Urban2Vec combines street view imagery and POIs for better urban neighborhood embeddings.
problem Lack of comprehensive representation of urban neighborhoods using heterogeneous data.
method Unsupervised multi-modal framework using CNN for visual features and bag-of-words for POI data.
result Urban2Vec achieves better performance than baseline models and comparable to fully-supervised methods.
A new method encodes data structure from neighborhood-similarity graphs without bias.
problem Distortion and bias in high-dimensional data analysis.
method Directly encodes data point neighborhood similarities as a sparse graph, avoiding assumptions and iterative schemes.
result Efficacy demonstrated in natural and synthetic data applications.
Proposes robust local scaling using conditional quantiles of graph similarities.
problem Spectral analysis sensitivity to parameters and noise.
method Auto-encoding neural network for inferring conditional quantiles of similarity functions.
result Proposed approach outperforms existing methods in spectral clustering and single-example label propagation.
NSL layer improves convolutional networks' ability to recognize novel appearances.
problem Convolutional networks struggle with recognizing novel appearances not seen in training data.
method NSL layer uses neighborhood similarity to induce appearance invariance.
result NSL layer enhances network's ability to generalize to novel appearances.
SNG-DBSCAN clusters data faster with subsampled similarity queries.
problem Efficiently clustering large datasets with DBSCAN's high complexity.
method Subsampled ε-neighborhood graph for similarity queries. result Subsampling 0.1% of the graph leads to 200x speedup and 250x RAM reduction. NNK algorithm improves neighborhood and graph construction for machine learning.
problem Ad hoc selection of k and ε parameters in kNN and ε-neighborhood methods.
method NNK algorithm for better sparse signal approximation.
result NNK leads to superior performance in local neighborhood and graph-based machine learning tasks.
Embed nodes with multi-scale attributes for robust network analysis.
problem Capturing complex node attributes across different scales.
method Multi-scale attributed node embedding (AE & MUSAE) using Skip-gram approach.
result Proves node-feature mutual information is implicitly factorized by embeddings.
Proposes multi-neighborhood LBPs for land use classification.
problem Challenges in classifying land use images due to intra class variability and inter class similarities.
method Uses multi-neighborhood LBPs combined with nearest neighbor classifier.
result Achieved an accuracy of 77.76% on UC Merced 21 class land use image dataset.
Neural networks fail to bridge modalities as expected.
problem Understanding how well neural networks map between different modalities.
method Proposed a new similarity measure and conducted experiments on cross-modal benchmarks.
result Predicted vectors do not resemble the target vectors' neighborhood structure.
Inspired by a work of Kapranov, we define the notion of Dolbeault complex of the formal neighborhood of a closed embedding of complex manifolds. This construction allows us to study coherent sheaves over the formal neighborhood via complex analytic approach, as in the case of usual complex manifolds and their Dolbeault…
Paper proposes SVM-based methods for inferring interaction networks.
problem Modeling interaction between variables in time series and high dimensions.
method Two approaches: neighborhood SVM and restricted Bayesian network for time series.
result Efficiency demonstrated through simulations with linear and nonlinear data.
Proposes a new NMF method incorporating neighborhood structure for better anomaly detection.
problem NMF's inability to incorporate neighborhood structure information limits its performance in nonlinear manifold structures.
method Integrates neighborhood structure information using Minimum Spanning Tree (MST) within NMF framework.
result Empirical results show superior performance in anomaly detection using the proposed method.
LPL optimizes embeddings to align local neighborhoods, improving cross-lingual word alignment.
problem Aligning embeddings across different datasets and languages.
method Locality Preserving Loss (LPL) optimizes model to project embeddings while maintaining local neighborhoods and aligning them.
result LPL-based alignment leads to better and consistent accuracy, especially in small training set settings.
GraphWave learns node embeddings from graph neighborhoods without manual feature selection.
problem Learning structural node representations in graphs is challenging.
method GraphWave uses heat wavelet diffusion patterns to learn low-dimensional node embeddings.
result Nodes with similar network neighborhoods have similar GraphWave embeddings.
This paper sets a lower limit for the size of Weinstein's Lagrangian tubular neighborhoods.
problem Finding the minimum size of Weinstein's Lagrangian tubular neighborhoods.
method Using the curvature tensor and second fundamental form of the submanifold.
result Explicit lower bounds for the radii of tubular neighborhoods are derived.
GCNs learn by embedding similar nodes within a class and leveraging consistent neighborhood structures.
problem Understanding how GCNs perform semi-supervised node classification on both homophilous and heterophilous graphs.
method Investigated the latent node embeddings and neighborhood structures of GCNs.
result GCNs learn by embedding similar nodes within a class and leveraging consistent neighborhood structures.
New method pools labels from similar data items to improve learning from small samples.
problem Learning from small, human-annotated samples with potential disagreement among annotators.
method Proposes neighborhood-based pooling for sharing labels across similar data items.
result Improves learning from small, noisy samples by pooling labels from similar items.
Mathematical analysis of SNE and t-SNE for dimension reduction.
problem Optimal mapping of high-dimensional data to low dimensions.
method Gradient flow of relative entropy to minimize the distance between points.
result The diameter of the evolving sets remains bounded for SNE but may blow up for t-SNE.
The study clusters neighborhoods based on childhood vulnerability data and program retention rates.
problem Improving childhood outcomes and decision-making in early childhood development.
method Data-driven approaches combining public and private sources to visualize children's experiences and analyze program retention rates.
result Neighborhoods can be clustered based on childhood vulnerability, and certain programs have higher retention rates.
Finding relationships between multiple views of data is essential both for exploratory analysis and as pre-processing for predictive tasks. A prominent approach is to apply variants of Canonical Correlation Analysis (CCA), a classical method seeking correlated components between views. The basic CCA is restricted to ma…
GCNs improve regression tasks by aggregating neighbor signals.
problem GCNs' statistical properties in regression tasks are poorly understood.
method Examined two GCN convolutions and their impact on learning error.
result GCNs have a bias-variance trade-off that depends on neighborhood size and topology.
Develops an ordinal-similarity framework for scalable and interpretable representation alignment.
problem Measuring representation similarity in large datasets.
method Triplet and Quadruplet Similarity Indices.
result Demonstrates inherent interpretability, robustness to outliers, and computational efficiency.
In this paper, using similar idea as in Fukaya-Oh's work ([9]), we devise a method to compute the Fukaya category of certain exact symplectic manifolds by reducing it to the corresponding Morse category of non-Hausdorff manifold as perturbation of the Lagrangian skeleton of the exact symplectic manifold.
GraphReach improves GNN performance by incorporating node positions.
problem Existing GNNs fail to capture node positions, leading to inaccurate predictions.
method GraphReach uses reachability estimations from anchor nodes to capture global node positions.
result GraphReach achieves up to 40% relative improvement in accuracy compared to state-of-the-art GNNs.
Smooth flow around a helix, extending previous circle solution.
problem Constructing smooth Euler flows near helical shapes.
method Generalization of a previous circle solution approach.
result Smooth flow supported near a helix.
The paper explores similarities in even and odd-dimensional geometry.
problem Understanding the Lagrangian Grassmannian in cosymplectic geometry.
method Study of compatible co-complex structures, Moser's trick, and Weinstein 1-form derivation.
result The de Rham class of the Weinstein 1-form is a co-flux.
Paper operationalizes individual fairness using side-information and a unified representation.
problem Difficulty in eliciting a human specification of a similarity metric for individual fairness.
method Proposes a Pairwise Fair Representation (PFR) model that learns from fairness graph and side-information.
result Unified PFR model effectively operationalizes individual fairness without human specification.
Proposes NRS to find flat minima in deep neural networks.
problem Finding optimal solutions in deep neural networks with overparameterization.
method NRS leverages the concept of flat minima and uses Kullback-Leibler divergence to regularize the neighborhood region in weight space.
result NRS drives optimizers towards flat minima, improving generalization ability across various model architectures.
Introduces Fock bundles for studying surface group character varieties.
problem Character varieties of surface groups without fixed complex structures.
method Introduces Fock bundles as smooth principal bundles with special adjoint-valued 1-forms, constructs canonical connections, and solves non-linear PDEs.
result Explicit solutions for Fock bundles in the Fuchsian locus map to the Hitchin component.
A new GCN model learns higher-order neighbors without explicit adjacency matrix computation.
problem GCN's performance drops for deeper structures due to limited neighborhood information.
method Assumes higher-order neighbors are similar to first-order neighbors, learns weights through Lasso to minimize feature loss.
result HWGCN achieves state-of-the-art results on various datasets.
GraLSP improves graph neural networks by incorporating local structural patterns.
problem GNNs struggle with identifying common structural patterns in graphs.
method GraLSP uses random anonymous walks to capture local graph structures and incorporates these into feature aggregation mechanisms.
result GraLSP outperforms other models in various prediction tasks on multiple datasets.
The paper bounds eigenvalues of hyperbolic manifolds with infinite volume.
problem Bounding eigenvalues of geometrically finite hyperbolic manifolds of infinite volume.
method Provided a lower bound on the kth eigenvalue of the Laplace-Beltrami operator by the kth eigenvalue of a neighborhood of the thick part of the convex core.
result Recovered a theorem bounding the bottom eigenvalue from below by a specific formula involving the volume of the 1-neighborhood of the convex core.
In many scientific disciplines structures in high-dimensional data have to be found, e.g., in stellar spectra, in genome data, or in face recognition tasks. In this work we present a novel approach to non-linear dimensionality reduction. It is based on fitting K-nearest neighbor regression to the unsupervised regressio…
A new method for efficient structural node embeddings using Von Neumann entropy.
problem Efficiently identifying structurally equivalent nodes in complex networks.
method VNEstruct: a simple approach generating low-dimensional structural node embeddings using Von Neumann entropy.
result VNEstruct achieves robustness on structural role identification and state-of-the-art performance on graph classification tasks.
This research improves classification performance by learning a distance metric from balanced data.
problem Data imbalance in learning methods.
method Extracts a low-dimensional manifold, learns local neighborhood relationships, and optimizes distance metric.
result The proposed method outperforms other approaches, especially in imbalanced datasets.
Geotagged data can be used to describe regions in the world and discover local themes. However, not all data produced within a region is necessarily specifically descriptive of that area. To surface the content that is characteristic for a region, we present the geographical hierarchy model (GHM), a probabilistic model…
We prove 3-dimensional hyperbolic cone-manifolds are geometrically inflexible: a cone-deformation of a hyperbolic cone-manifold determines a bi-Lipschitz diffeomorphism between initial and terminal manifolds in the deformation in the complement of a standard tubular neighborhood of the cone-locus whose pointwise bi-Lip…
This paper improves forecasts for diverse time series by averaging similar ones.
problem Forecasting challenges in heterogeneous time series.
method Dynamic Time Warping to find similar time series, k-Nearest Neighbor averaging.
result Averaging improves forecasts of simple models.
Study quantifies pedestrian traffic patterns in NYC.
problem Understanding pedestrian traffic dynamics in urban areas.
method Publicly available traffic camera data in NYC, time series analysis.
result Pedestrian traffic exhibits diurnal patterns with weekday peaks and no peak on weekends.
Meta-Neighborhoods adapts predictions based on input neighborhoods.
problem Adaptive prediction based on input neighborhoods for AI.
method Semi-parametric method with induced neighborhoods and meta-learning.
result Meta-Neighborhoods more accurately represents predictive distributions.
Paper proposes a new word embedding method optimizing word similarity.
problem Optimizing word similarity in embedding space.
method Two-step random walks between words via topics to learn an optimal embedding simplex.
result Our method outperforms existing approaches in various queries.
PGRec improves recommendation by modeling user-item preferences as a graph and embedding it for better predictions.
problem Sparse user-item data in recommender systems.
method PGRec models user-item preferences as a PrefGraph, then uses deep learning and factorization to embed and predict user preferences.
result PGRec outperforms state-of-the-art methods by up to 3.2% in NDCG@10.
DGCNN improves graph CNNs by handling irregular graphs.
problem Handling structural information loss and redundancy in graph CNNs.
method Proposes DGCNN using DGCL with mixed Gaussian model to handle irregular graphs.
result DGCNN outperforms state-of-the-art methods in graph classification and retrieval.
Data poisoning attacks can fool neighborhood-based recommender systems.
problem Robustness of neighborhood-based recommender systems to data poisoning attacks.
method Proposed a novel data poisoning attack framework (UNAttack) to fool the systems.
result Neighborhood-based recommender systems can be easily fooled by well-designed fake users.
GNNs may be limited by graph topology, affecting their learning outcomes.
problem Understanding how graph topology influences GNN behavior and performance.
method Investigating the interaction between local topological features and GNN message-passing schemes.
result Locally similar neighborhoods can lead to consistent node representations, affecting GNN performance.
We derive spectral sequences for the intersection homology of stratified fibrations and approximate tubular neighborhoods in manifold stratified spaces. These neighborhoods include regular neighborhoods in PL stratified spaces.
Defense against user shilling attacks in collaborative filtering using edge reweighting.
problem Vulnerability of collaborative filtering to profile injection attacks.
method Adversarial robustness based edge reweighting to attenuate non-robust edges.
result Effective defense against various types of attacks demonstrated through experiments.
Paper improves SOMs for non-Euclidean data modeling.
problem Traditional SOMs assume Euclidean data, limiting their applicability.
method Introduces topology-related extensions to traditional SOM algorithm.
result Improves SOMs for non-Euclidean data, enhancing data modeling.