# Learning from Semi-Factuals: A Debiased and Semantic-Aware Framework for Generalized Relation Discovery

arXiv: https://arxiv.org/abs/2401.06327 · HTML: https://mlsanity.com/paper/2401.06327/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 59 references that are in the map.
- First posted on arXiv 12 Jan 2024.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Self-supervised Learning: Generative or Contrastive](https://mlsanity.com/paper/2006.08218/) (2020)
- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation](https://mlsanity.com/paper/1810.10147/) (2018)
- [Generalized Category Discovery](https://mlsanity.com/paper/2201.02609/) (2022)
- [Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2102.03526/) (2021)
- [Dynamic Conceptional Contrastive Learning for Generalized Category Discovery](https://mlsanity.com/paper/2303.17393/) (2023)
- [Supporting Clustering with Contrastive Learning](https://mlsanity.com/paper/2103.12953/) (2021)
- [Discovering New Intents with Deep Aligned Clustering](https://mlsanity.com/paper/2012.08987/) (2020)
- [On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learning](https://mlsanity.com/paper/2009.06399/) (2020)
- [SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction](https://mlsanity.com/paper/2004.02438/) (2020)
- [Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis](https://mlsanity.com/paper/2205.03784/) (2022)
- [A Rationale-Centric Framework for Human-in-the-loop Machine Learning](https://mlsanity.com/paper/2203.12918/) (2022)
- [Even if Explanations: Prior Work, Desiderata & Benchmarks for Semi-Factual XAI](https://mlsanity.com/paper/2301.11970/) (2023)
- [MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction](https://mlsanity.com/paper/2109.04108/) (2021)
- [A Relation-Oriented Clustering Method for Open Relation Extraction](https://mlsanity.com/paper/2109.07205/) (2021)
- [Unsupervised Open Relation Extraction](https://mlsanity.com/paper/1801.07174/) (2018)
- [Revisiting Unsupervised Relation Extraction](https://mlsanity.com/paper/2005.00087/) (2020)
- [Element Intervention for Open Relation Extraction](https://mlsanity.com/paper/2106.09558/) (2021)
- [Open Relation and Event Type Discovery with Type Abstraction](https://mlsanity.com/paper/2212.00178/) (2022)
- [Distantly-Supervised Long-Tailed Relation Extraction Using Constraint Graphs](https://mlsanity.com/paper/2105.11225/) (2021)
- [Pre-training to Match for Unified Low-shot Relation Extraction](https://mlsanity.com/paper/2203.12274/) (2022)
- [This changes to that : Combining causal and non-causal explanations to generate disease progression in capsule endoscopy](https://mlsanity.com/paper/2212.02506/) (2022)
- [Think Rationally about What You See: Continuous Rationale Extraction for Relation Extraction](https://mlsanity.com/paper/2305.03503/) (2023)
- [Actively Supervised Clustering for Open Relation Extraction](https://mlsanity.com/paper/2306.04968/) (2023)

## Built on by (most cited first, 2 of 2)

- [Category Discovery: An Open-World Perspective](https://mlsanity.com/paper/2509.22542/) (2025)
- [Few-shot Open Relation Extraction with Gaussian Prototype and Adaptive Margin](https://mlsanity.com/paper/2410.20320/) (2024)

## Abstract (arXiv)

We introduce a novel task, called Generalized Relation Discovery (GRD), for open-world relation extraction. GRD aims to identify unlabeled instances in existing pre-defined relations or discover novel relations by assigning instances to clusters as well as providing specific meanings for these clusters. The key challenges of GRD are how to mitigate the serious model biases caused by labeled pre-defined relations to learn effective relational representations and how to determine the specific semantics of novel relations during classifying or clustering unlabeled instances. We then propose a novel framework, SFGRD, for this task to solve the above issues by learning from semi-factuals in two stages. The first stage is semi-factual generation implemented by a tri-view debiased relation representation module, in which we take each original sentence as the main view and design two debiased views to generate semi-factual examples for this sentence. The second stage is semi-factual thinking executed by a dual-space tri-view collaborative relation learning module, where we design a cluster-semantic space and a class-index space to learn relational semantics and relation label indices, respectively. In addition, we devise alignment and selection strategies to integrate two spaces and establish a self-supervised learning loop for unlabeled data by doing semi-factual thinking across three views. Extensive experimental results show that SFGRD surpasses state-of-the-art models in terms of accuracy by 2.36% ~5.78% and cosine similarity by 32.19%~ 84.45% for relation label index and relation semantic quality, respectively. To the best of our knowledge, we are the first to exploit the efficacy of semi-factuals in relation extraction.