paper-with-me

홈 › Papers

Exploring the Limits of Simple Learners in Knowledge Distillation for Document Classification with DocBERT

2020-07-01 · WS 2020 7 · Ashutosh Adhikari, Achyudh Ram, Raphael Tang, William L. Hamilton, Jimmy Lin

Fine-tuned variants of BERT are able to achieve state-of-the-art accuracy on many natural language processing tasks, although at significant computational costs. In this paper, we verify BERT{'}s effectiveness for document classification and investigate the extent to which BERT-level effectiveness can be obtained by different baselines, combined with knowledge distillation{---}a popular model compression method. The results show that BERT-level effectiveness can be achieved by a single-layer LSTM with at least $40\times$ fewer FLOPS and only ${\sim}3\%$ parameters. More importantly, this study analyzes the limits of knowledge distillation as we distill BERT{'}s knowledge all the way down to linear models{---}a relevant baseline for the task. We report substantial improvement in effectiveness for even the simplest models, as they capture the knowledge learnt by BERT.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Document ClassificationGeneral ClassificationKnowledge DistillationModel Compression

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…
Weight Decay 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Adam 설명 없음
Multi-Head Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…

Similar Papers 제목 키워드 기반

Linkless Link Prediction via Relational Distillation

2022-10-11 · Zhichun Guo, William Shiao, Shichang Zhang, Yozen Liu 외

Graph Neural Networks (GNNs) have shown exceptional performance in the task of link prediction. Despite their effectiveness, the high latency brought by non-trivial neighborhood data dependency limits GNNs in practical d…

Knowledge DistillationLink PredictionNode ClassificationPrediction

Learning Behavior-oriented Knowledge Tracing

2023-08-06 · ACM SIGKDD Conference on Knowledge Discovery and Data Mining 2023 8 · Xu, Bihan and Huang, Zhenya and Liu, Jiayu and Shen 외

Exploring how learners' knowledge states evolve during the learning activities is a critical task in online learning systems, which can facilitate personalized services downstream, such as course recommendation. Most of …

Knowledge Tracing

Cooperative Knowledge Distillation: A Learner Agnostic Approach

2024-02-02 · Michael Livanos, Ian Davidson, Stephen Wong

Knowledge distillation is a simple but powerful way to transfer knowledge between a teacher model to a student model. Existing work suffers from at least one of the following key limitations in terms of direction and sco…

counterfactualKnowledge DistillationSelf-Supervised LearningTransfer Learning

Leveraging Graph Retrieval-Augmented Generation to Support Learners' Understanding of Knowledge Concepts in MOOCs

2025-05-15 · Mohamed Abdelmagied, Mohamed Amine Chatti, Shoeb Joarder, Qurat Ul Ain 외

Massive Open Online Courses (MOOCs) lack direct interaction between learners and instructors, making it challenging for learners to understand new knowledge concepts. Recently, learners have increasingly used Large Langu…

Knowledge GraphsQuestion AnsweringQuestion GenerationQuestion-Generation+2

Exploring the Limits of Model Compression in LLMs: A Knowledge Distillation Study on QA Tasks

2025-07-10 · Joyeeta Datta, Niclas Doll, Qusai Ramadan, Zeyd Boukhers arxiv

Large Language Models (LLMs) have demonstrated outstanding performance across a range of NLP tasks, however, their computational demands hinder their deployment in real-world, resource-constrained environments. This work…

Knowledge DistillationQuestion AnsweringModel Compression