Related papers: Improving Text-based Early Prediction by Distillat…
In supervised machine learning, privileged information (PI) is information that is unavailable at inference, but is accessible during training time. Research on learning using privileged information (LUPI) aims to transfer the knowledge…
The use of large pretrained neural networks to create contextualized word embeddings has drastically improved performance on several natural language processing (NLP) tasks. These computationally expensive models have begun to be applied to…
Over the past year, the emergence of transfer learning with large-scale language models (LM) has led to dramatic performance improvements across a broad range of natural language understanding tasks. However, the size and memory footprint…
In natural language processing (NLP) tasks, slow inference speed and huge footprints in GPU usage remain the bottleneck of applying pre-trained deep models in production. As a popular method for model compression, knowledge distillation…
Pre-trained models like BERT (Devlin et al., 2018) have dominated NLP / IR applications such as single sentence classification, text pair classification, and question answering. However, deploying these models in real systems is highly…
Many of the affect modelling tasks present an asymmetric distribution of information between training and test time; additional information is given about the training data, which is not available at test time. Learning under this setting…
We introduce a learning framework called learning using privileged information (LUPI) to the computer vision field. We focus on the prototypical computer vision problem of teaching computers to recognize objects in images. We want the…
Large language models have led to significant progress across many NLP tasks, although their massive sizes often incur substantial computational costs. Distillation has become a common practice to compress these large and highly capable…
Structured prediction models aim at solving a type of problem where the output is a complex structure, rather than a single variable. Performing knowledge distillation for such models is not trivial due to their exponentially large output…
Large language models (LLMs) have gained extended context windows through scaling positional encodings and lightweight continual pre-training. However, this often leads to degraded performance on short-text tasks, while the reasons for this…
Sequential recommendation models user interests based on historical behaviors to provide personalized recommendation. Previous sequential recommendation algorithms primarily employ neural networks to extract features of user interests,…
Knowledge distillation methods have recently shown to be a promising direction to speedup the synthesis of large-scale diffusion models by requiring only a few inference steps. While several powerful distillation methods were recently…
Language models significantly benefit from context tokens, such as prompts or scratchpads. They perform better when prompted with informative instructions, and they acquire new reasoning capabilities by generating a scratch-pad before…
In learning-to-rank problems, a privileged feature is one that is available during model training, but not available at test time. Such features naturally arise in merchandised recommendation systems; for instance, "user clicked this item"…
Training deep neural networks from scratch on natural language processing (NLP) tasks requires significant amount of manually labeled text corpus and substantial time to converge, which usually cannot be satisfied by the customers. In this…
In this paper we present a technique of NLP to tackle the problem of inference relation (NLI) between pairs of sentences in a target language of choice without a language-specific training dataset. We exploit a generic translation dataset,…
This paper studies the problem of pre-training for small models, which is essential for many mobile devices. Current state-of-the-art methods on this problem transfer the representational knowledge of a large network (as a Teacher) into a…
Deep networks tend to learn spurious feature-label correlations in real-world supervised learning tasks. This vulnerability is aggravated in distillation, where a student model may have lesser representational capacity than the…
We propose selective debiasing -- an inference-time safety mechanism designed to enhance the overall model quality in terms of prediction performance and fairness, especially in scenarios where retraining the model is impractical. The…
Biomedical literature is a rapidly expanding field of science and technology. Classification of biomedical texts is an essential part of biomedicine research, especially in the field of biology. This work proposes the fine-tuned DistilBERT,…