Fast Label Embeddings for Extremely Large Output Spaces
Many modern multiclass and multilabel problems are characterized by increasingly large output spaces. For these problems, label embeddings have been shown to be a useful primitive that can improve computational and statistical efficiency. In this work we utilize a correspondence between rank constrained estimation and low dimensional label embeddings that uncovers a fast label embedding algorithm which works in both the multiclass and multilabel settings. The result is a randomized algorithm for partial least squares, whose running time is exponentially faster than naive algorithms. We demonstrate our techniques on two large-scale public datasets, from the Large Scale Hierarchical Text Challenge and the Open Directory Project, where we obtain state of the art results.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Fast Label Embeddings via Randomized Linear Algebra
Many modern multiclass and multilabel problems are characterized by increasingly large output spaces. For these problems, label embeddings have been shown to be a useful primitive that can improve computational and stati…
Multi-View Learning of Word Embeddings via CCA
Recently, there has been substantial interest in using large amounts of unlabeled data to learn word representations which can then be used as features in supervised classifiers for NLP tasks. However, most current appro…
ChunkingMULTI-VIEW LEARNINGnamed-entity-recognitionNamed Entity Recognition+3Towards Characterizing Cyber Networks with Large Language Models
Threat hunting analyzes large, noisy, high-dimensional data to find sparse adversarial behavior. We believe adversarial activities, however they are disguised, are extremely difficult to completely obscure in high dimens…
Language ModelingLanguage ModellingSOLAR: Sparse Orthogonal Learned and Random Embeddings
Dense embedding models are commonly deployed in commercial search engines, wherein all the document vectors are pre-computed, and near-neighbor search (NNS) is performed with the query vector to find relevant documents. …
Multi-Label ClassificationMUlTI-LABEL-ClASSIFICATIONE-Stitchup: Data Augmentation for Pre-Trained Embeddings
In this work, we propose data augmentation methods for embeddings from pre-trained deep learning models that take a weighted combination of a pair of input embeddings, as inspired by Mixup, and combine such augmentation …
Data AugmentationGeneral ClassificationTransfer Learning