Graphs are ubiquitous real-world data structures, and generative models that approximate distributions over graphs and derive new samples from them have significant importance. Among the known challenges in graph generation tasks, scalability handling of large graphs and datasets is one of the most important for practi…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,878 papers · 148 categories
Trend · papers per month
48 results for “scalable generative models”
Scalable method bounds Lipschitz constant of generative models.
problem Bounding the Lipschitz constant of generative models.
method Layerwise convex approximations using zonotopes.
result Efficient and tight bounds on generative models.
Towards Scalable Meta-Learning of near-optimal Interpretable Models via Synthetic Model Generationscs.LG
Meta-learning interpretable decision trees with synthetic data.
problem Lack of efficient, scalable methods for generating synthetic data for decision tree meta-learning.
method Synthetic generation of near-optimal decision trees using the MetaTree transformer architecture.
result Meta-learning of decision trees achieves performance comparable to real-world data or optimal decision trees, with significant computational cost reduction.
SCALOR learns scalable object representations for crowded scenes.
problem Scalability in scenes with many objects.
method Spatially-parallel attention and proposal-rejection mechanisms.
result SCALOR can handle up to a hundred objects in crowded scenes.
Develops a flexible deep autoencoding topic model with scalable hybrid Bayesian inference.
problem Flexible and interpretable document analysis models.
method DATM with hybrid Bayesian inference, including topic-layer-adaptive stochastic gradient Riemannian MCMC and Weibull variational encoder.
result Demonstrates scalability and efficacy on big corpora in unsupervised and supervised learning tasks.
Paper proposes MMI-ALI for scalable joint distribution matching across multiple domains.
problem Scalability issue in matching joint distributions across multiple domains.
method Adversarial training with Multivariate Mutual Information maximization.
result MMI-ALI achieves scalable joint distribution matching across multiple domains.
DiPhon generates scalable graphs via diffusion on graphons.
problem Scaling diffusion models to large graphs.
method Formulated a continuous diffusion process on graphon space via Jacobi SDE, discretized for finite graphs.
result DiPhon matches the first moment of graphon dynamics and approximates the second moment.
dAUTOMAP scales AUTOMAP by decomposing domain transformation.
problem Inadequate scalability limits AUTOMAP's practicality.
method Decomposes AUTOMAP's domain transformation for linear scalability.
result dAUTOMAP outperforms AUTOMAP with fewer parameters.
Generative model on manifolds reduces divergence computation and improves scalability.
problem Difficulties in modeling data on non-Euclidean spaces due to expensive divergence computation and approximations of heat kernel.
method Riemannian Diffusion Mixture, a principled framework using a mixture of bridge processes.
result Achieves superior performance on diverse manifolds with reduced simulation steps.
SIGL learns scalable graphons from graphs.
problem Estimating graphons from graphs of varying sizes.
method Combines INRs and GNNs for scalable graphon estimation.
result SIGL learns consistent graphons at arbitrary resolutions.
New framework classifies generated images into finer categories.
problem Difficulty in detecting new types of generated images.
method Scalable deep metric learning for multi-class classification.
result Improved detection performance on new types of generated data.
We present a novel, scalable and Bayesian approach to modelling the occurrence of pairs of symbols (i,j) drawn from a large vocabulary. Observed pairs are assumed to be generated by a simple popularity based selection process followed by censoring using a preference function. By basing inference on the well-founded pri…
EnFF uses flows to speed up DA in high dimensions.
problem Efficiently assimilating noisy data in high-dimensional systems.
method Flow Matching (FM) for training-free, scalable data assimilation.
result EnFF accelerates DA with improved cost-accuracy tradeoffs and scalability.
New scalable GP approximation using Fourier series decomposition.
problem Scalability and accuracy in Gaussian process approximations.
method Harmonic kernel decomposition (HKD) to decompose kernels orthogonally.
result Significantly outperforms standard variational methods in scalability and accuracy.
In this paper, we present a general framework to scale graph autoencoders (AE) and graph variational autoencoders (VAE). This framework leverages graph degeneracy concepts to train models only from a dense subset of nodes instead of using the entire graph. Together with a simple yet effective propagation mechanism, our…
A scalable algorithm for sampling and fine-tuning models using Tilt Matching.
problem Efficient sampling and fine-tuning of generative models.
method Tilt Matching, arising from a dynamical equation, minimizes variance and inherits regularity from stochastic interpolants.
result Empirically verified to be efficient and highly scalable, providing state-of-the-art results.
SCALLOP improves likelihood flow maps for efficient Boltzmann generation.
problem Efficient estimation of model likelihood in flow-based generative models.
method SCALLOP introduces a Hutchinson-free likelihood distillation objective for scalable flow-based models.
result SCALLOP achieves up to 10x inference speedup while improving performance.
Scalable method learns context-specific models for hundreds of variables.
problem Learning context-specific models for large numbers of variables.
method Order-based Markov chain Monte-Carlo search with context-specific sparsity assumption.
result Method scales to hundreds of variables and learns accurate models.
Paper presents a new method to learn unnormalized models efficiently.
problem Scalability issues in score matching for flexible unnormalized models.
method Connects learning objectives to Wasserstein gradient flows for scalability.
result Demonstrates improved learning of unnormalized models on manifolds.
Bayesian optimization sped up with scalable Gaussian processes.
problem Optimizing functions with derivative information and large datasets.
method Combines derivative acceleration and scalable Gaussian process models.
result Significant speedup in optimization convergence for large datasets.
Framework generates precise synthetic populations for scalable modeling.
problem Generating accurate synthetic populations without personal data.
method Constraint-programming framework encoding aggregated statistics and structural relations.
result Exact control of demographic profiles without requiring microdata.
This work connects BNNs to GPs, providing scalable inference and identifying key properties.
problem Scaling and inference challenges in Bayesian neural networks.
method General convergence from BNNs to GPs, new covariance function, and scalable Nyström approximation.
result Established a scalable maximum a posterior (MAP) training and prediction procedure.
SG-PALM learns interpretable tensor models for high-dimensional data.
problem Learning interpretable tensor models for high-dimensional data.
method SG-PALM combines Sylvester generative model and fast proximal alternating linearized minimization.
result SG-PALM converges linearly to global optimum and scales to high dimensions.
Bayesian learning made scalable with posteriors library.
problem Computational challenges in Bayesian learning with modern models.
method Introducing posteriors library and tempered MCMC.
result Bayesian approximations are useful and scalable.
A scalable factorized Gaussian process VAE for faster inference.
problem Inference bottlenecks in Gaussian process VAEs.
method Factorizes latent kernel across auxiliary features, leveraging independence.
result Significant speed-up in inference time (in theory and practice).
Bayesian non-linear matrix completion tackles large, sparse data.
problem Predict missing elements in large, sparsely observed matrices.
method Bayesian Gaussian process latent variable models with data-parallel distributed computation.
result Scalable Bayesian non-linear matrix completion outperforms linear methods.
Scalable physics-informed deep generative model for solving forward and inverse stochastic differential equationsphysics.comp-ph
New model solves complex SDEs with high-dimensional spatial and stochastic spaces.
problem Solving SDEs with high-dimensional spatial and stochastic spaces.
method Physics-informed deep generative model (sPI-GeM) combining PI-BasisNet and PI-GeM.
result Scalable solution for high-dimensional SDE problems.
Deep model learns complex latent codes without assuming factor structure.
problem Learning latent codes with complex, non-factorial distributions.
method Deep generative factor analysis with beta process prior and stochastic EM algorithm.
result Preliminary results show model can approximate complex distributions.
S3VDC improves DC methods for scalability, stability, and simplicity.
problem Poor scalability, instability, and lack of simplicity in DC methods.
method Four algorithmic improvements: initial -training, periodic -annealing, mini-batch GMM initialization, and inverse min-max transform. S3VDC incorporates all improvements.
result S3VDC outperforms state-of-the-art methods on benchmark and industrial datasets.
EiNets improve PCs for scalable probabilistic modeling.
problem Scalability issues in training PCs on real-world data.
method Combining einsum operations for speedups and memory savings; simplifying EM for PCs.
result EiNets can scale to large datasets like SVHN and CelebA.
Scalable Bayesian Learning for State Space Models using Variational Inference with SMC Samplersstat.ML
We present a scalable approach to performing approximate fully Bayesian inference in generic state space models. The proposed method is an alternative to particle MCMC that provides fully Bayesian inference of both the dynamic latent states and the static parameters of the model. We build up on recent advances in compu…
The paper discusses scalable learning for wireless data-driven systems.
problem Expanding data volume and model complexity limit centralized learning solutions.
method Discusses scalable architecture and local learning strategies.
result Promising research directions in scalable data-driven wireless communications.
AutoGraph uses transformers to efficiently generate graphs as sequences.
problem Efficiently generating large, sparse graphs without expensive node features.
method Flattening graphs into sequences and using decoder-only transformers.
result AutoGraph achieves state-of-the-art performance on synthetic and molecular benchmarks.
New GP-VAE model improves scalability and performance.
problem Inability of conventional VAEs to model correlations between data points.
method Principled sparse inference approaches to improve scalability of GP-VAEs.
result New model outperforms existing approaches in runtime and memory usage.
BiGG model efficiently generates sparse graphs with reduced complexity.
problem Challenges in scalable deep learning for sparse graphs.
method BiGG model, an autoregressive model that leverages graph sparsity.
result Graph generation time complexity reduced from to .
Bayesian GAMs improve predictive performance for high-dimensional data.
problem Sparse regularization in GAMs leads to excess shrinkage and difficulty in selecting nonlinear effects.
method Developed a novel spike-and-slab LASSO prior and scalable EM-Coordinate Descent algorithm.
result Improved predictive and computational performance compared to existing models.
DAMNETS generates complex network dynamics models.
problem Generating flexible and scalable models for network time series is challenging.
method Deep autoregressive model for Markovian network time series.
result DAMNETS outperforms other methods in sample quality.
DKL-KAN combines deep learning and kernel methods for scalable, expressive models.
problem Combining deep learning's depth with kernel methods' flexibility for scalable models.
method DKL-KAN uses Kolmogorov-Arnold Networks (KAN) to optimize kernel attributes within a Gaussian process framework.
result DKL-KAN outperforms DKL-MLP on datasets with a low number of observations and DKL-MLP on large datasets.
Model identifies causal structure from paired observational and interventional data with unknown soft interventions.
problem Identifying causal structure from observational and interventional data with unknown soft interventions.
method Proposes a scalable causal discovery model that aggregates subset-level PDAGs and applies contrastive cross-regime orientation rules.
result The model asymptotically recovers the identifiable PDAG and can orient additional edges compared to non-contrastive subset-restricted methods.
Dynamic topic models (DTMs) model the evolution of prevalent themes in literature, online media, and other forms of text over time. DTMs assume that word co-occurrence statistics change continuously and therefore impose continuous stochastic process priors on their model parameters. These dynamical priors make inferenc…
Scalable TS using sparse GPs improves efficiency without sacrificing performance.
problem Efficiently applying TS to complex, multi-modal problems.
method Sparse Gaussian Process models for scalable TS.
result Theoretical and empirical validation of scalable TS's effectiveness.
Generalized additive models (GAMs) are a widely used class of models of interest to statisticians as they provide a flexible way to design interpretable models of data beyond linear models. We here propose a scalable and well-calibrated Bayesian treatment of GAMs using Gaussian processes (GPs) and leveraging recent adv…
A scalable Bayesian linear regression framework for spatial data.
problem Scalable methodologies for analyzing large spatial datasets.
method Conjugate Bayesian linear regression framework.
result Exact sampling from joint posterior distribution without iterative algorithms.
EduQG generates better educational questions by pre-training on scientific text.
problem Improving the quality of educational questions for scalable self-assessment.
method Adapting a large language model for educational question generation, pre-trained on scientific text.
result EduQG produces superior educational questions compared to baseline models.
A new model learns latent spaces for graph data.
problem Scalability and expressivity limitations in graph generative models.
method Sequential Graph Variational Autoencoder (SGVAE) that learns latent spaces directly from graph data.
result Promising results on a cycle dataset, but need for permutation relaxation.
A new method generates graphs with hierarchical structures.
problem Generating graphs with natural hierarchical structures.
method Recursively generates community structures at multiple resolutions, parallel generation of all sub-structures.
result Improves generative performance on multiple graph datasets.
Despite advances in scalable models, the inference tools used for Gaussian processes (GPs) have yet to fully capitalize on developments in computing hardware. We present an efficient and general approach to GP inference based on Blackbox Matrix-Matrix multiplication (BBMM). BBMM inference uses a modified batched versio…
A scalable algorithm approximates Wasserstein Barycenters using neural networks.
problem Representing the weighted mean of probability distributions in high dimensions.
method Input Convex Neural Networks (ICNNs) for Kantorovich dual formulation of Wasserstein-2 distance.
result Generative model representation of the Barycenter with infinite samples.