds without immediately destroying signal propagation.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Spectral aspects of random heavy-tailed tensors arXiv:2607.24695
Unverified 2026

Morphogen-Controlled Topology-Preserving Sparse Growth

Replace fixed sparse masks with a stochastic birth-death process for neural connections or spatial units. A diffusing morphogen-like utility field controls where connections are added or removed, while a local simple-point test rejects removals or additions that would disconnect a layer or alter a prescribed computational topology. This creates an adaptive sparse architecture with a tunable compact-to-branched transition rather than unconstrained magnitude pruning.

Useful6/10
Difficulty6/10
Novelty6/10
Paper: Control of morphology and topology in a lattice model of branching morphogenesis arXiv:2607.24619
Unverified 2026

Holder-Stable Density Kernel Attention

Use a density-weighted kernel operator whose features are multiplied by sqrt(rho) on both input and output sides. Under bounded kernels, changing the density by L1 distance changes the operator in Hilbert-Schmidt norm only at square-root order, giving a directly testable robustness guarantee for adaptive attention or graph layers.

Useful6/10
Difficulty3/10
Novelty6/10
Paper: Density-Dependent Operators on Density-Projection Condensation Spaces: Ambient Extensions, Zero-Density Defects, and Stability arXiv:2607.24540
Unverified 2026

Refine-and-Coarsen Block Router

Turn the paper's graphon refinement operation into an adaptive mixture-of-experts or relational-attention router whose number of blocks is learned rather than fixed. Split a block when its members produce incompatible constraint gradients, and merge blocks when their relation rows are statistically indistinguishable, yielding a compact architecture that grows only where the data require extra structure.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Constrained Multi-Relational Graphons with Maximum Entropy arXiv:2607.22383
Unverified 2026

Tangential Landau Pairwise Noise

Replace isotropic particle noise or unconstrained pairwise graph updates by antisymmetric, relative-velocity-tangential noise. For each pair of particles, the update lies approximately in the hyperplane orthogonal to their relative displacement and has variance determined by a regularized soft-potential kernel. This should produce stochastic exploration while reducing center-of-mass drift and violations of kinetic-energy-like invariants.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: The Homogeneous Landau Equation with Regularised Thermal Noise arXiv:2607.22329
Unverified 2026

Rough Area Consistency Features

Augment ordinary edge or line-integral features with a learned second-level area term, then train the model to make predictions invariant to path subdivision and stable under nearby path perturbations. The second-level feature captures ordered pair interactions that a sum of edge increments cannot represent, providing a compact alternative to explicitly processing every intermediate point in a trajectory or graph walk.

Useful6/10
Difficulty4/10
Novelty5/10
Paper: A PDE approach to the 2D Yang-Mills measure arXiv:2607.22236
Unverified 2026

Principal-module graph compression

Build a low-dimensional basis for the principal module generated by the all-ones vector, then perform adjacency and degree propagation in compressed coordinates. On forests, the paper states that this module equals the automorphism-orbit module, so the reduced representation can preserve principal adjacency-degree information while using far fewer coordinates than the number of vertices.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Adjacency-degree algebras and spectral determination of graphs arXiv:2607.21494
Unverified 2026

Noncommutative adjacency-degree moments

Augment a graph neural network with features generated by noncommutative words in the adjacency matrix and diagonal degree matrix. Ordered patterns such as AD^2A and DADA distinguish where degree information occurs along a walk; the paper proves that the full scalar moment family determines every tree.

Useful6/10
Difficulty4/10
Novelty6/10
Paper: Adjacency-degree algebras and spectral determination of graphs arXiv:2607.21494
Unverified 2026

Subcritical Blob Graph Sparsifier

Turn stochastic edge thinning into a mass-aware graph sparsifier: first form retained connected blobs, then connect blob summaries using the rank-one shortcut probability from the paper. Choose the retention rate below the explicit subcritical threshold so the contracted graph remains a collection of small decorations around leading blobs, reducing message-passing cost without creating an artificial giant component.

Useful6/10
Difficulty6/10
Novelty6/10
Paper: Subcritical percolation and network archaeology on random recursive tree substrate networks arXiv:2607.21428
Unverified 2026

Approximation-Aware Hard-Core Routing

Construct a sparse routing or graph-neural architecture whose activation gates satisfy a hard-core constraint: neighboring sites, experts, or token groups cannot be active simultaneously. Compare the same local routing rule on bipartite and random regular interaction graphs; the graph structure should change the maximum usable activation dimension and may also change optimization stability.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: A Hard-Core Subshift Whose Sofic Mean Dimension Depends on the Sofic Approximation arXiv:2607.21398
Unverified 2026

Entropy-Calibrated Non-Backtracking Message Passing

Replace ordinary graph propagation, which repeatedly revisits the edge it just traversed, with a directed-edge non-backtracking operator. Normalize its learned gain using an estimate of the Hashimoto spectral radius so that feature magnitudes neither explode on high-growth graphs nor vanish on sparse graphs.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Critical-exponent spectra and rank two inverse realization on biregular trees arXiv:2607.21294
Unverified 2026

Multiplicative Adaptive Attention Graph

Give each query-token pair a positive adaptive edge weight that evolves by a multiplicative rule instead of relying only on instantaneous dot-product attention logits. Edges whose aggregate interaction is useful can grow, while overloaded or incompatible neighborhoods can shrink. Sparse initialization is preserved because an edge initialized at zero remains zero under the multiplicative dynamics.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: The mean-field limit of non-exchangeable particle systems with non-conservative dynamics and adaptive weights arXiv:2607.21110
Unverified 2026

L2-Certified DAG Attention Ordering

Add a learned scalar ordering to a directed graph attention layer and retain only forward edges, producing a DAG attention mask without requiring a supplied topological order. Train the ordering with a differentiable surrogate for weighted surplus, and regularize it toward the paper's explicit half-weight-minus-l2 certificate. This supplies a principled alternative to random masking or unconstrained bidirectional graph attention when causal or hierarchical information flow is desirable.

Useful6/10
Difficulty5/10
Novelty8/10
Paper: The optimal constant for minimum weight feedback arc sets in oriented graphs arXiv:2607.20996
Unverified 2026

Degree-Capped Simplicial Residual Step

Set the residual propagation coefficient of a simplicial neural layer from a cheap upper bound on the operator spectrum instead of tuning it blindly. The degree-majorization theorem supplies a bound on the largest eigenvalue, while the Brouwer-type inequality supplies a topology-count-based bound on sums of the top eigenvalues.

Useful6/10
Difficulty3/10
Novelty6/10
Paper: Degree Majorization and Laplacian Eigenvalue Sums for Simplicial Complexes arXiv:2607.20910
Unverified 2026

Simplicial Ky-Fan Spectral Budget

Use the conjugate degree sequence of codimension-one faces as a mathematically justified upper envelope for the spectrum of a simplicial up-Laplacian. Penalize violations of the corresponding top-k eigenvalue budgets in a simplicial message-passing layer, discouraging a few dominant propagation modes that cause oversmoothing or unstable amplification.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Degree Majorization and Laplacian Eigenvalue Sums for Simplicial Complexes arXiv:2607.20910
Unverified 2026

Constraint-Free Skew Coupling

Compose independently parameterized neural dynamical modules through power-preserving skew coupling instead of equality penalties or projected constraints. This creates a modular graph or world model in which information exchanged between modules is antisymmetric, so internal coupling cannot create or destroy total latent energy.

Useful6/10
Difficulty6/10
Novelty6/10
Paper: Mixed finite element discretization of intrinsic geometrically exact beams for explicit multibody dynamics arXiv:2607.20245
Unverified 2026

Reactive Mass-Weighted Message Passing

Augment every graph or set token with a positive learned mass M_i that controls how strongly it contributes to other nodes and evolves through a growth-minus-inhibition equation. Use separate learned interaction kernels for state transport and mass inhibition, while retaining a directed interaction matrix so the layer is not forced to be permutation-symmetric or conservative.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: A note on application of mean-field limit to non-exchangeable non-conservative systems arXiv:2607.20014
Unverified 2026

Volume-Weighted Hodge Convolution

Replace the ordinary combinatorial Hodge propagation in a simplicial neural network with a geometry-induced weighted Hodge Laplacian built from Euclidean simplex volumes. The operator preserves the harmonic/topological subspace while changing the positive spectrum according to the shape and scale of the simplices, allowing message passing to distinguish geometrically meaningful cells that have identical incidence patterns.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Geometry-Induced Hodge Stars on Rips and Dowker--Rips Complexes arXiv:2607.18692
Unverified 2026

Ramanujan Signed Ring Mixer

Replace an unsigned two-hop cyclic mixer by the paper's alternating signed circulant. The sign pattern preserves one-step and two-step interactions while reducing the exact spectral radius from 4 to 2√2, allowing a larger raw mixing coefficient under the same operator-norm stability constraint.

Useful6/10
Difficulty3/10
Novelty6/10
Paper: Signed circulants at the Ramanujan bound arXiv:2607.18334