The paper provides concentration bounds for embeddings of generative models.
problem Establishing accurate statistical analysis of generative models.
method Data Kernel Perspective Space embedding method.
result Required number of sample responses for accurate approximation.
The paper establishes concentration bounds for embeddings of generative models.
problem Analyzing statistical properties of generative models.
method High probability concentration bounds on sample vector embeddings using Data Kernel Perspective Space.
result Determines the number of samples needed for accurate approximation of generative model embeddings.
Generative LLE modifies LLE to generate stochastic embeddings.
problem Nonlinear dimensionality reduction and manifold learning.
method Generative LLE modifies LLE by using stochastic linear reconstruction.
result Generative LLE can generate various LLE embeddings stochastically.
A new embedding structure, res-embedding, improves deep CTR models by enhancing generalization performance.
problem Deep CTR models often suffer from poor generalization performance due to learning of embedding parameters.
method Developed a res-embedding structure that combines a central embedding vector from an item-based interest graph with a residual embedding vector.
result Empirical evaluation shows significant improvement in model performance using the res-embedding structure.
Visualization tools show how embeddings generalize beyond validation data.
problem Understanding how learned embeddings generalize to new data.
method Visualization tools and triplet selection strategies for metric learning.
result Best performance in metric learning comes from selecting a few well-considered triplets.
This work analyzes PPR-based node embeddings and their topological information.
problem Understanding and interpreting PPR-based node embeddings.
method Unified framework and two methods for topology recovery.
result PPR-based embeddings maintain more topological information than random walk-based embeddings.
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.
Generalizes embedding complex Grassmannians into quadrics.
problem Holomorphic isometric embeddings of complex Grassmannians into quadrics.
method Generalization of do Carmo-Wallach theory for moduli spaces.
result Moduli spaces of embeddings discussed.
The paper generalizes a key theorem in complex geometry.
problem Complex geometry theorems and their generalizations.
method Analytical methods
result Generalization of the Kodaira embedding theorem
Defines coupled embeddability for maps on products of spaces, generating examples and nonexamples.
problem Understanding when maps on products of spaces can be embedded.
method Uses known results for nonsingular biskew and bilinear maps, studies genericity properties, extends Whitney embedding theorems, and relates to Z/2-coindex of embedding spaces. result Generates strong obstructions to coupled embeddability in terms of combinatorics of triangulations.
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 faster, space-saving methods for subspace embeddings in tensors.
problem Efficiently embedding large tensors with fewer random bits.
method Modewise Johnson-Lindenstrauss embeddings for rank-r tensors. result Improved space complexity for tensor subspaces with fewer random bits.
Paper studies embedding conditions for homogeneous quandles.
problem Embedding problem of homogeneous quandles.
method Necessary and sufficient condition for quandle homomorphisms to be embeddings.
result Generalization of embedding theorem for generalized Alexander quandles.
A new method for fast graph embedding using diffusion graphs.
problem Efficiently generating graph embeddings for large networks.
method Diffusion graphs for rapid vertex sequence generation.
result Improved accuracy and performance with higher edge density.
Author2Vec generates user embeddings from social media data.
problem Generating useful user embeddings from noisy social media data.
method End-to-end neural network with BERT sentence representations and unsupervised pre-training.
result Author2Vec outperforms traditional methods in user classification tasks.
Maps can be embedded in higher dimensions if they lift to embeddings in product spaces.
problem Embedding maps in higher dimensions without self-intersections.
method Lifting maps to embeddings in product spaces.
result Maps can be embedded in higher dimensions if they lift to embeddings in product spaces.
For leveled spatial graphs, we find a surface embedding that allows cellular embedding.
problem Finding a surface embedding for general spatial graphs is not always possible.
method Define leveled property, decompose graph into subgraphs, and construct surface.
result For leveled spatial graphs with a small number of levels, a surface can always be found.
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.
Study improves radio show segmentation using audio embeddings.
problem Automated segmentation of radio shows.
method Created audio embeddings from multi-class classification tasks on different datasets, evaluated performance against text-only baseline.
result Audio embeddings from non-speech sound event classification significantly outperformed text-only baseline by 32.3% in F1-measure.
In this paper we study the embedding of Riemannian manifolds in low codimension. The well-known result of Nash and Kuiper says that any short embedding in codimension one can be uniformly approximated by C1 isometric embeddings. This statement clearly cannot be true for C2 embeddings in general, due to the classi…
This paper tightens the generalization error bound for graph embedding in non-Euclidean spaces.
problem High generalization error in non-Euclidean graph embedding, preventing practical applications.
method Novel upper bound of graph embedding's generalization error using local Rademacher complexity.
result The new bound is tighter and faster, allowing better performance in non-Euclidean spaces.
New proof shows no Hölder embeddings into Heisenberg group.
problem Non-existence of Hölder embeddings into Heisenberg group.
method Developed a new elementary proof method.
result Generalization of Gromov's theorem proven.
Models use embeddings and attention for better claim severity prediction.
problem Improving predictive modeling of claim severity with categorical data.
method Developed neural networks and attention-based architectures with embeddings.
result Attention-based models enhance predictive performance with contextual augmentation.
Meta-Embedding improves CTR predictions for new ads, addressing cold-start and warm-up issues.
problem Improving CTR predictions for new ads with little logging data.
method Meta-learning approach to generate initial embeddings for new ad IDs.
result Meta-Embedding significantly improves CTR predictions for various models, including lightweight and deep learning.
A new method for document network embedding interprets and generalizes well.
problem Lack of interpretability and generalization to new documents in existing methods.
method Introduces Topic-Word Attention (TWA) and Inductive Document Network Embedding (IDNE) to generate document representations.
result Achieves state-of-the-art performance on various networks and produces meaningful representations.
In this paper, we show that, under arbitrary bounded Willmore energy assumption, embedded Willmore spheres (or more generally, embedded Willmore spheres under area constraint) with small diameter in a given 3-dimensional Riemannian manifold (M,h) necessarily concentrate at a critical point of the scalar curvature …
DiSeNE generates interpretable node embeddings without supervision.
problem Lack of interpretability in unsupervised node embeddings.
method Disentangled representation learning with novel objective functions and metrics.
result DiSeNE produces interpretable node embeddings aligned with graph structure.
CR embeddings in complex spaces for specific Lie groups.
problem Embedding specific Lie groups in complex spaces.
method Using integrable complex structures on subbundles of tangent bundles.
result CR embeddings possible as the edge of wedges in complex domains.
Paper proposes a method to refine embeddings efficiently.
problem Efficiently refining embeddings after their creation.
method Uses a Domain Adversarial Network (DAN) with constraints.
result Significantly outperforms state-of-the-art unsupervised algorithms.
New method detects and analyzes correlation in multiple network data.
problem Detecting and analyzing correlation in multiple network data.
method Generalized omnibus embedding methodology.
result Induced correlation can significantly extend the reach of spectral inference procedures.
We give a solution to the equivalence and the embedding problems for smooth CR-submanifolds of complex spaces (and, more generally, for abstract CR-manifolds) in terms of complete differential systems in jet bundles satisfied by all CR-equivalences or CR-embeddings respectively (local and global). For the equivalence p…
Improves machine learning performance with domain-specific embeddings.
problem Tuning word embeddings for specific use cases and domains.
method Combines multiple domain-specific embeddings using a ranking function and dimensionality reduction.
result Effective domain-specific embeddings improve machine learning performance.
Paper proposes a black-box adversarial attack method for graph embedding models.
problem Robustness of graph embedding models against adversarial attacks.
method GF-Attack constructs a generalized adversarial attacker by the graph filter and feature matrix, performing the attack on the graph filter in a black-box fashion.
result GF-Attack can consistently make strong attacks on different graph embedding models even with small perturbations.
Explicitly constructs CR regular embeddings of spheres in complex spaces.
problem Embedding spheres in complex spaces with CR regularity.
method Generalizes Ahern and Rudin's construction to higher dimensions.
result Odd dimensional spheres admit CR regular embeddings in complex spaces if and only if the dimension is even.
Unified framework for word embedding models using noise examples.
problem Improving word embedding models with negative sampling.
method Formulated a Word-Context Classification (WCC) framework that generalizes SkipGram word embedding models.
result The best noise distribution is the data distribution, improving both performance and training speed.
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.
PGEL learns embeddings to diversify protein motifs while maintaining biological function.
problem Generating diverse protein structures while preserving biological function.
method Embedding learning framework that enhances motif diversity in a diffusion model's frozen denoiser.
result PGEL achieves greater structural diversity, better designability, and improved self-consistency compared to partial diffusion.
Proposes spherical text embedding for better directional similarity.
problem Directional similarity is more effective but unsupervised text embeddings are typically learned in Euclidean space.
method Develops a spherical generative model and an efficient optimization algorithm for unsupervised word and paragraph embeddings.
result Achieves state-of-the-art performances on various text embedding tasks.
This paper improves topic modeling by embedding words and topics together.
problem Topic models struggle with short documents and approximate inference.
method Model each document as a mixture of word embeddings and each topic as a mixture of topic embeddings.
result The method optimizes topic embeddings to minimize semantic differences between words and topics.
We introduce (k,l)-regular maps, which generalize two previously studied classes of maps: affinely k-regular maps and totally skew embeddings. We exhibit some explicit examples and obtain bounds on the least dimension of a Euclidean space into which a manifold can be embedded by a (k,l)-regular map. The problem c…
Extends graph encoder embedding to weighted graphs and matrices.
problem Classifying vertices in various graph types efficiently.
method Graph encoder embedding applied to weighted graphs, distance matrices, and kernel matrices.
result The method achieves asymptotic normality, enabling optimal classification.
Conventional text classification models make a bag-of-words assumption reducing text into word occurrence counts per document. Recent algorithms such as word2vec are capable of learning semantic meaning and similarity between words in an entirely unsupervised manner using a contextual window and doing so much faster th…
A new graph embedding method using Hebbian learning for improved vector representations.
problem Creating accurate vector representations for nodes in graphs.
method Hebbian learning with non-convex Gaussian mixture model for node embeddings.
result The method outperforms state-of-the-art methods on benchmark data sets and generates relevant recommendations.
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.
We introduce a new multi-dimensional nonlinear embedding -- Piecewise Flat Embedding (PFE) -- for image segmentation. Based on the theory of sparse signal recovery, piecewise flat embedding with diverse channels attempts to recover a piecewise constant image representation with sparse region boundaries and sparse clust…
This work examines how embedding complexity impacts domain adaptation.
problem Improving generalization to an unlabeled target domain.
method Theoretical and empirical study of embedding complexity in multilayer neural networks.
result Developed a strategy to mitigate embedding complexity sensitivity and achieve performance on par with best tradeoffs.
Generalized Tanaka prolongation ensures convergence of formal embeddings of complex manifolds.
problem Ensuring convergence of formal embeddings of complex manifolds under weaker conditions.
method Formulated and proved generalized Tanaka prolongation for geometric structures.
result Convergence of formal embeddings holds under weaker semi-positive normal bundle conditions.
This work optimizes induced correlation in joint graph embeddings.
problem Optimizing correlation across embedded networks in joint graph embeddings.
method Developed corr2Omni algorithm to estimate optimal Omnibus weights.
result corr2Omni algorithm improves inference fidelity compared to classical Omnibus construction.