Graph-Sparse Logistic Regression for sparse and connected support classification.
problem Sparse and connected support classification problems.
method Introduces Graph-Sparse Logistic Regression algorithm.
result Validated and benchmarked against L1-regularized Logistic Regression.
The paper explores graphons of line graphs from sparse finite graphs.
problem Estimating graph limits from sparse finite graphs.
method Mapping finite graphs to their line graphs and analyzing graphs with the square-degree property.
result Graphons of line graphs can distinguish between sparse graphs like star graphs and superlinear preferential attachment graphs.
Connectedness constraint for sparse graph learning.
problem Learning sparse graphs often results in disconnected components.
method Formulated connectedness as a convex constraint.
result Connected sparse graphs can be learned from data.
New method speeds up sparse graph neural networks training on dense hardware.
problem Training sparse graph neural networks is slow on custom hardware.
method Inspired by sparse matrix optimization, developed techniques for dense hardware.
result Sparse graph neural networks trained in 13 minutes on 512-core TPUv2 Pod.
The paper infers graph structure from sparse signal observations.
problem Inferring graph structure from sparse signal observations.
method Formulates a non-convex graph learning problem and solves it via alternating signal sparse coding and graph update steps.
result The method generally outperforms other network inference algorithms in graph recovery.
Improved GCNs for non-sparse graphs with low-rank filters.
problem Training and evaluation of GCNs on large non-sparse graphs is computationally expensive.
method Introduced low-rank filters and a reduced-order GCN architecture.
result Significant runtime acceleration and improved accuracy achieved.
This paper proposes a method to reveal task relationships in multi-task learning models using sparse graphs.
problem Understanding the underlying task relationships in multi-task learning models.
method Proposes a bilevel formulation of multi-task learning that induces sparse graphs.
result The method improves interpretability of multi-task learning models without sacrificing generalization performance.
Generative model captures hubs and dense communities in social networks.
problem Capturing both hubs and dense communities in social networks.
method Graphon mixture model with a new condition on sparse graphs.
result Estimation of hub normalized degree and graphon for sparse components.
A new method embeds sparse stochastic graphs into low dimensions.
problem Embedding large, sparse, stochastic graphs into low-dimensional spaces.
method Spaceland Embedding (SG-t-SNE) inspired by t-SNE, leveraging modern computing techniques.
result Effective embedding results on synthetic and real-world graphs.
Method learns sparse graph for multivariate data prediction efficiently.
problem Prediction of multivariate data processes using sparse graph models.
method Recursive learning of sparse partial correlation graph without cross-validation or tuning.
result Significant performance gains in prediction compared to existing graphs.
Method converts sparse systems to dense ones for statistical mechanics problems.
problem Statistical mechanics on sparse graphs
method Extracts a Feedback Vertex Set, learns variational distribution, estimates free energy.
result More accurate and faster than existing methods for sparse systems.
Graph-Dictionary model for sparse multivariate signal representation.
problem Capturing complex relational information in multivariate signals.
method Graph dictionaries and bilinear primal-dual splitting algorithm.
result Graph-dictionary model outperforms baselines in signal reconstruction and classification.
Framework models graph-connected entities with sparse shared HMMs.
problem Model sequential data from graph-connected entities.
method Sparse Mixture of Hidden Markov Models (HMMs) trained jointly with graph topology.
result Effectiveness and versatility demonstrated in experiments.
SGATs learn sparse attention coefficients to improve graph learning tasks on large, noisy graphs.
problem Overfitting and noisy edges in GNNs on large, noisy graphs.
method Sparse Graph Attention Networks (SGATs) learn sparse attention coefficients under L0-norm regularization. result SGATs can remove 50%-80% edges from large graphs while maintaining similar classification accuracies.
NGRs merge sparse graph recovery with PGMs for efficient probabilistic inference.
problem Efficiently recover sparse graphs and learn distributions over variables.
method Integrates sparse graph recovery methods with PGMs using Graph-constrained path norm.
result NGRs can handle multimodal data and perform sparse graph recovery and probabilistic inference.
FI-GNNs learn expressive node representations from sparse features.
problem Sparse and high-dimensional node features limit GNN performance.
method Plug-and-play GNN framework that highlights informative feature interactions.
result FI-GNNs learn highly expressive node representations on feature-sparse graphs.
Random projections help in representing sparse graphs efficiently.
problem Efficiently representing sparse graphs of varying sizes and vertex sets.
method Random projection of adjacency matrices to retain graph functionality and properties.
result Random projections can accurately represent graphs of different sizes and vertex sets in the same space.
Sparse hierarchical graph classification improves graph-based benchmarks.
problem Sparse hierarchical graph classification challenges.
method Combining recent advances in graph neural network design, differentiable graph coarsening, and sparse pooling.
result Competitive hierarchical graph classification results possible without sacrificing sparsity.
SpaPool combines dense and sparse techniques for efficient graph pooling.
problem Efficiently processing large graphs in graph neural networks.
method Adaptive clustering of graph vertices into clusters.
result SpaPool outperforms existing methods on small-scale graphs.
New method estimates graph compatibility from sparse labels.
problem Estimating graph compatibility from sparse labeled data.
method Factorized graph representations and algebraic amplification.
result End-to-end classification accuracy comparable to gold standard.
GLAD learns a compact model to recover sparse graphs from data.
problem Recovering sparse conditional independence graphs from data.
method GLAD uses an Alternating Minimization (AM) algorithm as a model inductive bias and learns parameters via supervised learning.
result GLAD learns a very compact and effective model for sparse graph recovery.
New model allows sparse graphs with many triangles to be represented.
problem Sparse graphs with many triangles cannot be accurately represented in finite dimensions.
method Infinite-dimensional inner product model with manifold representations.
result Local neighborhoods can be represented in lower dimensions.
New matrix reveals cluster info in sparse directed graphs.
problem Analyzing cluster information in directed graphs.
method Proposed complex non-backtracking matrix integrating Hermitian adjacency matrix and non-backtracking matrix properties.
result The complex non-backtracking matrix holds cluster information, especially for sparse directed graphs.
This work introduces a method to compare sparse neural network topologies using graph theory.
problem Comparing and understanding sparse neural network topologies, especially during training.
method Introducing Neural Network Sparse Topology Distance (NNSTD) to measure distances between different sparse neural networks.
result Sparse neural networks can outperform over-parameterized models without further structure optimization.
The paper tackles sparse graph learning under Laplacian-related constraints, improving upon existing methods.
problem Learning a sparse undirected graph from multivariate data under Laplacian-related constraints.
method Modifications to penalized log-likelihood approaches to enforce total positivity and lasso/adaptive lasso penalties using ADMM.
result The proposed constrained adaptive lasso approach significantly outperforms existing Laplacian-based approaches.
Learning the "blocking" structure is a central challenge for high dimensional data (e.g., gene expression data). Recently, a sparse singular value decomposition (SVD) has been used as a biclustering tool to achieve this goal. However, this model ignores the structural information between variables (e.g., gene interacti…
Linear time algorithm for random walk kernels on sparse graphs.
problem Efficient computation of general random walk kernels for large graphs.
method Sample dependent random walks to compute graph embeddings without direct graph product.
result Up to 27x faster and scalable to 128x larger graphs than previous methods.
SGLDS models multivariate data with a sparse graph linking latent states.
problem Modeling sequential multivariate data with varying dynamics.
method Nonparametric Bayesian approach using a gamma process and Bernoulli-Poisson link.
result Demonstrates state-of-the-art performance on synthetic and real data.
Sparse RSP routing improves graph exploration and classification.
problem Optimal randomized routing and distance measures on weighted graphs.
method Tsallis divergence regularization for sparse RSP.
result Sparse random walk converges to least-cost graph as temperature decreases.
Kernel regression predicts graph signals in noisy environments.
problem Predicting smooth graph signals in the presence of sparse noise.
method Kernel regression with ℓ1-norm and ℓ2-norm optimization using IRLS. result Efficacy demonstrated on real-world temperature data.
HopGAT improves node classification in sparsely labeled graphs by learning from distant neighbors.
problem Classifying nodes in sparsely labeled graphs with limited labeled data.
method Hop-aware supervision mechanism and simulated annealing learning strategy.
result The model achieves high accuracy even with 40% labeled data, reducing performance loss to 3.9%.
New theory for partial disentanglement from sparse graphs.
problem Disentangling latent factors from sparse causal graphs.
method Generalization of disentanglement theory to any graph, using consistency equivalence.
result Partial disentanglement captures expected factor entanglement based on graph structure.
Detecting correlated trees helps align sparse graphs.
problem Detecting correlation between trees for sparse random graphs.
method MPAlign message-passing algorithm for graph alignment.
result MPAlign succeeds in polynomial time for partial alignment.
Designs interventions to learn causal graphs with minimum cost.
problem Learning causal graphs with minimum intervention cost.
method Prove NP-hardness, develop greedy and constrained algorithms.
result Achieve nearly optimal intervention design for sparse graphs.
ASAP improves graph pooling for hierarchical graph representations.
problem Pooling in graphs fails to effectively capture substructure or scale to large graphs.
method ASAP uses self-attention and modified GNN to capture node importance and learn sparse soft cluster assignments.
result Combining ASAP with GNN architectures leads to state-of-the-art results on graph classification benchmarks.
Sparse DNN challenge aims to improve graph data analysis.
problem Scalability issues in sparse data analysis.
method Mathematically defined DNN inference, vertex-centric and array-based implementations.
result Performance predictions based on simple hardware models.
Proposes RBGP framework for efficient block sparse neural networks.
problem Efficiently exploit structured sparsity patterns for sparse neural networks on GPU.
method Uses Ramanujan Bipartite Graph Product to generate structured multi-level block sparse neural networks.
result Achieves 5-9x and 2-5x runtime gains over unstructured and block sparsity patterns respectively, while maintaining accuracy.
We compute an approximate Fréchet mean for sets of sparse graphs.
problem Characterizing the location of a set of graphs in a metric space.
method We use the pseudometric defined by the ℓ₂ norm of eigenvalues of adjacency matrices.
result We describe an algorithm to approximate the Fréchet mean of a set of graphs.
New SRC algorithm for faster image recognition on graphs.
problem Image recognition on graphs with subspace assumptions.
method Sparse representation classifier with screening for graph classification.
result Consistent classification for random graphs, faster than original SRC.
Graph neural networks improve AMG convergence for sparse systems.
problem Efficiently constructing algebraic multigrid prolongation operators for sparse linear systems.
method Train a graph neural network to learn prolongation operators from matrix classes, using an unsupervised loss function.
result Improved convergence rates compared to classical AMG methods.
New algorithm efficiently learns sparse causal graphs from time series data.
problem Learning sparse causal graphs from time series data efficiently and automatically selecting the number of edges.
method Cyclical coordinate descent algorithm with two non-parametric error metrics for LASSO coefficient selection.
result State-of-the-art performance on simulated and real datasets.
Improved graph clustering for sparse graphs using non-backtracking random walks.
problem Improving graph clustering performance for sparse graphs.
method VEC-NBT uses a non-backtracking random walk to modify VEC, a graph embedding technique.
result VEC-NBT achieves comparable or greater accuracy with shorter walks than VEC for sparser graphs.
Improved community detection in sparse graphs using Bethe-Hessian matrix.
problem Community detection in sparse heterogeneous graphs.
method Spectral clustering based on the Bethe-Hessian matrix Hr for degree-corrected stochastic block models. result Clustering is insensitive to degree heterogeneity for r=ζ. A deep neural network framework for forecasting sparse spatio-temporal data.
problem Forecasting sparse spatio-temporal data with real-time interactions.
method Coupling self-exciting point process and graph structured recurrent neural network.
result More accurate real-time forecasting of crime and traffic data.
New method handles structural uncertainty in graphs better than existing models.
problem Handling heterophily and structural noise in semi-supervised learning on graphs.
method Sparse signed message passing network that models a posterior distribution over signed adjacency matrices.
result Our method outperforms strong baseline models on heterophilic benchmarks under both synthetic and real-world structural noise.
Network Lasso clusters sparse graph clusters efficiently.
problem Local graph clustering of sparse and chain-like clusters.
method Network Lasso minimizes total variation of cluster indicator signals.
result Network Lasso handles sparse clusters difficult for spectral clustering.
Originally designed to model text, topic modeling has become a powerful tool for uncovering latent structure in domains including medicine, finance, and vision. The goals for the model vary depending on the application: in some cases, the discovered topics may be used for prediction or some other downstream task. In ot…
MFCNs use sparse graphs to approximate manifold convergence.
problem Understanding manifold neural networks (MNNs).
method Sparse graph approximation for manifold convergence.
result Method converges to continuum limit as data points increase.