We show that the skip-gram formulation of word2vec trained with negative sampling is equivalent to a weighted logistic PCA. This connection allows us to better understand the objective, compare it to other word embedding methods, and extend it to higher dimensional models.
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.
168,694 papers · 148 categories
Trend · papers per month
48 results for “skip-gram negative sampling”
Corrected CBOW performs similarly to Skip-gram.
problem CBOW embeddings underperform Skip-gram embeddings in word2vec.
method Fixed a bug in CBOW gradient update to improve performance.
result Corrected CBOW embeddings are competitive with Skip-gram on various tasks.
A new method learns dynamic graph representations from time-varying data.
problem Learning dynamic graph representations from time-varying data.
method Higher-order skip-gram with negative sampling (HOSGNS) for tensor factorization.
result HOSGNS outperforms state-of-the-art methods in downstream tasks.
This work shows dimension regularization can replace skip-gram negative sampling for graph embeddings, improving efficiency and performance.
problem Efficiently enforcing dissimilarity among node embeddings in graph learning.
method Dimension regularization as an alternative to skip-gram negative sampling.
result Dimension regularization is a more efficient approach to enforcing dissimilarity in graph embeddings.
We revisit skip-gram negative sampling (SGNS), one of the most popular neural-network based approaches to learning distributed word representation. We first point out the ambiguity issue undermining the SGNS model, in the sense that the word vectors can be entirely distorted without changing the objective value. To res…
Generates low-dimensional node vectors for graphs with privacy while preserving structural preferences.
problem Publishing graph node vectors can leak sensitive individual information.
method SE-PrivGEmb, a skip-gram based technique with a unified noise tolerance mechanism and negative sampling probabilities.
result Our method outperforms existing methods in structural equivalence and link prediction tasks.
Recent work has demonstrated that embeddings of tree-like graphs in hyperbolic space surpass their Euclidean counterparts in performance by a large margin. Inspired by these results and scale-free structure in the word co-occurrence graph, we present an algorithm for learning word embeddings in hyperbolic space from fr…
Proposes SNML for selecting word2vec Skip-gram dimensionality.
problem Selecting optimal dimensionality for word2vec Skip-gram models.
method Information criteria (AIC, BIC, SNML) applied to SG and SG Negative Sampling models.
result SNML outperforms AIC and BIC, selecting closer optimal dimensionality.
Although the word-popularity based negative sampler has shown superb performance in the skip-gram model, the theoretical motivation behind oversampling popular (non-observed) words as negative samples is still not well understood. In this paper, we start from an investigation of the gradient vanishing issue in the skip…
Since the invention of word2vec, the skip-gram model has significantly advanced the research of network embedding, such as the recent emergence of the DeepWalk, LINE, PTE, and node2vec approaches. In this work, we show that all of the aforementioned models with negative sampling can be unified into the matrix factoriza…
The Global Vectors for word representation (GloVe), introduced by Jeffrey Pennington et al. is reported to be an efficient and effective method for learning vector representations of words. State-of-the-art performance is also provided by skip-gram with negative-sampling (SGNS) implemented in the word2vec tool. In this…
Network representation learning, as an approach to learn low dimensional representations of vertices, has attracted considerable research attention recently. It has been proven extremely useful in many machine learning tasks over large graph. Most existing methods focus on learning the structural representations of ver…
Skip-gram with negative sampling, a popular variant of Word2vec originally designed and tuned to create word embeddings for Natural Language Processing, has been used to create item embeddings with successful applications in recommendation. While these fields do not share the same type of data, neither evaluate on the …
SCE improves network embedding using sparsest cut for negative samples only.
problem Efficient unsupervised network embedding using negative samples.
method Inspired by sparsest cut, SCE uses Laplacian smoothing for node representations.
result SCE outperforms GraphSAGE, G2G, and DGI in accuracy and scalability.
Network embedding techniques inspired by word2vec represent an effective unsupervised relational learning model. Commonly, by means of a Skip-Gram procedure, these techniques learn low dimensional vector representations of the nodes in a graph by sampling node-context examples. Although many ways of sampling the contex…
We simplify word embeddings by removing sigmoid in SGNS, revealing connections to hyperbolic spaces.
problem Improving word embeddings quality and understanding their relationship with hyperbolic spaces.
method Analyzing squashed shifted PMI matrix and its relation to graph properties and hyperbolic geometry.
result Word embeddings can be connected to hyperbolic spaces through squashed shifted PMI matrix.
The recently introduced continuous Skip-gram model is an efficient method for learning high-quality distributed vector representations that capture a large number of precise syntactic and semantic word relationships. In this paper we present several extensions that improve both the quality of the vectors and the traini…
InfiniteWalk connects deep network embeddings to spectral graph theory with a nonlinear transformation.
problem Learning node representations from networks with deep learning methods.
method Study of the DeepWalk objective in the limit as window size goes to infinity, linking to spectral graph embeddings with a nonlinear transformation.
result Simple binary thresholding of the Laplacian pseudoinverse can approximate DeepWalk embeddings.
Enhancing Network Embedding with Auxiliary Information: An Explicit Matrix Factorization Perspectivecs.SI
Recent advances in the field of network embedding have shown the low-dimensional network representation is playing a critical role in network analysis. However, most of the existing principles of network embedding do not incorporate auxiliary information such as content and labels of nodes flexibly. In this paper, we t…
Eliciting semantic similarity between concepts in the biomedical domain remains a challenging task. Recent approaches founded on embedding vectors have gained in popularity as they risen to efficiently capture semantic relationships The underlying idea is that two words that have close meaning gather similar contexts. …
Zipfian Whiteningcs.CL
PCA whitening weighted by Zipfian word frequencies improves task performance.
problem Skewed word embedding spaces in neural models.
method PCA whitening weighted by empirical word frequencies following Zipf's law.
result Significantly improves task performance, surpassing baselines.
Dynamic Word Embeddingsstat.ML
We present a probabilistic language model for time-stamped text data which tracks the semantic evolution of individual words over time. The model represents words and contexts by latent trajectories in an embedding space. At each moment in time, the embedding vectors are inferred from a probabilistic version of word2ve…
Word embeddings provide point representations of words containing useful semantic information. We introduce multimodal word distributions formed from Gaussian mixtures, for multiple word meanings, entailment, and rich uncertainty information. To learn these distributions, we propose an energy-based max-margin objective…
Representing networks in a low dimensional latent space is a crucial task with many interesting applications in graph learning problems, such as link prediction and node classification. A widely applied network representation learning paradigm is based on the combination of random walks for sampling context nodes and t…
New unsupervised method selects hard negative samples for contrastive learning.
problem How to select good negative examples for contrastive learning without using true similarity information.
method Developed a new family of unsupervised sampling methods for hard negative selection.
result Improves downstream performance across multiple modalities.
SANS uses graph structure to find meaningful negatives for entity and relation embeddings.
problem Finding hard negatives for entity and relation embeddings in knowledge graphs.
method Structure Aware Negative Sampling (SANS) that selects negatives from a node's k-hop neighborhood.
result SANS finds semantically meaningful negatives and is competitive with state-of-the-art approaches.
Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learningcs.LG
New framework analyzes why more negative samples improve self-supervised learning performance.
problem Inconsistency between theoretical degradation and empirical improvement of downstream supervised tasks with more negative samples.
method Coupon collector's problem framework to analyze self-supervised representation learning with more negative samples.
result Bound can implicitly incorporate supervised loss in self-supervised loss by increasing negative samples.
New insights into negative sampling for graph representation learning.
problem Challenges in generating high-quality graph representations for large node sets.
method Theoretical analysis and derivation of negative sampling distribution correlation, proposing MCNS method.
result The negative sampling distribution should be positively but sub-linearly correlated to the positive sampling distribution.
We describe a method for learning word embeddings with data-dependent dimensionality. Our Stochastic Dimensionality Skip-Gram (SD-SG) and Stochastic Dimensionality Continuous Bag-of-Words (SD-CBOW) are nonparametric analogs of Mikolov et al.'s (2013) well-known 'word2vec' models. Vector dimensionality is made dynamic b…
A new method improves graph node embeddings by considering both nearby and distant node similarities.
problem Improving graph node embeddings by considering both nearby and distant node similarities.
method Distance-aware Negative Sampling (DNS) which maximizes cohesion at nearby node-pairs and separation at distant node-pairs.
result DNS outperforms baseline methods in downstream node classification tasks on various datasets and GRL algorithms.
Unified interpretation of softmax cross-entropy and negative sampling for knowledge graph embedding.
problem Lack of theoretical relationship between softmax cross-entropy and negative sampling loss functions in knowledge graph embedding.
method Used Bregman divergence to provide a unified interpretation of the two loss functions.
result Theoretical findings for fair comparison of softmax cross-entropy and negative sampling are derived.
We present network embedding algorithms that capture information about a node from the local distribution over node attributes around it, as observed over random walks following an approach similar to Skip-gram. Observations from neighborhoods of different sizes are either pooled (AE) or encoded distinctly in a multi-s…
Extends conformal prediction to contrastive learning for better coverage of positive samples.
problem Lack of principled guarantees on coverage in contrastive learning.
method Introduces minimum-volume covering sets with learnable constraints.
result Improves inclusion-exclusion trade-offs in positive and negative samples.
Contrastive learning performance doesn't degrade with more negative samples.
problem Theoretical and empirical evidence of negative samples hurting performance in contrastive learning.
method Simple theoretical setting and empirical support on CIFAR-10 and CIFAR-100 datasets.
result Contrastive learning performance does not degrade with the number of negative samples.
In recent years, the Word2Vec model trained with the Negative Sampling loss function has shown state-of-the-art results in a number of machine learning tasks, including language modeling tasks, such as word analogy and word similarity, and in recommendation tasks, through Prod2Vec, an extension that applies to modeling…
Improved visual representation learning with conditional negative sampling.
problem Learning strong unsupervised visual representations using contrastive learning.
method Introduce a family of mutual information estimators that sample negatives conditionally.
result Improves accuracy by 2-5% points on four standard image datasets.
New theory shows how learning algorithms can create a bias towards negative outcomes.
problem Negativity bias in adaptive learning algorithms.
method Generalization of the Hot Stove Effect to settings with negative estimates leading to smaller sample sizes.
result Negativity bias persists even when negative estimates do not lead to avoidance.
Proposes a novel method for generating hard negatives near time series data boundaries.
problem Challenges in generating effective negative samples for time series anomaly detection.
method Reconstruction-driven boundary negative generation framework using reinforcement learning.
result Improves anomaly representation learning and achieves competitive detection performance.
Improved estimation for imbalanced data using log odds correction and optimal sampling.
problem Parameter estimation with nonuniform negative sampling for imbalanced data.
method Derive asymptotic distribution of IPW estimator, derive optimal sampling probability, propose likelihood-based estimator.
result Improved estimator has the smallest asymptotic variance.
State-of-the-art approaches for Knowledge Base Completion (KBC) exploit deep neural networks trained with both false and true assertions: positive assertions are explicitly taken from the knowledge base, whereas negative ones are generated by random sampling of entities. In this paper, we argue that random sampling is …
Paper connects sampling and labeling biases in large-output spaces.
problem Efficient training in large-output spaces with label imbalance.
method Unified approach to address sampling and labeling biases.
result Different negative sampling schemes trade-off performance on dominant and rare labels.
Enhances contrastive learning for better representation learning on wild images.
problem Binary partition of views from same and different instances limits CL's performance.
method Doubly Contrastive Learning (CACR) with contrastive attraction and repulsion.
result CACR improves performance and robustness on wild image datasets.
Proposes a new method for posterior sampling using MMD with negative distance kernel.
problem Posterior sampling and conditional generative modeling.
method Approximates joint distribution using discrete Wasserstein gradient flows of MMD with negative distance kernel.
result Establishes an error bound for posterior distributions and proves the method is a Wasserstein gradient flow.
We introduce Negative Sampling in Semi-Supervised Learning (NS3L), a simple, fast, easy to tune algorithm for semi-supervised learning (SSL). NS3L is motivated by the success of negative sampling/contrastive estimation. We demonstrate that adding the NS3L loss to state-of-the-art SSL algorithms, such as the Virtual Adv…
There is rising interest in vector-space word embeddings and their use in NLP, especially given recent methods for their fast estimation at very large scale. Nearly all this work, however, assumes a single vector per word type ignoring polysemy and thus jeopardizing their usefulness for downstream tasks. We present an …
Proposes a new method to improve regression models with reweighted samples.
problem Improves regression models' performance under low sample sizes and covariate perturbations.
method Reparametrizes sample weights using a doubly non-negative matrix and solves the reweighted estimate efficiently.
result Adversarial reweighting strategy delivers promising results on various datasets.
Training a classifier over a large number of classes, known as 'extreme classification', has become a topic of major interest with applications in technology, science, and e-commerce. Traditional softmax regression induces a gradient cost proportional to the number of classes , which often is prohibitively expensive…
The paper introduces the concept of a cluster structure to define a joint distribution of the sample size and its exchangeable random partitions. The cluster structure allows the probability distribution of the random partitions of a subset of the sample to be dependent on the sample size, a feature not presented in a …