paper-with-me

Papers

Mutually-paced Knowledge Distillation for Cross-lingual Temporal Knowledge Graph Reasoning

2023-03-27 · Ruijie Wang, Zheng Li, Jingfeng Yang, Tianyu Cao, Chao Zhang, Bing Yin, Tarek Abdelzaher

This paper investigates cross-lingual temporal knowledge graph reasoning problem, which aims to facilitate reasoning on Temporal Knowledge Graphs (TKGs) in low-resource languages by transfering knowledge from TKGs in high-resource ones. The cross-lingual distillation ability across TKGs becomes increasingly crucial, in light of the unsatisfying performance of existing reasoning methods on those severely incomplete TKGs, especially in low-resource languages. However, it poses tremendous challenges in two aspects. First, the cross-lingual alignments, which serve as bridges for knowledge transfer, are usually too scarce to transfer sufficient knowledge between two TKGs. Second, temporal knowledge discrepancy of the aligned entities, especially when alignments are unreliable, can mislead the knowledge distillation process. We correspondingly propose a mutually-paced knowledge distillation model MP-KD, where a teacher network trained on a source TKG can guide the training of a student network on target TKGs with an alignment module. Concretely, to deal with the scarcity issue, MP-KD generates pseudo alignments between TKGs based on the temporal information extracted by our representation module. To maximize the efficacy of knowledge transfer and control the noise caused by the temporal knowledge discrepancy, we enhance MP-KD with a temporal cross-lingual attention mechanism to dynamically estimate the alignment strength. The two procedures are mutually paced along with model training. Extensive experiments on twelve cross-lingual TKG transfer tasks in the EventKG benchmark demonstrate the effectiveness of the proposed MP-KD method.

📄 PDF Abstract BibTeX arXiv:2303.14898

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationKnowledge GraphsTransfer Learning

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

D$^2$TV: Dual Knowledge Distillation and Target-oriented Vision Modeling for Many-to-Many Multimodal Summarization

2023-05-22 · Yunlong Liang, Fandong Meng, Jiaan Wang, Jinan Xu 외

Many-to-many multimodal summarization (M$^3$S) task aims to generate summaries in any language with document inputs in any language and the corresponding image sequence, which essentially comprises multimodal monolingual…

Knowledge Distillation

Joint Representation Learning of Cross-lingual Words and Entities via Attentive Distant Supervision

2018-11-27 · EMNLP 2018 10 · Yixin Cao, Lei Hou, Juanzi Li, Zhiyuan Liu 외

Joint representation learning of words and entities benefits many NLP tasks, but has not been well explored in cross-lingual settings. In this paper, we propose a novel method for joint representation learning of cross-l…

Cross-Lingual Entity LinkingEntity LinkingRepresentation LearningTranslation+1

Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification

2020-01-06 · ECCV 2020 8 · Liuyu Xiang, Guiguang Ding, Jungong Han

In real-world scenarios, data tends to exhibit a long-tailed distribution, which increases the difficulty of training deep networks. In this paper, we propose a novel self-paced knowledge distillation framework, termed L…

General ClassificationKnowledge DistillationLong-tail Learning

Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching

2022-09-13 · Findings (NAACL) 2022 7 · Kunbo Ding, Weijie Liu, Yuejian Fang, Zhe Zhao 외

Previous studies have proved that cross-lingual knowledge distillation can significantly improve the performance of pre-trained models for cross-lingual similarity matching tasks. However, the student model needs to be l…

Contrastive LearningKnowledge DistillationSemantic SimilaritySemantic Textual Similarity+1

Right Time to Learn:Promoting Generalization via Bio-inspired Spacing Effect in Knowledge Distillation

2025-02-10 · Guanglong Sun, HongWei Yan, Liyuan Wang, Qian Li 외

Knowledge distillation (KD) is a powerful strategy for training deep neural networks (DNNs). Although it was originally proposed to train a more compact "student" model from a large "teacher" model, many recent efforts h…

Knowledge Distillation