# Self-Distillation with Meta Learning for Knowledge Graph Completion

arXiv: https://arxiv.org/abs/2305.12209 · HTML: https://mlsanity.com/paper/2305.12209/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Graph neural network distillation, one of 12 directions in Knowledge distillation.
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 20 May 2023.

## Placed in

- Knowledge distillation / [Graph neural network distillation](https://mlsanity.com/distill/graph-neural-network-distillation/)

## Builds on (most cited first, 19 of 19)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://mlsanity.com/paper/1710.01878/) (2017)
- [One-Shot Relational Learning for Knowledge Graphs](https://mlsanity.com/paper/1808.09040/) (2018)
- [Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks](https://mlsanity.com/paper/1903.01306/) (2019)
- [Adaptive Attentional Network for Few-Shot Knowledge Graph Completion](https://mlsanity.com/paper/2010.09638/) (2020)
- [Faster Meta Update Strategy for Noise-Robust Deep Learning](https://mlsanity.com/paper/2104.15092/) (2021)
- [Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations](https://mlsanity.com/paper/2110.02834/) (2021)
- [Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion](https://mlsanity.com/paper/2011.05816/) (2020)
- [Evaluating the Impact of Knowledge Graph Context on Entity Disambiguation Models](https://mlsanity.com/paper/2008.05190/) (2020)
- [Probabilistic Reasoning via Deep Learning: Neural Association Models](https://mlsanity.com/paper/1603.07704/) (2016)
- [SCL-RAI: Span-based Contrastive Learning with Retrieval Augmented Inference for Unlabeled Entity Problem in NER](https://mlsanity.com/paper/2209.01646/) (2022)
- [SANTA: Separate Strategies for Inaccurate and Incomplete Annotation Noise in Distantly-Supervised Named Entity Recognition](https://mlsanity.com/paper/2305.04076/) (2023)

## Built on by (most cited first, 1 of 1)

- [DuetGraph: Coarse-to-Fine Knowledge Graph Reasoning with Dual-Pathway Global-Local Fusion](https://mlsanity.com/paper/2507.11229/) (2025)

## Abstract (arXiv)

In this paper, we propose a selfdistillation framework with meta learning(MetaSD) for knowledge graph completion with dynamic pruning, which aims to learn compressed graph embeddings and tackle the longtail samples. Specifically, we first propose a dynamic pruning technique to obtain a small pruned model from a large source model, where the pruning mask of the pruned model could be updated adaptively per epoch after the model weights are updated. The pruned model is supposed to be more sensitive to difficult to memorize samples(e.g., longtail samples) than the source model. Then, we propose a onestep meta selfdistillation method for distilling comprehensive knowledge from the source model to the pruned model, where the two models coevolve in a dynamic manner during training. In particular, we exploit the performance of the pruned model, which is trained alongside the source model in one iteration, to improve the source models knowledge transfer ability for the next iteration via meta learning. Extensive experiments show that MetaSD achieves competitive performance compared to strong baselines, while being 10x smaller than baselines.