# Finding Influential Instances for Distantly Supervised Relation Extraction

arXiv: https://arxiv.org/abs/2009.09841 · HTML: https://mlsanity.com/paper/2009.09841/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2020.

## Built on by (most cited first, 13 of 13)

- [KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction](https://mlsanity.com/paper/2104.07650/) (2021)
- [Document-level Relation Extraction as Semantic Segmentation](https://mlsanity.com/paper/2106.03618/) (2021)
- [PRGC: Potential Relation and Global Correspondence Based Joint Relational Triple Extraction](https://mlsanity.com/paper/2106.09895/) (2021)
- [Learning from Noisy Labels for Entity-Centric Information Extraction](https://mlsanity.com/paper/2104.08656/) (2021)
- [PAC-Bayes Information Bottleneck](https://mlsanity.com/paper/2109.14509/) (2021)
- [DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population](https://mlsanity.com/paper/2201.03335/) (2022)
- [Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuning](https://mlsanity.com/paper/2205.02355/) (2022)
- [Information Extraction in Low-Resource Scenarios: Survey and Perspective](https://mlsanity.com/paper/2202.08063/) (2022)
- [Towards Better Document-level Relation Extraction via Iterative Inference](https://mlsanity.com/paper/2211.14470/) (2022)
- [Normal vs. Adversarial: Salience-based Analysis of Adversarial Samples for Relation Extraction](https://mlsanity.com/paper/2104.00312/) (2021)
- [A Densely Connected Criss-Cross Attention Network for Document-level Relation Extraction](https://mlsanity.com/paper/2203.13953/) (2022)
- [NC-DRE: Leveraging Non-entity Clue Information for Document-level Relation Extraction](https://mlsanity.com/paper/2204.00255/) (2022)
- [On Influence Functions, Classification Influence, Relative Influence, Memorization and Generalization](https://mlsanity.com/paper/2305.16094/) (2023)

## Abstract (arXiv)

Distant supervision (DS) is a strong way to expand the datasets for enhancing relation extraction (RE) models but often suffers from high label noise. Current works based on attention, reinforcement learning, or GAN are black-box models so they neither provide meaningful interpretation of sample selection in DS nor stability on different domains. On the contrary, this work proposes a novel model-agnostic instance sampling method for DS by influence function (IF), namely REIF. Our method identifies favorable/unfavorable instances in the bag based on IF, then does dynamic instance sampling. We design a fast influence sampling algorithm that reduces the computational complexity from O(mn) to O(1), with analyzing its robustness on the selected sampling function. Experiments show that by simply sampling the favorable instances during training, REIF is able to win over a series of baselines that have complicated architectures. We also demonstrate that REIF can support interpretable instance selection.