A new method improves graph node embeddings by considering both nearby and distant node similarities.
problem Improving graph node embeddings by considering both nearby and distant node similarities.
method Distance-aware Negative Sampling (DNS) which maximizes cohesion at nearby node-pairs and separation at distant node-pairs.
result DNS outperforms baseline methods in downstream node classification tasks on various datasets and GRL algorithms.
New sampling methods improve node embedding efficiency.
problem Efficiency and scalability in node embedding methods.
method Sampling approaches to node embedding, modeling eigenvectors and feature vectors.
result Improved computational efficiency and scalability.
A new model for graph sampling that preserves structure without explicit targeting.
problem Graphs are often not fully representative of true relationships, leading to biased machine learning models.
method Node copying model: randomly replaces each node's neighbors with those of a randomly sampled similar node.
result The model achieves higher accuracy in node classification and mitigates adversarial attacks.
This research improves graph embeddings by optimizing node sampling with centrality weights.
problem Improving the accuracy and efficiency of graph embeddings using Skip-Gram methods.
method Implemented and analyzed four graph embedding techniques with different centrality-weighted sampling distributions.
result Centrality-weighted sampling leads to improved accuracy and faster learning times.
LADIES improves GCN training efficiency and accuracy for large graphs.
problem Training large graph convolutional networks (GCNs) is computationally expensive.
method LADIES uses layer-dependent importance sampling to select nodes for training.
result LADIES outperforms previous methods in both time and memory efficiency.
A new data-driven sampling method improves GraphSAGE's accuracy in node classification.
problem High variance in neighborhood sampling leads to sub-optimum accuracy in GraphSAGE.
method A data-driven node sampling approach using a non-linear regressor trained with reinforcement learning.
result Enhanced GraphSAGE accuracy in inductive node classification benchmarks.
Improves GCN by sampling neighbors and features for better node representation.
problem GCN's aggregation process treats all neighbors and features equally, leading to suboptimal node representations.
method Introduces a new convolution operation on feature maps constructed from a fixed node bandwidth, then passes to a standard GCN.
result Outperforms competing methods in semi-supervised node classification tasks.
BLISS optimizes GNN training by adaptively sampling nodes.
problem High computational costs in training GNNs on large graphs.
method Uses Bandit Layer Importance Sampling to dynamically select nodes.
result Improves GNN performance with reduced computational cost.
A graph-based method for two-sample testing across connected nodes.
problem Identifying nodes where two probability distributions differ significantly.
method Collaborative non-parametric two-sample testing (CTST) framework.
result CTST outperforms independent node tests by leveraging graph structure.
Efficient algorithm removes redundant nodes and obsolete samples in machine learning.
problem Pruning redundant nodes and removing obsolete training samples in machine learning.
method Deduced decremented learning algorithms from incremental learning algorithms, using inverse Cholesterol factor and unitary transformation.
result Proposed decremented learning algorithms efficiently prune redundant nodes and remove obsolete training samples.
GraphVite efficiently trains node embeddings for large networks.
problem Scaling node embedding algorithms to handle large networks (tens of millions of nodes).
method CPU-GPU hybrid system with parallel edge sampling and negative sampling.
result GraphVite achieves high performance (50x faster) for large networks.
In this paper, we study the problem of structure learning for Bayesian networks in which nodes take discrete values. The problem is NP-hard in general but we show that under certain conditions we can recover the true structure of a Bayesian network with sufficient number of samples. We develop a mathematical model whic…
The paper studies a method to sample nodes from a massive graph using personalized PageRank.
problem Sampling from a massive network is expensive and impractical; the paper provides an alternative.
method The paper introduces a crawling method to approximate the personalized PageRank vector without querying the entire graph.
result The adjusted personalized PageRank vector can effectively select nodes within the same block as the seed node.
This paper proposes a novel type of random forests called a denoising random forests that are robust against noises contained in test samples. Such noise-corrupted samples cause serious damage to the estimation performances of random forests, since unexpected child nodes are often selected and the leaf nodes that the i…
This work shows dimension regularization can replace skip-gram negative sampling for graph embeddings, improving efficiency and performance.
problem Efficiently enforcing dissimilarity among node embeddings in graph learning.
method Dimension regularization as an alternative to skip-gram negative sampling.
result Dimension regularization is a more efficient approach to enforcing dissimilarity in graph embeddings.
A new algorithm improves sample complexity for thresholding in Monte Carlo Tree Search.
problem Determining if the root node value of a tree is at least a given threshold.
method Developed a δ-correct sequential sampling algorithm based on the Track-and-Stop strategy.
result Ratio-based modification of D-Tracking strategy reduces sample complexity and computational cost.
GraphSAC detects anomalies in large graphs by sampling and filtering node subsets.
problem Vulnerability of holistic anomaly detection methods to compromised nodal attributes and network links.
method Randomly draws subsets of nodes, filters out contaminated sets, and uses SSL to estimate nominal label distributions.
result GraphSAC provides performance guarantees and is scalable to large graphs.
New insights into negative sampling for graph representation learning.
problem Challenges in generating high-quality graph representations for large node sets.
method Theoretical analysis and derivation of negative sampling distribution correlation, proposing MCNS method.
result The negative sampling distribution should be positively but sub-linearly correlated to the positive sampling distribution.
Boost GNNs for node classification by incorporating label dependencies.
problem Current GNNs lack expressiveness and fail to capture label dependencies.
method Proposes a collective learning framework combining collective classification and self-supervised learning.
result Consistent, significant improvement in node classification accuracy across various GNNs.
A method to control results of gradient descent unsupervised learning in a deep neural network by using evolutionary algorithm is proposed. To process crossover of unsupervisedly trained models, the algorithm evaluates pointwise fitness of individual nodes in neural network. Labeled training data is randomly sampled an…
Laplacian matrix helps in reducing data dimensions and clustering.
problem Representing and clustering data using graphs and matrices.
method Using the Laplacian matrix to assign values to nodes based on their connectivity.
result The Laplacian matrix can be used to find a good embedding of data in a low-dimensional space and perform clustering.
Kernel interpolation improved with continuous volume sampling.
problem Approximating functions from RKHS using weighted sums of kernel translates.
method Continuous volume sampling for choosing node locations.
result Proved almost optimal bounds for interpolation and quadrature under VS.
New method speeds up GNNs to constant time.
problem Scaling GNNs to large graphs.
method Analyzing uniform node sampling for GNNs.
result Node sampling complexity is constant, independent of graph size.
A novel GNN architecture improves link prediction by combining positive and negative samples.
problem Link prediction accuracy limited by node-wise methods and increased model complexity of edge-wise methods.
method Proposes a novel GNN architecture that uses both positive and negative samples to inform node embeddings.
result The method retains the inference speed of node-wise models while achieving competitive accuracy with edge-wise alternatives.
GCN-LASE incorporates link attributes in graph convolutional networks.
problem Ignoring link attributes in GCNs limits their performance.
method Proposes GCN-LASE, incorporating both node and link attributes, using tensor product of link attributes as neighbor features, and estimating feature sums through Monte Carlo sampling.
result GCN-LASE outperforms strong baselines on various graph datasets.
Study on learning sparse fixed-structure Gaussian Bayesian networks with near-optimal sample complexity.
problem Learning a fixed-structure Gaussian Bayesian network up to a bounded error in total variation distance.
method Analysis of node-wise least squares regression and introduction of BatchAvgLeastSquares and CauchyEst algorithms.
result BatchAvgLeastSquares and CauchyEstTree have near-optimal sample complexity.
GATs improve node regression on noisy graphs with provable advantage.
problem Improving node regression on graphs with noisy covariates and edges.
method Proposes a GAT designed for denoising proxy features in node regression.
result GAT achieves lower error in estimating regression coefficient and predicting responses.
We present a new Markov chain Monte Carlo method for estimating posterior probabilities of structural features in Bayesian networks. The method draws samples from the posterior distribution of partial orders on the nodes; for each sampled partial order, the conditional probabilities of interest are computed exactly. We…
Enhances GNNs by capturing node relationships, outperforming 2-WL test.
problem Inability of conventional GNNs to fully capture node relationships due to permutation invariance.
method Develops permutation-sensitive aggregation mechanism using permutation groups.
result Proves superior expressivity compared to 2-WL test and not less than 3-WL test.
Policy-GNN optimizes GNN aggregation for diverse node iterations.
problem Optimizing GNN performance by varying aggregation iterations for different nodes.
method Policy-GNN uses a meta-policy framework with deep reinforcement learning to adaptively determine the number of aggregations for each node.
result Policy-GNN significantly outperforms state-of-the-art alternatives on real-world datasets.
Network embedding algorithms are able to learn latent feature representations of nodes, transforming networks into lower dimensional vector representations. Typical key applications, which have effectively been addressed using network embeddings, include link prediction, multilabel classification and community detectio…
Link prediction in networks is typically accomplished by estimating or ranking the probabilities of edges for all pairs of nodes. In practice, especially for social networks, the data are often collected by egocentric sampling, which means selecting a subset of nodes and recording all of their edges. This sampling mech…
Polynomial-time algorithm for near-optimal community detection in graphs.
problem Node-private community estimation in stochastic block models.
method Explicit Lipschitz surrogate and accept-reject algorithm for sampling community labels.
result Achieves minimax rates for exact recovery with polynomial-time runtime and logarithmic privacy parameter.
P-GNNs learn node embeddings considering node positions in graphs.
problem Capturing node positions in graph structures.
method Samples anchor nodes, computes distances, and learns weighted aggregation.
result P-GNNs outperform state-of-the-art GNNs in link prediction and community detection.
Low-dimensional embeddings of nodes in large graphs have proved extremely useful in a variety of prediction tasks, from content recommendation to identifying protein functions. However, most existing approaches require that all nodes in the graph are present during training of the embeddings; these previous approaches …
Unified theory linking node embeddings and graph representations.
problem Clarifying the relationship between node embeddings and graph representations.
method Using invariant theory, the paper establishes a theoretical framework bridging node embeddings and structural graph representations.
result Proves equivalence between node embeddings and structural graph representations, showing they are interchangeable for various tasks.
Simple algorithm samples graph nodes efficiently.
problem Sampling representative nodes from large graphs efficiently.
method Minimum inner product greedy selection rule, column-selective sampling.
result Achieves sampling proportional to cluster size, error decays with inter-cluster connectivity.
Bayesian Optimization for graph node subset functions.
problem Optimizing functions over node subsets in graphs.
method Bayesian Optimization framework for combinatorial optimization on graphs.
result Effectiveness of the proposed BO framework on various graph types and tasks.
Proposes BGCN-NRWS for semi-supervised node classification with reduced overfitting.
problem Uncertainty in graph structure for semi-supervised node classification.
method Bayesian Graph Convolutional Network using Neighborhood Random Walk Sampling (BGCN-NRWS) with MCMC graph sampling and variational inference.
result Consistently competitive classification results compared to state-of-the-art.
This paper improves signal reconstruction using determinantal sampling from random nodes.
problem Approximating square-integrable functions from random node evaluations.
method Combines determinantal point processes and mixtures thereof for RKHS-adapted approximations.
result Proves mean-square guarantees in L2 norm and shows faster convergence rates. We consider the problem of learning classifiers for labeled data that has been distributed across several nodes. Our goal is to find a single classifier, with small approximation error, across all datasets while minimizing the communication between nodes. This setting models real-world communication bottlenecks in the …
Study examines consistent graph recovery from partial network data.
problem Consistent graph recovery from partially observed diffusion networks.
method Developed estimators for combination matrix under partial observability.
result Node degrees' statistical concentration enables consistent graph learning.
The present work deals with active sampling of graph nodes representing training data for binary classification. The graph may be given or constructed using similarity measures among nodal features. Leveraging the graph for classification builds on the premise that labels across neighboring nodes are correlated accordi…
DrGCN improves GCNs by addressing dimensional imbalance.
problem Dimensional imbalance in node representations of graphs.
method Dimensional reweighting method combined with GCN.
result DrGCN improves GCNs' stability and outperforms existing models.
We propose a new yet natural algorithm for learning the graph structure of general discrete graphical models (a.k.a. Markov random fields) from samples. Our algorithm finds the neighborhood of a node by sequentially adding nodes that produce the largest reduction in empirical conditional entropy; it is greedy in the se…
RL automates sensor configuration for energy harvesting IoT nodes.
problem Manual or heuristic configuration of energy harvesting sensors is inefficient and requires domain expertise.
method Reinforcement Learning (RL) to automate and optimize sensor configuration.
result RL can effectively learn and configure sensor sampling rates for optimal energy use and node operation.
HighwayGraph models long-distance node relations in GNNs with improved performance.
problem Limited-layer information propagation in GNNs hinders long-distance node relation modeling.
method Proposes two solutions: implicit and explicit modeling of long-distance node relations using shallow GNN architectures and a self-training framework.
result HighwayGraph achieves consistent and significant improvements over four GNNs on three benchmark datasets.
Causal discovery from empirical data is a fundamental problem in many scientific domains. Observational data allows for identifiability only up to Markov equivalence class. In this paper we first propose a polynomial time algorithm for learning the exact correctly-oriented structure of the transitive reduction of any c…