Funnelling: A New Ensemble Method for Heterogeneous Transfer Learning and its Application to Cross-Lingual Text Classification
Cross-lingual Text Classification (CLC) consists of automatically classifying, according to a common set C of classes, documents each written in one of a set of languages L, and doing so more accurately than when naively classifying each document via its corresponding language-specific classifier. In order to obtain an increase in the classification accuracy for a given language, the system thus needs to also leverage the training examples written in the other languages. We tackle multilabel CLC via funnelling, a new ensemble learning method that we propose here. Funnelling consists of generating a two-tier classification system where all documents, irrespectively of language, are classified by the same (2nd-tier) classifier. For this classifier all documents are represented in a common, language-independent feature space consisting of the posterior probabilities generated by 1st-tier, language-dependent classifiers. This allows the classification of all test documents, of any language, to benefit from the information present in all training documents, of any language. We present substantial experiments, run on publicly available multilingual text collections, in which funnelling is shown to significantly outperform a number of state-of-the-art baselines. All code and datasets (in vector form) are made publicly available.
Code (2)
Tasks
AllClassificationEnsemble LearningGeneral Classificationtext-classificationText ClassificationTransfer LearningSimilar Papers 제목 키워드 기반
Generalized Funnelling: Ensemble Learning and Heterogeneous Document Embeddings for Cross-Lingual Text Classification
\emph{Funnelling} (Fun) is a recently proposed method for cross-lingual text classification (CLTC) based on a two-tier learning ensemble for heterogeneous transfer learning (HTL). In this ensemble method, 1st-tier classi…
Ensemble LearningMultilabel Text Classificationtext-classificationText Classification+1Boosting Adversarial Transferability via Ensemble Non-Attention
Ensemble attacks integrate the outputs of surrogate models with diverse architectures, which can be combined with various gradient-based attacks to improve adversarial transferability. However, previous work shows unsati…
Ensemble Diversity Facilitates Adversarial Transferability
With the advent of ensemble-based attacks the transferability of generated adversarial examples is elevated by a noticeable margin despite many methods only employing superficial integration yet ignoring the diversit…
Diversityreinforcement-learningReinforcement LearningHeterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning
Federated learning (FL) enables edge-devices to collaboratively learn a model without disclosing their private data to a central aggregating server. Most existing FL algorithms require models of identical architecture to…
DiversityEnsemble LearningFederated LearningTransfer LearningEdgeConvEns: Convolutional Ensemble Learning for Edge Intelligence
Deep edge intelligence aims to deploy deep learning models that demand computationally expensive training in the edge network with limited computational power. Moreover, many deep edge intelligence applications require h…
Ensemble LearningFederated Learning