GraphZoom improves graph embedding accuracy and scalability.
problem Node attribute noise and scalability issues in graph embedding models.
method GraphZoom combines graph fusion and multi-level coarsening to improve accuracy and scalability.
result GraphZoom significantly increases classification accuracy and speeds up the embedding process.
A new method for solving complex sequential decision-making problems by decomposing them into multiple levels.
problem Sequential decision-making with natural multi-level structure.
method Multi-level meta-reinforcement learning with skill-based curriculum.
result Efficiently reduces stochasticity and policy search space, leading to fewer iterations and computations.
New graph coarsening method preserves GNN message-passing signals.
problem Preserving GNN message-passing on coarsened graphs.
method Proposed a new oriented message-passing operation for coarsened graphs.
result Improved node classification results compared to naive methods.
Unified framework for graph coarsening using node features and graph matrices.
problem Dimensionality reduction of large graphs while preserving node features.
method Optimization-based framework that unifies graph learning and dimensionality reduction.
result The learned coarsened graph is ε-similar to the original graph, where ε is a small positive number.
Paper introduces a taxonomy of reduction matrices for more efficient graph coarsening.
problem Efficiently reducing graph size while preserving important information.
method Introduces a more general notion of reduction matrix, not necessarily the pseudo-inverse of the lifting matrix.
result Reducing the Restricted Spectral Approximation (RSA) by modifying the reduction matrix.
Efficiently computes embeddings for large graphs using coarsening.
problem Inefficient computation of graph embeddings for large-scale graphs.
method Graph coarsening based on Schur complements and Gaussian elimination.
result Efficiently computed embeddings on coarsened graph match Schur complement embeddings in expectation.
How does coarsening affect the spectrum of a general graph? We provide conditions such that the principal eigenvalues and eigenspaces of a coarsened and original graph Laplacian matrices are close. The achieved approximation is shown to depend on standard graph-theoretic properties, such as the degree and eigenvalue di…
A new unsupervised method learns graph hierarchies using optimal transport.
problem Learning meaningful graph hierarchies without labeled data.
method Differentiable coarsening and optimal transport.
result OTCoarsening produces meaningful coarse graphs and competitive performance.
This study improves graph coarsening methods by preserving graph spectrum and distances.
problem Solving large-scale graph problems by working on a smaller graph.
method Developed a geometric approach using Gromov--Wasserstein distance to minimize the difference between graph distances and their coarsened versions.
result Minimizing the difference between graph distances and their coarsened versions can be achieved using the weighted kernel K-means method. Study intersection homotopy groups in coarsenings of CS sets.
problem Understanding invariance of intersection homotopy groups in coarsenings of CS sets.
method Introduced a general perversity and its pushforward, established invariance theorems for intersection homotopy groups in coarsenings of CS sets.
result Found invariance theorems for intersection homotopy groups in coarsenings of CS sets.
Paper improves GNN inference speed and memory usage.
problem Scalability issues in GNNs during inference.
method Graph coarsening techniques for faster inference.
result Significant reduction in inference time and memory usage.
New estimators improve efficiency in two-phase designs with coarsened data.
problem Efficient estimation in two-phase designs with incomplete data.
method Developed new estimators within the TMLE framework.
result New estimators are asymptotically equivalent and more efficient.
A novel algorithm for unsupervised graph representation learning combining coarsening and mutual information maximization.
problem Current limitations in unsupervised graph representation learning, especially in embedding new graphs and considering both micro- and macro-structures.
method Combines coarsening with mutual information maximization to produce high-quality embeddings.
result The algorithm produces high-quality embeddings that are competitive with state-of-the-art methods.
We consider the problem of statistical inference for ranking data, specifically rank aggregation, under the assumption that samples are incomplete in the sense of not comprising all choice alternatives. In contrast to most existing methods, we explicitly model the process of turning a full ranking into an incomplete on…
New algorithm trains binary-activation, multi-level RNNs for noise-resilient, ADC-/DAC-free PIM inference.
problem Training noise-resilient, ADC-/DAC-free neural networks.
method Binary activations and multi-level weights for eNVM-based processing-in-memory circuits.
result Higher accuracy and noise resilience for recurrent networks compared to existing methods.
New method reduces spatial graphs while preserving their topological features.
problem Finding a smaller spatial graph with the same structure.
method Topological spatial graph coarsening approach based on triangle-aware graph filtration.
result Significant reduction in graph size while preserving topological information.
3D object recognition accuracy can be improved by learning the multi-scale spatial features from 3D spatial geometric representations of objects such as point clouds, 3D models, surfaces, and RGB-D data. Current deep learning approaches learn such features either using structured data representations (voxel grids and o…
Improved graph clustering with modularity and coarsening for attributes and communities.
problem Inaccurate community detection and computational inefficiency in graph clustering.
method Integrates coarsening and modularity maximization, using a loss function with log-determinant, smoothness, and modularity components.
result Superior clustering outcomes, proven consistent under DC-SBM, and efficient algorithm integration with GNNs and VGAEs.
PASCO speeds up graph clustering for large graphs.
problem Efficiently clustering large graphs with many communities.
method Overlay method combining coarsening and parallel clustering.
result PASCO accelerates clustering with improved efficiency and quality.
New method for valid prediction intervals with coarsened data.
problem Handling missing data and censored outcomes in training samples.
method Multiply robust conformal risk control with semiparametric theory.
result Stronger coverage properties under covariate shift.
The paper tackles multi-level fairness in algorithmic systems, addressing bias at both individual and structural levels.
problem Algorithmic systems can unfairly impact marginalized groups, especially when considering only individual-level bias.
method Formalizes multi-level fairness using causal inference tools, addressing effects of sensitive attributes at multiple levels.
result Illustrates the importance of accounting for macro-level sensitive attributes in fairness assessments.
NDP improves GNN efficiency by coarsening graphs without losing structure.
problem Efficiently summarize graph data for deep learning models.
method Node Decimation Pooling (NDP) reduces graph density while preserving topology.
result NDP achieves comparable performance to state-of-the-art pooling methods but with improved efficiency.
CoSimGNN improves graph similarity computation for large graphs.
problem Efficiently computing graph similarity scores for large graphs.
method Embedding-coarsening-matching framework with adaptive pooling and fine-grained interactions.
result CoSimGNN achieves best performance in graph similarity computation.
Paper uses Shapley values to identify key confounders in product funnel data.
problem Identifying important confounders in product funnel data.
method Applies Shapley values for scalable coarsened exact matching.
result Shapley values provide robust importance-ranking for confounders.
New methods for handling confounding in observational studies.
problem Handling confounding variables in observational studies.
method Generalized coarsened procedures for clustering confounding variables, followed by estimation of treatment effects and variance.
result Developed a general asymptotic framework for the average causal effect estimator and variance formulae.
Study recovers community structure from coarse graph measurements.
problem Community recovery from low-resolution graph measurements.
method Formalized coarsening process of graph measurements, developed conditions for perfect recovery.
result Simple and closed-form asymptotic conditions for perfect recovery of coarse graph communities.
This paper proposes a method to improve few-shot learning by generating multi-level weight-centric features.
problem Improving few-shot learning performance by leveraging both representation power and weight generation capacity.
method A multi-level weight-centric feature learning approach with a weight-centric training strategy and multi-level feature incorporation.
result Significantly outperforms existing methods in low-shot classification benchmarks.
We introduce in this paper a new way of optimizing the natural extension of the quantization error using in k-means clustering to dissimilarity data. The proposed method is based on hierarchical clustering analysis combined with multi-level heuristic refinement. The method is computationally efficient and achieves bett…
This thesis explores GNNs, categorizing them into local and global approaches.
problem Understanding the convergence of global GNNs and connecting local and global approaches.
method Categorization of GNNs into local and global, study of Invariant Graph Networks, connecting local and global approaches, and using local MPNN for graph coarsening.
result Established a connection between local and global GNN approaches.
We propose a multi-level method to increase the accuracy of machine learning algorithms for approximating observables in scientific computing, particularly those that arise in systems modeled by differential equations. The algorithm relies on judiciously combining a large number of computationally cheap training data o…
New algorithm tackles self-selection bias in estimating linear regressors.
problem Estimating k linear regressors with self-selection bias in d dimensions. method First local convergence algorithm for self-selection, reducing to coarsening problem.
result Improves running time of previous algorithms by a poly(d, k, 1/ε) factor.
New algorithms solve complex multi-level optimization problems with improved efficiency.
problem Smooth stochastic multi-level composition optimization problems.
method Two algorithms using moving-average and linearized stochastic estimates.
result Achieved sample complexities of O(1/ε^4) and O(1/ε^6).
PFPN improves salient object detection by progressively polishing multi-level features.
problem Improving salient object detection by refining multi-level features.
method Progressive Feature Polishing Network (PFPN) with Feature Polishing Modules (FPMs).
result PFPN achieves superior performance on five benchmark datasets without post-processing.
A distributed SGD method for heterogeneous networks with hubs and workers.
problem Learning in heterogeneous multi-level networks with worker heterogeneity and varying communication.
method Multi-Level Local SGD: distributed SGD with hub-and-spoke paradigm and hub averaging.
result The method converges with error dependent on worker heterogeneity, hub network topology, and iterations.
Paper proposes a deep subspace clustering method using multi-level representations.
problem Deep subspace clustering of images.
method Convolutional autoencoders with multiple fully-connected layers for multi-level representations, loss minimization with iterative updates.
result The method outperforms state-of-the-art methods on real-world datasets.
Paper creates transparent, safe synthetic data from coarsened margins.
problem Creating synthetic data that maintains original relationships and is safe from disclosure.
method Defining and curating margins, applying SDC, coarsening counts, and using IPF algorithm.
result Synthetic data derived from safe, coarsened margins maintains original relationships.
This paper tackles tensor recovery from noisy and multi-level quantized measurements.
problem Tensors from multi-level quantized measurements.
method Nonconvex optimization problem with alternating proximal gradient descent.
result The recovery error diminishes to zero with increasing tensor dimensions.
Efficient memory layer improves graph neural networks for graph classification and regression.
problem Efficiently learning node representations and graph coarsening for arbitrary graph topology.
method Introduces a memory layer for GNNs that learns node representations and graph coarsening, and two new networks: MemGNN and GMN.
result Proposed models achieve state-of-the-art results in graph classification and regression benchmarks.
The web link selection problem is to select a small subset of web links from a large web link pool, and to place the selected links on a web page that can only accommodate a limited number of links, e.g., advertisements, recommendations, or news feeds. Despite the long concerned click-through rate which reflects the at…
While recommendation systems generally observe user behavior passively, there has been an increased interest in directly querying users to learn their specific preferences. In such settings, considering queries at different levels of granularity to optimize user information acquisition is crucial to efficiently providi…
Optimal gradient quantization reduces communication costs in distributed deep learning.
problem High communication costs in distributed training of deep neural networks.
method Deduced optimal gradient quantization conditions for binary and multi-level quantization, developed novel schemes for dynamic quantization levels.
result Demonstrated superior performance of proposed quantization schemes on CIFAR and ImageNet datasets.
New framework estimates target functions from incomplete data.
problem Estimating target functions from partially observed data.
method IF-learning framework using influence functions.
result Two learning algorithms developed for estimation.
In rank aggregation (RA), a collection of preferences from different users are summarized into a total order under the assumption of homogeneity of users. Model misspecification in RA arises since the homogeneity assumption fails to be satisfied in the complex real-world situation. Existing robust RAs usually resort to…
In this article we propose a novel approach to reduce the computational complexity of various approximation methods for pricing discrete time American options. Given a sequence of continuation values estimates corresponding to different levels of spatial approximation and time discretization, we propose a multi-level l…
New method reduces confidence interval sizes for causal inference.
problem Inaccurate propensity scores and extreme scores cause large confidence intervals.
method Data-dependent Coarse IPW (CIPW) estimators.
result Robust CIPW estimators reduce confidence interval sizes to ε+1/√n.
Enhances social spam detection using multi-level dependency of relational sequences.
problem Social spam detection in multi-relation social networks.
method Developed the Multi-level Dependency Model (MDM) to exploit long-term and short-term dependencies in user relational sequences.
result MDM improves social spam detection accuracy on a real-world multi-relational social network.
Paper introduces a VAE-based framework for multi-level Granger-causal learning.
problem Capturing lead-lag relationships in related dynamical systems.
method Variational Autoencoder (VAE) framework for joint learning.
result Framework handles shared and individual system structures.
COLUMBUS discovers new features to improve domain generalization.
problem Improving machine learning models' ability to generalize to unseen domains.
method COLUMBUS uses targeted corruption of input and multi-level representations to discover new features.
result COLUMBUS achieves state-of-the-art performance on DG benchmarks.