paper-with-me

Papers

Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor

2020-10-10 · ACL 2021 5 · Xinyu Wang, Yong Jiang, Zhaohui Yan, Zixia Jia, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

Knowledge distillation is a critical technique to transfer knowledge between models, typically from a large model (the teacher) to a more fine-grained one (the student). The objective function of knowledge distillation is typically the cross-entropy between the teacher and the student's output distributions. However, for structured prediction problems, the output space is exponential in size; therefore, the cross-entropy objective becomes intractable to compute and optimize directly. In this paper, we derive a factorized form of the knowledge distillation objective for structured prediction, which is tractable for many typical choices of the teacher and student models. In particular, we show the tractability and empirical effectiveness of structural knowledge distillation between sequence labeling and dependency parsing models under four different scenarios: 1) the teacher and student share the same factorization form of the output structure scoring function; 2) the student factorization produces more fine-grained substructures than the teacher factorization; 3) the teacher factorization produces more fine-grained substructures than the student factorization; 4) the factorization forms from the teacher and the student are incompatible.

📄 PDF Abstract BibTeX arXiv:2010.05010

Code (1)

Alibaba-NLP/StructuralKD 공식 구현 pytorch

Tasks

Dependency ParsingKnowledge DistillationStructured Prediction

Methods 이 논문이 사용한 방법론

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.…

Similar Papers 제목 키워드 기반

Exploring Graph-based Knowledge: Multi-Level Feature Distillation via Channels Relational Graph

2024-05-14 · Zhiwei Wang, Jun Huang, Longhua Ma, Chengyu Wu 외

In visual tasks, large teacher models capture essential features and deep information, enhancing performance. However, distilling this information into smaller student models often leads to performance loss due to struct…

Multi-Granularity Structural Knowledge Distillation for Language Model Compression

2022-05-01 · ACL 2022 5 · Chang Liu, Chongyang Tao, Jiazhan Feng, Dongyan Zhao

Transferring the knowledge to a small model through distillation has raised great interest in recent years. Prevailing methods transfer the knowledge derived from mono-granularity language units (e.g., token-level or sam…

Knowledge DistillationLanguage ModelingLanguage ModellingModel Compression+1

On Distilling the Displacement Knowledge for Few-Shot Class-Incremental Learning

2024-12-15 · Pengfei Fang, Yongchun Qin, Hui Xue

Few-shot Class-Incremental Learning (FSCIL) addresses the challenges of evolving data distributions and the difficulty of data acquisition in real-world scenarios. To counteract the catastrophic forgetting typically enco…

class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental Learning+1

Edge-free but Structure-aware: Prototype-Guided Knowledge Distillation from GNNs to MLPs

2023-03-24 · Taiqiang Wu, Zhe Zhao, Jiahao Wang, Xingyu Bai 외

Distilling high-accuracy Graph Neural Networks (GNNs) to low-latency multilayer perceptions (MLPs) on graph tasks has become a hot research topic. However, conventional MLP learning relies almost exclusively on graph nod…

Knowledge Distillation

Contrastive Representation Distillation

2019-10-23 · ICLR 2020 1 · Yonglong Tian, Dilip Krishnan, Phillip Isola

Often we wish to transfer representational knowledge from one neural network to another. Examples include distilling a large network into a smaller one, transferring knowledge from one sensory modality to a second, or en…

Contrastive LearningKnowledge DistillationModel CompressionTransfer Learning