Order-free Learning Alleviating Exposure Bias in Multi-label Classification
Multi-label classification (MLC) assigns multiple labels to each sample. Prior studies show that MLC can be transformed to a sequence prediction problem with a recurrent neural network (RNN) decoder to model the label dependency. However, training a RNN decoder requires a predefined order of labels, which is not directly available in the MLC specification. Besides, RNN thus trained tends to overfit the label combinations in the training set and have difficulty generating unseen label sequences. In this paper, we propose a new framework for MLC which does not rely on a predefined label order and thus alleviates exposure bias. The experimental results on three multi-label classification benchmark datasets show that our method outperforms competitive baselines by a large margin. We also find the proposed approach has a higher probability of generating label combinations not seen during training than the baseline models. The result shows that the proposed approach has better generalization capability.
Code (1)
Tasks
DecoderGeneral ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONSimilar Papers 제목 키워드 기반
Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps
Diffusion Probabilistic Models (DPM) have shown remarkable efficacy in the synthesis of high-quality images. However, their inference process characteristically requires numerous, potentially hundreds, of iterative steps…
DenoisingYour Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One
Autoregressive generative models are commonly used, especially for those tasks involving sequential data. They have, however, been plagued by a slew of inherent flaws due to the intrinsic characteristics of chain-style c…
Image GenerationLanguage ModelingLanguage ModellingMachine TranslationAlleviating Exposure Bias via Multi-level Contrastive Learning and Deviation Simulation in Abstractive Summarization
Most Transformer based abstractive summarization systems have a severe mismatch between training and inference, i.e., exposure bias. From diverse perspectives, we introduce a simple multi-level contrastive learning frame…
Abstractive Text SummarizationContrastive LearningDecoderFew-Shot LearningAlleviating Exposure Bias via Contrastive Learning for Abstractive Text Summarization
Encoder-decoder models have achieved remarkable success in abstractive text summarization, which aims to compress one or more documents into a shorter version without the loss of the essential content. Unfortunately, the…
Abstractive Text SummarizationContrastive LearningDecoderText SummarizationMinimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extraction
Joint entity and relation extraction aims to extract relation triplets from plain text directly. Prior work leverages Sequence-to-Sequence (Seq2Seq) models for triplet sequence generation. However, Seq2Seq enforces an un…
Joint Entity and Relation ExtractionRelationRelation ExtractionTriplet