Adversarial ASV improves speaker verification robustness.
problem Mismatches in training, enrollment, and test conditions degrade deep speaker embeddings.
method Adversarial multi-task training to learn condition-invariant embeddings.
result 8.8% and 14.5% relative EER improvements for known and unknown conditions.
Paper develops neural network for Mandarin polyphone disambiguation.
problem Homograph problem in Mandarin Chinese text-to-speech.
method Bidirectional RNN for context, prediction network for mapping embeddings to pronunciations.
result Achieves 94.69% accuracy on polyphonic character dataset.
ExplaiNE offers explanations for NE-based link predictions.
problem Lack of transparency in NE methods for link prediction.
method Identifies counterfactual explanations for NE-based LP methods.
result Accuracy and scalability demonstrated for ExplaiNE.
Proposes CCME framework for estimating heterogeneous treatment effects.
problem Estimating heterogeneous treatment effects in complex distributions.
method Embeds conditional distributions into RKHS, develops meta-estimators for CCME.
result Establishes finite-sample convergence rates and double robustness for CCME estimators.
CGNP embeds functional processes into latent vectors using graph neural networks.
problem Embedding and sampling functional processes over arbitrary domains.
method CGNP employs graph neural networks to embed and decode functional processes.
result CGNP effectively samples encoded functions over any domain.
Use network embeddings to correct for unobserved confounding.
problem Causal inference in the presence of unobserved confounding.
method Use network embeddings to semi-supervised predict treatments and outcomes.
result Valid causal inferences under suitable conditions on predictive model quality.
The paper examines how different fusion strategies in neural networks affect user embeddings and their quality.
problem The need for automated processing of user data, particularly in predicting ratings and estimating user similarity.
method Analyzed the effect of various fusion strategies in neural networks on user embeddings quality and prediction performance.
result Fusion strategies in neural networks affect both embedding quality and prediction performance, and prediction performance does not necessarily reflect embedding quality.
Neural-Kernel CME tackles scalability and expressiveness challenges in conditional distribution representation.
problem Scalability and expressiveness challenges in kernel conditional mean embeddings.
method Combines deep learning with CMEs using a neural network optimization framework.
result Achieves competitive and often superior performance in conditional density estimation and RL.
Network Embeddings (NEs) map the nodes of a given network into d-dimensional Euclidean space Rd. Ideally, this mapping is such that `similar' nodes are mapped onto nearby points, such that the NE can be used for purposes such as link prediction (if `similar' means being `more likely to be connected') or c…
Proposes CCE to assess point-wise reliability of neural network predictions.
problem Overconfidence and misaligned predictive distributions in neural networks.
method Introduces Conditional Congruence (CCE) metric using conditional kernel mean embeddings.
result CCE exhibits correctness, monotonicity, reliability, and robustness in high-dimensional regression tasks.
CSNE embeds signed networks by separating structural and fine-grained information.
problem Improving sign prediction in signed networks using inaccurate or incomplete balance theories.
method Conditional Signed Network Embedding (CSNE) models structural and fine-grained information separately, integrating them rigorously.
result CSNE outperforms state-of-the-art on sign prediction tasks, and MaxEnt priors are competitive in resource-constrained settings.
Improved far-field speaker verification for short utterances in noisy conditions.
problem Challenges in speaker verification on short utterances in uncontrolled noisy environments.
method Used deep neural network architectures (TDNN and ResNet) and experimented with various embedding extractors and training procedures.
result ResNet architectures outperform x-vector approach in speaker verification quality for both long and short utterances.
A new method separates instruments in music using shared embeddings.
problem Separating individual instruments in a musical mixture.
method Common embedding space for all instruments, auxiliary Gaussian mixture model.
result Outperforms mask-inference baseline on MUSDB-18 dataset.
Softmax emerges naturally in neural networks as a measure of conditional mutual information.
problem The artificial nature of softmax in neural networks.
method Information-theoretic perspective to derive log-softmax and evaluate conditional mutual information.
result Training deterministic neural networks through log-softmax maximises conditional mutual information.
Neural model synthesizes music with flexible timbre controls.
problem Creating audio samples with varied timbres from musical scores.
method Recurrent neural network conditioned on learned instrument embedding followed by WaveNet vocoder.
result Learned embedding space captures diverse timbres and enables interpolation for morphing.
A new model learns demand patterns from data, reducing complexity and improving accuracy.
problem Forecasting short-term demand from spatiotemporal data with complex patterns.
method Temporal-Guided Network (TGNet) using graph networks and temporal-guided embedding.
result TGNet achieves competitive performance with fewer parameters compared to state-of-the-art models.
New method embeds dynamic networks with stability for node behavior.
problem Embed time-evolving node representations with stability.
method Unfolded adjacency spectral embedding for dynamic networks.
result Method satisfies cross-sectional and longitudinal stability.
CPFM integrates dimensionality reduction and reconstruction with flow networks.
problem Learning coupled continuous flows for data and embeddings.
method Coupled flow matching framework with Gromov-Wasserstein objective and dual-conditional flow network.
result CPFM preserves and recovers residual information in latent space.
Generative model for 3D point clouds using invertible flows.
problem Generating realistic 3D point clouds.
method Invertible flow-based models for point cloud generation with parameter sharing and embedding vectors.
result The model generates high-quality 3D point clouds with good similarity.
Conditional kernel mean embeddings are nonparametric models that encode conditional expectations in a reproducing kernel Hilbert space. While they provide a flexible and powerful framework for probabilistic inference, their performance is highly dependent on the choice of kernel and regularization hyperparameters. Neve…
In this paper, we present a novel system that separates the voice of a target speaker from multi-speaker signals, by making use of a reference signal from the target speaker. We achieve this by training two separate neural networks: (1) A speaker recognition network that produces speaker-discriminative embeddings; (2) …
SPIRE enables efficient federated learning for diffusion models by separating client-specific embeddings from a shared backbone.
problem Large diffusion models are impractical for federated learning due to their size.
method SPIRE separates the network into a global backbone and client-specific embeddings, enabling efficient finetuning.
result SPIRE achieves parameter-efficient finetuning, updating only a small fraction of weights.
The paper introduces a new method for graph embedding using exponential family distributions.
problem Representing networks in a low dimensional latent space for various applications.
method Introduces the exponential family graph embedding model, generalizing random walk-based techniques to exponential family conditional distributions.
result The proposed techniques outperform existing methods in link prediction and node classification tasks.
We investigate deep neural network performance in the textindependent speaker recognition task. We demonstrate that using angular softmax activation at the last classification layer of a classification neural network instead of a simple softmax activation allows to train a more generalized discriminative speaker embedd…
DDMI generates high-quality INRs by adapting positional embeddings.
problem Existing INR generative models fail to produce high-quality representations.
method DDMI uses adaptive positional embeddings and a D2C-VAE to enhance expressive power.
result DDMI outperforms existing models across multiple modalities and datasets.
Improved Naive Bayes classifier with neural network models.
problem Limited complexity handling and independence assumption in Naive Bayes.
method Introducing Neural Naive Bayes and Neural Pooled Markov Chain models.
result Error rate reduced by 4.5 on IMDB dataset.
DANE adapts network embeddings across multiple domains.
problem Learning embeddings for multiple networks without transferability.
method Graph Convolutional Network with adversarial learning.
result DANE achieves superior performance in cross-network domain adaptation.
We present a meta-learning approach for adaptive text-to-speech (TTS) with few data. During training, we learn a multi-speaker model using a shared conditional WaveNet core and independent learned embeddings for each speaker. The aim of training is not to produce a neural network with fixed weights, which is then deplo…
dynnode2vec embeds dynamic networks efficiently.
problem Capturing evolving patterns in large dynamic networks.
method dynnode2vec: a random walk based method initialized with previous embedding vectors.
result Demonstrates advantages over static methods on large dynamic network datasets.
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.
Deep ReLU networks can efficiently approximate Sobolev and Besov functions.
problem Approximating functions in Sobolev and Besov spaces using deep neural networks.
method Used deep ReLU neural networks with varied width and depth to approximate functions in Sobolev and Besov spaces.
result Generalized the approximation rate to hold under the Sobolev embedding condition.
New model predicts radiative properties of nanoparticle layers with high accuracy and uncertainty.
problem Predicting radiative properties of nanoparticle embedded layers accurately and with uncertainty.
method Conditional normalizing flows learn conditional distributions of optical outputs given input parameters.
result The model achieves high predictive accuracy and reliable uncertainty estimates.
Unified view of context in machine learning models.
problem Exploring context in machine learning models.
method Decompose observation into context-free and context-sensitive parts.
result Significant performance boost in sentence embedding models.
Develops a rigorous theory for conditional mean embeddings.
problem Efficient conditioning of probability distributions in RKHSs.
method Mathematical theory for both centred and uncentred covariance operators.
result Significantly weakens conditions for applicability of CMEs.
Compositional Network Embedding learns node embeddings from node features.
problem Cold-start problem and lack of robustness to noise in existing network embedding methods.
method Generative framework that combines node attribute embeddings through a graph-based loss.
result Effectiveness and generalization of compositional network embeddings, especially on unseen nodes.
New condition ensures submanifolds are skew in small areas.
problem Ensuring submanifolds are skew in Euclidean space.
method Introduces a third-order differential condition.
result Constructs improved totally skew embeddings for Rn. Graph neural networks over-smooth when layers increase, reducing discriminative power.
problem Over-smoothing in graph neural networks reduces model performance as the number of layers increases.
method Analyzed over-smoothing in general graph neural network architecture using Dirichlet energy.
result The Dirichlet energy of embeddings converges to zero, leading to loss of discriminative power.
A framework for stable dynamic network embeddings using static methods.
problem Dynamic network embedding in a nascent field.
method Using static network embedding methods on dilated unfolded adjacency matrices.
result Stable embeddings that preserve latent node behavior across time.
Comma.ai's approach to Artificial Intelligence for self-driving cars is based on an agent that learns to clone driver behaviors and plans maneuvers by simulating future events in the road. This paper illustrates one of our research approaches for driving simulation. One where we learn to simulate. Here we investigate v…
Network embedding helps predict speed limits on incomplete Danish road network.
problem Incomplete speed limit data on Danish roads limits machine learning applications.
method Applied node2vec network embedding to Danish road network.
result Network embedding can derive useful features for predicting speed limits.
Network embedding converts network data into vectors for machine learning.
problem Machine learning tasks on networks require vector representations of nodes and links.
method Various unsupervised and supervised methods for converting network data into vectors.
result Network embedding methods aim to preserve network structure in learned feature representations.
Proposes a neural network for handling multi-sensor time series with varying input dimensions.
problem Handling multi-sensor time series with varying input dimensions.
method Graph neural network conditioning vectors for zero-shot transfer learning.
result Better generalization in activity recognition and equipment prognostics datasets.
We offer a new, rigorous approach to conditional mean embeddings without operator constraints.
problem Lack of rigorous, operator-free approach to conditional mean embeddings.
method Measure-theoretic approach to conditional mean embeddings.
result Natural regression interpretation and universal consistency of empirical estimates.
A new method learns text network embeddings by combining generative autoencoder and homophilic priors.
problem Improving performance of network learning applications, especially for textual networks.
method Variational Homophilic Embedding (VHE) - a fully generative model that optimizes a variational autoencoder for semantic information and a homophilic prior for structural information.
result VHE outperforms existing methods in various tasks on real-world textual networks.
AUASE embeds dynamic networks with stability guarantees for node comparison.
problem Stability in dynamic network embeddings for comparing nodes across time.
method Attributed unfolded adjacency spectral embedding (AUASE) for stable unsupervised learning.
result AUASE provides significant improvements in link prediction and node classification.
A network embedding consists of a vector representation for each node in the network. Its usefulness has been shown in many real-world application domains, such as social networks and web networks. Directed networks with text associated with each node, such as software package dependency networks, are commonplace. Howe…
A new explicit scheme calculates XVA adjustments using neural networks and conditional expectations.
problem Calculating cross valuation adjustments (XVA) in realistic financial scenarios.
method Simulation/regression scheme for BSDEs, using neural networks and quantile regressions.
result The scheme outperforms Picard iterations in high-dimensional and hybrid market risks.
PINN-FEM combines PINNs and FEM for accurate Dirichlet boundary condition enforcement.
problem Challenges in enforcing Dirichlet boundary conditions in PINNs.
method Hybrid approach combining PINNs and FEM for strong boundary condition enforcement.
result PINN-FEM outperforms standard PINN models in accuracy and robustness.