Efficient RL in large POMDPs with latent determinism and embeddings.
problem Efficient reinforcement learning in large-scale POMDPs with latent states and observations.
method Conditional Hilbert space embeddings, linear optimal Q-function, deterministic latent transitions, gap assumption. result Computationally and statistically efficient algorithm for exact optimal policy.
Graph neural networks can perform approximate reasoning in latent space for mathematical statements.
problem Can neural networks perform steps of approximate reasoning in a fixed dimensional latent space?
method Design and conduct an experiment using graph neural networks to predict rewrite-success of mathematical statements in a latent space.
result Graph neural networks can make non-trivial predictions about rewrite-success of statements in latent space.
PLIs improve classifier performance by fine-tuning latent representations.
problem Difficult interpretation of high-dimensional latent representations in neural networks.
method Back-propagation of manual changes to low-dimensional embeddings using t-distributed stochastic neighbourhood embeddings.
result Manual separation of class clusters in latent space enhances classifier performance.
New method estimates uncertainty in knowledge graph embeddings using neural variational inference.
problem Estimating uncertainty in knowledge graph embeddings.
method Constructs an inference network conditioned on symbolic representations of entities and relation types in a Knowledge Graph.
result Improved predictive uncertainty estimates during link prediction.
WiSE-ALE improves VAEs by learning a flexible aggregate posterior.
problem Learning compact latent representations from large datasets.
method Derives a new variational lower bound and uses it to place a prior on the entire dataset.
result WiSE-ALE achieves excellent reconstruction quality with a smooth, compact representation.
Unified Latent Dynamics unifies model-free and model-based reinforcement learning.
problem Combining the efficiency of model-free methods with the representational strengths of model-based approaches.
method Embedding state-action pairs into a latent space where the true value function is approximately linear, using synchronized updates of encoder, value, and policy networks.
result ULD achieves cross-domain competence with minimal tuning and a fraction of the parameter footprint.
Most existing word embedding methods can be categorized into Neural Embedding Models and Matrix Factorization (MF)-based methods. However some models are opaque to probabilistic interpretation, and MF-based methods, typically solved using Singular Value Decomposition (SVD), may incur loss of corpus information. In addi…
SEMASIA provides a large dataset of latent representations for model comparison.
problem Difficulty in comparing semantic structures across different neural network models.
method Collection of latent representations from 1700 pretrained models across various benchmarks.
result Consistent semantic organization across models and datasets.
A new model clusters networks with community-specific submanifold structures.
problem Clustering networks with community-specific submanifold structures.
method Latent Structure Block Models (LSBM) for Bayesian spectral graph clustering.
result LSBM correctly recovers underlying communities in one-dimensional manifold structures.
The Fisher information metric is an important foundation of information geometry, wherein it allows us to approximate the local geometry of a probability distribution. Recurrent neural networks such as the Sequence-to-Sequence (Seq2Seq) networks that have lately been used to yield state-of-the-art performance on speech…
New method embeds correlation networks to reveal underlying time series patterns.
problem Analyzing correlation networks derived from time series data.
method Spectral embedding of noisy correlation networks, leveraging Fourier basis elements.
result Spectral embedding recovers true vertex-level latent representations under suitable assumptions.
Generative Distribution Embeddings learn multiscale representations of distributions.
problem Learning representations of entire distributions for multiscale reasoning.
method Introducing GDE framework that lifts autoencoders to the space of distributions, using conditional generative models and distributional invariance.
result GDEs learn predictive sufficient statistics embedded in Wasserstein space, recovering distances and trajectories for Gaussian and Gaussian mixture distributions.
AMES framework selects optimal embedding space for latent graph inference.
problem No principled method for choosing the best embedding space for latent graph inference.
method Differentiable AMES framework using backpropagation to select optimal embedding space.
result Consistently achieves comparable or superior results across multiple datasets.
Improved recommendations using latent embeddings from user reviews.
problem Lack of consideration for latent embeddings in multi-criteria recommender systems.
method Utilized variational autoencoders to map user reviews into latent embeddings, which are then compressed into discrete vectors for multi-criteria recommendation.
result The proposed method significantly outperforms baselines across various datasets and evaluation measures.
New method neutralizes gender bias in word embeddings without losing semantic information.
problem Gender biases in word embeddings trained on human-generated corpora.
method Latent Disentanglement and Counterfactual Generation with siamese auto-encoder and gradient reversal layer.
result Our method outperforms existing debiasing methods in preserving semantic information and neutralizing gender biases.
Transformers encode latent distributions in text, improving performance in out-of-distribution cases.
problem What should embeddings from language models represent?
method Connecting autoregressive prediction to sufficient statistics, identifying three settings.
result Transformers encode latent generating distributions, improving performance.
Geometrically transforms word embeddings into a common space for better comparison.
problem Comparing embeddings from different sources is challenging.
method Applies orthogonal rotations and Mahalanobis scaling to transform embeddings into a shared latent space.
result The method improves word similarity and analogy tasks.
Bayesian model estimates latent dimension and communities in graphs.
problem Automatic selection of latent dimension and number of communities in spectral embeddings.
method Bayesian model for simultaneous selection of latent dimension and number of communities.
result Promising performance in recovering latent community structure on simulated and real-world data.
Develops a scalable multi-task Gaussian process with neural embedding for improved performance.
problem High model complexity and limited model capability in multi-task Gaussian processes.
method Neural embedding of coregionalization, advanced variational inference, sparse approximation.
result Higher prediction quality and better generalization of the NSVLMC model.
A new method for inferring latent states in Markov jump processes.
problem Intractable exact inference for Markov jump processes.
method Entropic matching within expectation propagation.
result Superior performance in approximating the mean of the posterior process.
Enhances word embedding by transferring external knowledge.
problem Low-frequency words in semantic space.
method Latent Semantic Imputation (LSI) integrating graph theory and spectral embeddings.
result LSI generates reliable embedding vectors for low-frequency words.
The paper shows how to recover true node positions from a graph or similarity matrix.
problem Recovering true distances and positions from a graph or similarity matrix.
method Two steps: matrix factorisation followed by nonlinear dimension reduction.
result Nonlinear dimension reduction can recover latent positions close to a manifold where geodesic distance is encoded.
NE-VAE prevents posterior collapse in VAEs by embedding neighbors in latent space.
problem Posterior collapse in VAEs when strong decoders are used.
method Neighbor embedding in latent space to prevent collapse.
result NE-VAE produces qualitatively different latent representations with active latent dimensions.
SyNGLER generates synthetic networks efficiently while preserving key structural properties.
problem Efficiently generating realistic synthetic networks with preserved structural properties.
method SyNGLER uses latent space network models to learn and reconstruct node embeddings, then generates synthetic networks.
result SyNGLER produces synthetic networks that better preserve key network characteristics than existing approaches.
DINOSAUR improves retrieval by accounting for embedding uncertainty in recommender systems.
problem Retrieval bias towards popular items due to noisy embeddings.
method Samples multiple embeddings per item and queries with sampled embeddings to account for uncertainty.
result Improves coverage of long-tail niche content without sacrificing recall.
Autoencoder optimizes data embedding for accurate PDF reproduction.
problem Inaccurate PDF reproduction in latent space of VAEs.
method Rate-Distortion Optimization guided autoencoder with isometric property.
result Our method achieves isometric data embedding and tractable PDF relations.
We would like to learn latent representations that are low-dimensional and highly interpretable. A model that has these characteristics is the Gaussian Process Latent Variable Model. The benefits and negative of the GP-LVM are complementary to the Variational Autoencoder, the former provides interpretable low-dimension…
Model learns multilingual word representations robust to noise.
problem Learning multilingual word representations in noisy environments.
method Fit a generative latent variable model to a multilingual dictionary.
result Competitive multilingual embeddings across various tasks.
The study categorizes knowledge graph relations and explains their embedding representations.
problem Understanding how knowledge graph relation representations capture semantic information.
method Categorizing knowledge graph relations into three types and deriving explicit requirements for their representations.
result Empirical properties of relation representations and the performance of methods are justified by the analysis.
Deep metric learning has been demonstrated to be highly effective in learning semantic representation and encoding information that can be used to measure data similarity, by relying on the embedding learned from metric learning. At the same time, variational autoencoder (VAE) has widely been used to approximate infere…
Improved graph embedding through refined linear transformation and community recovery.
problem Identifying meaningful latent communities in graph data.
method Refined graph encoder embedding via linear transformation, self-training, and latent community recovery.
result Improved vertex embedding and better decision boundaries for vertex classification.
DeepEDM forecasts time series by learning dynamics from embeddings.
problem Precise future prediction of complex nonlinear time series.
method Integrates nonlinear dynamical systems modeling with deep neural networks.
result DeepEDM outperforms state-of-the-art methods in forecasting accuracy.
Continuous latent time series models are prevalent in Bayesian modeling; examples include the Kalman filter, dynamic collaborative filtering, or dynamic topic models. These models often benefit from structured, non mean field variational approximations that capture correlations between time steps. Black box variational…
Proposes priors for interpretable word embeddings.
problem Lack of interpretability and unsupervised nature of word embeddings.
method Use of informative priors to create interpretable probabilistic word embeddings.
result Sensible priors capture latent semantic concepts better than current methods.
Diffusion Variational Autoencoders capture topological properties of datasets.
problem Standard VAEs struggle with topological properties of certain datasets.
method Introduces Diffusion VAEs with transition kernels of Brownian motion on arbitrary manifolds.
result Diffusion VAEs can capture topological properties of synthetic datasets.
Recently, considerable research attention has been paid to network embedding, a popular approach to construct feature vectors of vertices. Due to the curse of dimensionality and sparsity in graphical datasets, this approach has become indispensable for machine learning tasks over large networks. The majority of existin…
Paper shows graphs can be embedded in lower dimensions than expected.
problem Choosing the right embedding dimension for graph analysis.
method Utilizes hidden manifold structure to predict lower-dimensional embedding.
result Graphs can be embedded in much lower dimensions than previously thought.
Proposes a privacy-preserving method for graph embedding.
problem Privacy leakage in adjacency spectral embedding for stochastic blockmodels.
method Differentially private adjacency spectral embedding algorithm for stochastic blockmodels.
result Estimates latent positions close to those by non-private embedding, maintaining accuracy at desired privacy levels.
DSE learns transferable skills across changing dynamics and goals.
problem Learning transferable skills across different reinforcement learning tasks.
method Variational inference for multi-task reinforcement learning with shared and task-specific latent spaces.
result Policies can generalize to unseen dynamics and goals conditions.
We consider the problem of vertex classification for graphs constructed from the latent position model. It was shown previously that the approach of embedding the graphs into some Euclidean space followed by classification in that space can yields a universally consistent vertex classifier. However, a major technical d…
Paper learns meaningful state and action representations from MDP trajectories.
problem Learning good state and action representations from MDP trajectories.
method Tensor decomposition, kernelization, importance sampling, low-Tucker-rank approximation.
result The learned state/action abstractions provide accurate approximations to latent block structures.
This paper improves spectral embedding for multipartite networks, revealing latent subspaces and providing consistent node representations.
problem Improving spectral embedding for multipartite networks to better represent node types.
method Developed a follow-on step to spectral embedding that recovers node representations in their intrinsic rather than ambient dimension, proving consistency under a specific model.
result Node representations in multipartite networks lie near type-specific subspaces, and the proposed method recovers these representations consistently.
RL-VAE uses RL to decode molecular graphs from latent embeddings.
problem Efficiently decoding molecular graphs from latent embeddings.
method Repurposed simple graph generator for efficient decoding.
result Decoding molecular graphs from latent embeddings is possible with a simple graph generator.
LaT-PFN model predicts time series with zero-shot capability.
problem Zero-shot time series forecasting.
method In-context latent space learning with JEPA and PFN integration.
result Superior zero-shot predictions compared to baselines.
The Variational Autoencoder (VAE) is a powerful architecture capable of representation learning and generative modeling. When it comes to learning interpretable (disentangled) representations, VAE and its variants show unparalleled performance. However, the reasons for this are unclear, since a very particular alignmen…
A body of recent work in modeling neural activity focuses on recovering low-dimensional latent features that capture the statistical structure of large-scale neural populations. Most such approaches have focused on linear generative models, where inference is computationally tractable. Here, we propose fLDS, a general …
A new clustering method using deep autoencoder networks and spectral clustering.
problem Improving clustering accuracy in noisy data.
method Dual autoencoder network for robust latent representations, mutual information estimation for discriminative features, deep spectral clustering.
result Significantly outperforms state-of-the-art clustering approaches on benchmark datasets.
SLED improves factuality in LLMs without external knowledge.
problem Unreliable or factually incorrect outputs from large language models.
method Contrasts final layer logits with early layers' logits, uses approximate gradient to refine outputs.
result Consistently improves factual accuracy over existing methods.