ML: Graph nn

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

516 ideas found

Unverified 2026

Vineyard Activation Monitor

Construct a filtered cell complex from neural activations or a learned token/feature graph and track its persistence barcode incrementally as model activations change. Replace full persistent-homology recomputation at every checkpoint by maintaining homology bases and applying local transpositions when filtration blocks split or merge; use barcode drift as a training monitor or a weak regularization signal.

Useful5/10
Difficulty6/10
Novelty6/10
Paper: Computing Conley-Morse Persistence Barcode Efficiently by Updating Matrix Decompositions arXiv:2608.06507
Unverified 2026

Cycle-Spectrum Preservation Loss

Use the squarefree cycle polynomial as a structural loss for graph autoencoders, graph generators, or graph distillation. Penalize mismatch between input and reconstructed or generated graphs in weighted simple-cycle totals, preventing models from matching degree and edge statistics while destroying higher-order loop structure.

Useful5/10
Difficulty4/10
Novelty8/10
Paper: Squarefree Matrix Formulas for the CWR Invariant of Alternating Knots and Links arXiv:2608.06372
Unverified 2026

Squarefree Cycle Positional Encoding

Augment every graph node with weighted participation in simple cycles of lengths 3 through K, computed using the paper's squarefree trace construction. Feed these features into a graph transformer or message-passing network so nodes with identical local degrees and ordinary spectral statistics can still be distinguished by their exact loop environment.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Squarefree Matrix Formulas for the CWR Invariant of Alternating Knots and Links arXiv:2608.06372
Unverified 2026

Profile Consistency Regularizer

Regularize an encoder so that geometrically equivalent augmentations preserve the colored interaction profile across scales. Unlike a scalar overlap loss, the objective penalizes changes in connected overlap and alternating higher-dimensional topology simultaneously over a radius grid.

Useful5/10
Difficulty4/10
Novelty6/10
Paper: The Intersection Euler Characteristic Profile: Euler Calculus and Stability for Topological Interaction of Ball Unions arXiv:2608.06180
Unverified 2026

Simultaneous-Label Sparse Attention

Replace a dense attention pattern by the exact intersection of a fixed or cheaply computed base graph H and a learned shared-label relation. Two tokens can exchange information only when they are adjacent in H and share at least one of d labels, producing a controllable structured sparsity pattern. The label count d becomes an explicit capacity and compute knob: increasing d enlarges the relation vocabulary without requiring a dense pairwise mask.

Useful5/10
Difficulty6/10
Novelty5/10
Paper: Simultaneous Graph Parameters and How to Bound Them arXiv:2608.06055
Unverified 2026

Square-Root Boundary-Temperature Attention

Add a measurement-conditioned attention layer with two explicitly separated fields: a geometry-only inverse-temperature profile that controls interaction strength and an outcome-dependent chemical-potential bias. For a region bounded by coordinates a and b, force the interaction gate to vanish as the square root of the distance from either boundary, while allowing a separate potential channel to encode measured values.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: Measurement-induced entanglement Hamiltonian arXiv:2608.06006
Unverified 2026

Chain-Compatible Differential Pooling

Treat learned features on a mesh as differential forms and pool them against oriented chains using wedge or cap products instead of ordinary coordinate averaging. Couple forward and boundary features with the signed chain differential so that pooling commutes with differentiation, preserving local conservation and orientation information.

Useful5/10
Difficulty5/10
Novelty8/10
Paper: Differential Homology arXiv:2608.05048
Unverified 2026

Schur-Complement Barrier Message Passing

Add a small number of latent region-offset variables to a graph or token-mixing layer, interpreting selected edges as low-permeability barriers that suppress cross-region information flow. Eliminate the latent variables analytically, yielding a visible-node update with a structured low-rank correction rather than adding persistent hidden node states. The module is intended to preserve within-cluster propagation while preventing oversmoothing or contamination across learned boundaries.

Useful5/10
Difficulty6/10
Novelty6/10
Paper: An unfitted finite element discrete fracture model for low-permeability barriers via local stiffness matrix modification arXiv:2608.04431
Unverified 2026

Repair-cost detector for incompatible similarity predictions

Use the paper's lower bound on nearest-correlation repair cost to detect when a neural network's pairwise similarity predictions contain too much globally incompatible off-diagonal energy. Instead of projecting every predicted matrix onto the correlation cone, train the network to reduce the repair-risk statistic or trigger expensive repair only when a cheap diagnostic predicts substantial distortion.

Useful5/10
Difficulty4/10
Novelty6/10
Paper: Correlation Matrices in High Dimensions: The Elliptope as a Sample-Correlation Ensemble arXiv:2608.04162
Unverified 2026

Type-B fermionic equivariant layer

Represent each of n signed tokens with two or more anticommuting feature channels and build equivariant outputs from exterior products rather than unconstrained tensor products. Penalize or project out positive-degree signed-permutation invariants, approximating the coinvariant quotient so that the layer retains order-sensitive orientation information without learning redundant invariant directions.

Useful5/10
Difficulty6/10
Novelty6/10
Paper: Type $B$ fermionic coinvariant rings arXiv:2608.02881
Unverified 2026

Cocycle-Twisted Attention

Attach each token or graph node a discrete grade a in a finite group A, and modify attention value composition with a normalized group 2-cocycle rather than independent pairwise gates. The cocycle provides a globally consistent projective interaction rule, so composing three messages gives the same result under either parenthesization. This may improve relational reasoning while reducing the number of freely learned interaction parameters.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Zesting and the relative complexity of Reshetikhin-Turaev invariants arXiv:2608.02795
Unverified 2026

Response-Based Spectral Degeneracy Breaking

Add a positive multiplicative perturbation to the node or token measure of a symmetric neural operator and use the paper's eigenvalue-response matrix to identify nearly degenerate eigenspaces. Train the perturbation or its scale so that repeated eigenvalues split with a controlled minimum gap, making spectral positional encodings and eigenvector-based message passing more stable.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Response Calculus for Spectral Simplicity and Joint Eigenvalue Densities arXiv:2608.02459
Unverified 2026

Piecewise-Curvature Message Passing

Use local Ollivier–Ricci curvature as a data-dependent controller for the self-loop versus neighbor-mixing coefficient in a graph or hypergraph neural layer. Estimate the idleness-curvature curve from only a few idleness values, then choose a conservative mixing coefficient: highly positively curved edges receive stronger neighbor aggregation, while negatively curved edges retain more self-information to reduce oversmoothing and heterophily damage.

Useful5/10
Difficulty6/10
Novelty6/10
Paper: Idleness Functions for Ollivier-Ricci Curvature on Hypergraphs arXiv:2608.01970
Unverified 2026

Signed Theta Geometric Embedding Loss

Use the Lovász-style prescribed inner product as a differentiable regularizer on node embeddings. Positive and negative signed relations are compared through the identity or the involution respectively, encouraging a representation whose geometry respects signed colouring constraints and remains invariant to switching gauges.

Useful5/10
Difficulty3/10
Novelty6/10
Paper: A Lovász Theta Parameter and Theta Body for Signed Graphs arXiv:2608.01716
Unverified 2026

Holonomy-preserving quad-mesh augmentation

Use the paper's explicit square insertion surgery to generate new quad-mesh examples with altered local valence patterns but unchanged genus, unchanged non-target vertices, and unchanged rotational-holonomy subgroup. Train a mesh GNN with consistency loss or label-preserving augmentation across the original and surgically modified meshes, forcing predictions to depend on global structure rather than accidental local tessellation.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Which Holonomy Signatures Are Realizable? A Complete Answer for Closed Surfaces arXiv:2608.01444
Unverified 2026

Pyramidal one-sided Lipschitz attention

Replace unconstrained directed attention logits by observables that are one-sided 1-Lipschitz under a learned quasi-metric: an observable may increase from node j to node i by at most the directed cost from j to i, while the reverse direction can behave differently. Apply this constraint at several subsampled resolutions and penalize the Hausdorff mismatch between observable families of two augmented views, preserving directed structure while making attention stable under perturbations.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Pyramidal Compactification of Asymmetric Metric Measure Spaces via Adjoint Transport arXiv:2608.01145
Unverified 2026

Finite-State Extinction Monitor and Threshold Scheduler

Treat a quantized recurrent network as a finite deterministic state-transition system and distinguish absorption from latent periodic behavior during inference or training. Use the observed extinction threshold to adapt the activation threshold or recurrent gain, stopping once all tested trajectories reach the zero state and increasing the threshold when trajectories enter nontrivial cycles.

Useful5/10
Difficulty4/10
Novelty8/10
Paper: Extinction thresholds in a graph-based model of HIV infection dynamics arXiv:2608.00340
Unverified 2026

Contractive 9-Way Hierarchical Positional Encoding

Replace a large flat positional-embedding table with a recursively decoded nine-way address whose child transformations contract coordinates by exactly 1/3. Encode an input position using features attached to the address prefix at several depths, guaranteeing that increasing depth produces a geometrically localized representation and that an infinite valid address cannot ambiguously represent two distinct points. This is especially suitable for 2D vision tokens, maps, point clouds, or…

Useful5/10
Difficulty4/10
Novelty4/10
Paper: Hex9: A Quasi-Authalic, Quasi-Continuous Hexagonal DGGS on the Reference Ellipsoid arXiv:2608.00022
Unverified 2026

Collision-Aware Graph Edge Router

Use the model's non-monotonicity result to make graph connectivity a learned resource rather than assuming that every extra edge helps. An edge router assigns transmission scores but also charges a source-side collision cost for exposing an infected node to many susceptible neighbors. The resulting router can prune edges that increase competition and reduce useful reachability.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: The Zombie Infection Model arXiv:2607.29409
Unverified 2026

Covariance-complement uncertainty head

Represent uncertainty of a graph-structured neural feature field through dual covariance rather than explicitly storing a dense primal covariance. Recover calibrated primal marginal variances from dual statistics using the paper's covariance-complement identity.

Useful5/10
Difficulty4/10
Novelty8/10
Paper: Accelerated Random-Sweep Gibbs Sampling for Gaussian Graphical Models via Dual Normal Factor Graphs arXiv:2607.28706
Unverified 2026

Chain-Compatible Graph Pooling

Replace an arbitrary graph pooling map with a pooling operator constrained to commute with the graph incidence or boundary operator. This gives a hierarchical GNN an exact coarse-to-fine consistency condition: node and edge features must be pooled in a coordinated way that preserves local conservation and cycle structure.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Lifting Lifted Product Codes arXiv:2607.28621
Unverified 2026

Commutator-flow latent block

Represent each token or graph node by an anti-Hermitian matrix latent state and replace a standard residual transformation with a discretized Lie-algebra vortex flow. The commutator nonlinearities are equivariant under global unitary conjugation, so the block can learn interactions without selecting a basis and preserves the anti-Hermitian state space when initialized there.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Vortex Filaments in Hermitian Reductive Lie Algebras arXiv:2607.26650
Unverified 2026

Selector-Driven Hierarchical Permutation Mixer

Replace part of dense token mixing with a small bank of structured permutations acting on a hierarchical token tree. Diagonal inheritance shares the same local permutation across all descendant copies, while selector words activate one connector type at a chosen level and remain inactive on the next type, providing controllable multiscale receptive fields without constructing a dense attention matrix.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Near full groups of bounded type, \rom{2} arXiv:2607.26572
Unverified 2026

Stable directed-path topology features

Construct a filtration from learned directed edge or transition weights, compute persistent path homology, and feed compact persistence features into a graph or sequence neural network. Because the paper proves stability under network-distance perturbations, these features should be less sensitive to small changes in edge scores than raw adjacency statistics, while retaining orientation-sensitive information that ordinary undirected topology loses.

Useful5/10
Difficulty7/10
Novelty6/10
Paper: Stability of persistent path homology of path complexes arXiv:2607.26226