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.
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.
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.
Introduces PELP for graph-enhanced word embeddings.
problem Combining graph side-information into static word embeddings.
method Probabilistic embeddings using Laplacian priors.
result Unified and flexible approach to various embedding methods.
BC-Aligner maintains backward compatibility of embeddings after frequent updates.
problem Updating embeddings without requiring consumer teams to retrain their models.
method Learning backward compatible embeddings through BC-Aligner.
result BC-Aligner maintains backward compatibility with existing unintended tasks after multiple model version updates.
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.
New model for temporal KG completion using diachronic entity embeddings.
problem Temporal knowledge graph completion for incomplete KGs.
method Developed novel models by equipping static KG embedding models with a diachronic entity embedding function.
result Combining diachronic entity embeddings with SimplE results in superior temporal KG completion.
Paper proposes a new approach to unify and compare knowledge graph embedding methods.
problem Lack of understanding and comparison of existing knowledge graph embedding methods.
method Introduces a multi-embedding interaction mechanism to unify and generalize existing models.
result Proposes a new multi-embedding model based on quaternion algebra.
NIS learns optimal embedding sizes for recommendation models.
problem Finding optimal embedding sizes for large-scale recommendation models.
method Neural Input Search (NIS) uses reinforcement learning to automatically find optimal vocabulary sizes and embedding dimensions.
result NIS improves prediction accuracy by 6.8% on Recall@1 and 1.8% on ROC-AUC.
Minimal dimensions found for flag manifolds embeddings.
problem Finding the smallest dimensions for flag manifolds embeddings.
method Equivariant embeddings of orthogonal and unitary groups acting on real and complex flag manifolds.
result Minimal dimensions achieved at isospectral models.
Improved recommendation systems using multi-layer embeddings reduce model size while maintaining accuracy.
problem Improving model accuracy in recommendation systems while minimizing model size.
method Introducing a multi-layer embedding training (MLET) architecture that trains embeddings via a sequence of linear layers.
result Substantial advantages in model accuracy and memory footprint are achieved with reduced embedding dimensions.
The paper explores how word embeddings affect the stability of downstream NLP models.
problem Small changes in training data can cause significant changes in model predictions.
method Empirical and theoretical analysis of embedding instability, including the introduction of eigenspace instability measure.
result Increasing embedding memory can reduce the disagreement in predictions by 5% to 37%.
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.
New framework infers multiple classes per image for one-shot learning.
problem Inferring multiple classes per image in one-shot learning.
method Compositional embedding framework with joint training of embedding and composition/query functions.
result Compositional embedding models outperform existing methods on various datasets.
A fast graph embedding method for large graphs.
problem Efficiently embedding large graphs for various applications.
method One-hot graph encoder embedding with linear complexity.
result Graph encoder embedding is approximately normally distributed and converges to its mean.
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.
Paper distills word embeddings to reduce dimensionality without sacrificing accuracy.
problem Reducing neural model size for practical deployment.
method Teacher-student model-based embedding distillation with ensemble learning.
result Significant reduction in model size (80x faster and lighter) with minimal accuracy loss.
Graph neural networks refine speaker embeddings for better session-level diarization.
problem Local speaker distinction in meeting sessions using deep embeddings.
method Graph Neural Networks (GNNs) refine speaker embeddings using session-level structural information.
result Spectral clustering on refined embeddings outperforms original embeddings significantly.
MMbeddings reduces categorical embeddings by treating them as latent effects, significantly decreasing parameters and mitigating overfitting.
problem Large cardinalities in categorical embeddings lead to high parameter counts and overfitting.
method MMbeddings treats embeddings as latent random effects in a variational autoencoder framework, reducing parameter count and mitigating overfitting.
result MMbeddings consistently outperforms traditional embeddings across various tasks, demonstrating its potential in machine learning applications.
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.
The study shows how to accurately estimate embedding vectors in high dimensions.
problem How to accurately estimate embedding vectors in high-dimensional spaces.
method A simple probability model and a variant of low-rank approximate message passing (AMP) method.
result The AMP approach enables precise predictions of the accuracy of the estimation in certain high-dimensional limits.
Embeddings leak sensitive information about input data, which can be recovered or inferred.
problem Information leakage in embedding models.
method Developed three classes of attacks to study information leakage.
result Embeddings leak sensitive information about input data, which can be partially recovered or inferred.
MEI model improves knowledge graph completion by efficiently modeling interactions between embeddings.
problem Efficiently modeling interactions between knowledge graph embeddings to predict missing links.
method MEI divides embeddings into partitions and uses Tucker and block term formats to model interactions efficiently.
result Achieves state-of-the-art performance on link prediction tasks.
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.
Paper explores embedding methods for detecting pseudo-cliques in random graphs, showing limitations and potential.
problem Detecting planted pseudo-cliques in random dot product graphs.
method Adjacency Spectral Embedding (ASE) and Graph Encoder Embedding (GEE).
result These methods can localize pseudo-cliques with additional clean network data, but not without it.
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.
Paper debiases text embeddings using context injection.
problem Text embeddings capture and perpetuate biases.
method Review 19 embedding models, quantify biases, and test context injection.
result Higher performing models are more prone to biases but better at incorporating context.
D-ETM models document topics over time using embeddings and variational inference.
problem Capturing evolving topic patterns in sequential documents.
method Combines D-LDA and word embeddings, using random walk priors and variational inference.
result D-ETM outperforms D-LDA on document completion tasks, learning more diverse and coherent topics.
ETM discovers interpretable topics in large vocabularies.
problem Existing topic models fail with large, heavy-tailed vocabularies.
method Generative model combining topic models and word embeddings with variational inference.
result ETM discovers interpretable topics even with large vocabularies.
A novel geometric algebra-based KG embedding framework improves link prediction.
problem KG embedding to model entities and relations in a low-dimensional space.
method Utilizes multivector representations and geometric product in geometric algebra.
result Outperforms state-of-the-art models in link prediction experiments.
A framework converts spatial data into embeddings for insurance risk modelling.
problem Improving underwriting precision and risk management in insurance with spatial data.
method Multi-view contrastive learning framework for generating spatial embeddings.
result Spatial embeddings consistently improve predictive accuracy across various models.
ELM improves neural model embeddings for long-tail learning.
problem Learning skewed label distributions in neural models.
method Enforces margins in logit space and regularizes embedding distribution.
result ELM reduces generalization gap and tightens tail class embeddings.
Paper proposes a novel graph recovery attack from node embeddings.
problem Privacy risks of integrating graph embeddings with machine learning pipelines.
method Model-agnostic graph recovery attack exploiting preserved structural information in node embeddings.
result Adversaries can recover graph edges with decent accuracy from node embeddings alone.
Proposes DNN-based speaker embedding correlated with subjective inter-speaker similarity for speech synthesis.
problem Inadequate speaker representation for open speakers not in training data.
method Two training algorithms using inter-speaker similarity matrices: similarity vector embedding and similarity matrix embedding.
result Proposed algorithms learn speaker embedding highly correlated with subjective inter-speaker similarity.
Embedding-based Knowledge Base Completion models have so far mostly combined distributed representations of individual entities or relations to compute truth scores of missing links. Facts can however also be represented using pairwise embeddings, i.e. embeddings for pairs of entities and relations. In this paper we ex…
Disk Embeddings tackle embedding DAGs with exponential growth.
problem Embedding DAGs with exponentially increasing ancestors and descendants.
method Disk Embeddings framework for quasi-metric spaces, including Hyperbolic Disk Embeddings.
result Disk Embeddings outperform existing methods in complex DAGs.
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.
Paper explores duality in DPPs using embedding structure analysis.
problem Understanding the geometric structure of determinantal point processes.
method Analyzes the exponential family embedding of DPPs and uses the e-embedding curvature tensor.
result Discovers the duality between marginal and L-ensemble kernels.
This study improves sentence embeddings from BERT models.
problem Capturing the underlying meaning of sentences using BERT models.
method Comprehensive review and testing of various sentence embedding extraction and refinement methods.
result Representation-shaping techniques significantly improve sentence embeddings from BERT-based and simple baseline models.
Instance embeddings are an efficient and versatile image representation that facilitates applications like recognition, verification, retrieval, and clustering. Many metric learning methods represent the input as a single point in the embedding space. Often the distance between points is used as a proxy for match confi…
We create interpretable word embeddings through sparse coding.
problem Difficult to interpret word embeddings in natural language processing.
method Transform pretrained dense word embeddings into sparse embeddings through sparse coding.
result Sparse embeddings are more interpretable and achieve good performance.
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.
A new method for few-shot learning using embedded class models and shot-free meta training.
problem Few-shot learning with limited data and varying number of samples per class.
method Learning embeddings for few-shot learning with embedded class models and shot-free meta training.
result Achieves state-of-the-art performance on standard few-shot benchmark datasets.
New method integrates topological knowledge into data embeddings.
problem Lack of general tools to incorporate prior topological knowledge into embeddings.
method Introduces new topological losses to topologically regularize data embeddings.
result Natural representation of simple models like clusters and flares.
Framework for dynamic node embeddings from graph streams.
problem Temporal prediction-based applications using graph stream data.
method ε-graph time-series representation, temporal reachability graphs, weighted temporal summary graphs.
result Dynamic embedding methods achieve better predictive performance.
The paper proves limit theorems for graph embeddings out-of-sample.
problem Proving limit theorems for graph embeddings out-of-sample.
method Least-squares and maximum-likelihood objectives for adjacency and Laplacian spectral embeddings.
result Out-of-sample extensions based on these objectives obey central limit theorems and concentration inequalities.
Proposes VCLANC for attributed network clustering using node and attribute embeddings.
problem Lack of mutual affinity exploitation between nodes and attributes in graph convolution.
method Dual variational auto-encoders for node and attribute embeddings, Gaussian mixture model priors, mutual distance and clustering assignment hardening losses.
result Demonstrates effectiveness on real-world attributed network datasets.