{
 "artifacts": null,
 "category": "architecture",
 "description": "Replace random node or token subsampling by a subset selected to preserve the averages of low-frequency graph signals exactly or approximately. Build a graph over nodes or tokens, compute its Laplacian eigenspace, and choose a fixed-cardinality subset whose eigenvector moments match those of the full graph; use the retained subset for graph pooling or downstream attention.",
 "formulas_latex": [
  "$$\\frac{1}{n}\\sum_{v\\in[n]}f(v)=\\sum_{w\\in W}a_w f(w)$$",
  "$$\\frac{1}{m}\\sum_{j=1}^{n}z_jU_{rj}=\\frac{1}{n}\\sum_{j=1}^{n}U_{rj}\\quad (r\\in I_t),\\qquad z_j\\in\\{0,1\\},\\quad \\mathbf{1}^{\\top}z=m$$",
  "$$U_{\\mathrm{low}}z=0,\\qquad R(z)=\\left\\|\\frac{1}{m}U_{\\mathrm{low}}z\\right\\|_2^2$$",
  "$$P_t=\\operatorname{conv}\\{b_1,\\ldots,b_n\\},\\qquad b_j=(U_{rj})_{r\\in I_t}$$"
 ],
 "id": 2760,
 "implementation": "Integrate this at the node-pooling stage of a message-passing GNN, or at a token-pruning stage before an expensive attention block. For each graph or token set with n items, construct a symmetric affinity matrix A from existing node edges or from cosine similarities of current embeddings, define L=D-A with D_{ii}=\\sum_jA_{ij}, and compute the first q nonconstant eigenvectors U_low using Lanczos or a randomized eigensolver. Use this procedure: (1) choose target retention m=\\lceil\\rho n\\rceil and eigen-dimension q; (2) solve the binary problem min_{z\\in\\{0,1\\}^n,\\ 1^Tz=m} ||U_low z||_2^2, optionally adding a coverage term that discourages all selected nodes from being adjacent; (3) test whether the optimum is zero, which indicates an exact uniform design; (4) during training, use the selected indices as a hard mask and pass only retained nodes to later layers; (5) refresh the mask every K steps, or learn soft gates g_j\\in[0,1] with a straight-through top-m operator and penalty ||U_low g||_2^2/m^2. The paper-derived computation is the spectral residual and exact zero-moment constraint. The graph, eigenvectors, and q are estimated from the current batch, so no paper-specific constants are required. Start with a 2-4 layer GraphSAGE or GCN on Cora, Citeseer, or OGBN-Arxiv, retaining 25%, 50%, and 75% of nodes before a global readout or expensive cross-node layer. Compare random sampling, degree sampling, and leverage-score sampling at equal retained-node FLOPs. Measure validation accuracy, spectral residual R(z), loss at equal wall-clock/FLOPs, and memory. A successful result should show lower low-frequency reconstruction error and higher accuracy than random pruning at the same retention ratio, with approximately proportional reduction in the cost of subsequent message passing or attention. For a transformer adaptation, construct an affinity graph from token embeddings and evaluate perplexity together with KV-cache size, since the method only guarantees preservation of the selected low-frequency graph-signal subspace.",
 "math_summary": "The graphical-design condition is that a weighted subset W averages every function in a selected Laplacian eigenspace exactly: (1/n)\\sum_{v=1}^{n} f(v)=\\sum_{w\\in W}a_w f(w). Let L be the graph Laplacian, with eigenvalues 0=\\lambda_0\u003c\\lambda_1\u003c\\cdots and an eigenvector matrix U whose first row is the constant eigenvector. For a uniform subset of size m, define z\\in\\{0,1\\}^n by z_j=1 iff j\\in W. Exact averaging of the first s_t eigenvector rows is equivalent to \\frac{1}{m}\\sum_{j=1}^n z_jU_{rj}=\\frac{1}{n}\\sum_{j=1}^nU_{rj} for every r\\le s_t. Since the nonconstant eigenvectors are orthogonal to the constant vector, this reduces to U_{\\mathrm{low}}z=0 together with \\mathbf{1}^{\\top}z=m, where U_{\\mathrm{low}} contains the selected nonconstant rows. The paper's eigenconfiguration consists of the columns b_j=(U_{rj})_{r\\in I_t}; a design is a subset whose column sum is zero, equivalently whose selected-point centroid is the origin. The polytope P_t=\\operatorname{conv}\\{b_1,\\ldots,b_n\\} characterizes feasible positive weighted designs through faces and supports cardinality bounds. In neural networks, use the exact residual R(z)=\\|U_{\\mathrm{low}}z\\|_2^2/m^2 as a differentiable proxy when no exact 0-1 design exists.",
 "math_tags": [
  "graph-theory",
  "spectral-theory",
  "convex-analysis",
  "combinatorics"
 ],
 "ml_areas": [
  "graph-nn",
  "pruning",
  "attention",
  "memory"
 ],
 "paper": {
  "arxiv_id": "2608.27624",
  "arxiv_url": "https://arxiv.org/abs/2608.27624",
  "summary_what_math_gives_to_ml": "The paper gives a constructive way to select a uniform subset of graph vertices whose empirical average matches the full-graph average for every function in a prescribed collection of low-Laplacian-frequency eigenspaces. The transferable asset is the spectral moment-matching condition and its polyhedral interpretation: selecting vertices becomes finding a small 0-1 subset whose eigenvector-coordinate sum is zero. This suggests a graph-pooling or token-pruning module that preserves low-frequency information while reducing the number of nodes processed by later layers. Exact designs may not exist, so the practical version should combine the integer feasibility formulation with an approximate spectral residual penalty and compare it against random, degree-based, and leverage-score sampling.",
  "title": "Uniformly Weighted Graphical Designs",
  "year": "2026"
 },
 "ratings": {
  "difficulty": 5,
  "novelty": 7,
  "usefulness": 6
 },
 "solves": [
  "memory",
  "speedup",
  "accuracy"
 ],
 "title": "Uniform spectral graph coreset",
 "url": "https://synthcore.org/idea/2760/uniform-spectral-graph-coreset",
 "verification": {
  "peer_reviewed": false,
  "status": "unverified",
  "status_label": "Unverified",
  "verdict_source": "deterministic test code (paired-seed permutation statistics)"
 }
}