# Inductive Learning on Commonsense Knowledge Graph Completion

arXiv: https://arxiv.org/abs/2009.09263 · HTML: https://mlsanity.com/paper/2009.09263/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2020.

## Built on by (most cited first, 22 of 22)

- [Large Language Models and Knowledge Graphs: Opportunities and Challenges](https://mlsanity.com/paper/2308.06374/) (2023)
- [Analyzing Commonsense Emergence in Few-shot Knowledge Models](https://mlsanity.com/paper/2101.00297/) (2021)
- [DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledge](https://mlsanity.com/paper/2101.00154/) (2021)
- [Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2112.10006/) (2021)
- [Improving Inductive Link Prediction Using Hyper-Relational Facts](https://mlsanity.com/paper/2107.04894/) (2021)
- [An Overview on Language Models: Recent Developments and Outlook](https://mlsanity.com/paper/2303.05759/) (2023)
- [BiQUE: Biquaternionic Embeddings of Knowledge Graphs](https://mlsanity.com/paper/2109.14401/) (2021)
- [Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization](https://mlsanity.com/paper/2206.01532/) (2022)
- [Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset](https://mlsanity.com/paper/2109.07679/) (2021)
- [Analyzing and Evaluating Faithfulness in Dialogue Summarization](https://mlsanity.com/paper/2210.11777/) (2022)
- [Knowledge Graph Embedding: An Overview](https://mlsanity.com/paper/2309.12501/) (2023)
- [Negative Sampling in Knowledge Graph Representation Learning: A Review](https://mlsanity.com/paper/2402.19195/) (2024)
- [MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation](https://mlsanity.com/paper/2210.07570/) (2022)
- [Dense-ATOMIC: Towards Densely-connected ATOMIC with High Knowledge Coverage and Massive Multi-hop Paths](https://mlsanity.com/paper/2210.07621/) (2022)
- [A Survey On Few-shot Knowledge Graph Completion with Structural and Commonsense Knowledge](https://mlsanity.com/paper/2301.01172/) (2023)
- [Towards Graph Foundation Models: Training on Knowledge Graphs Enables Transferability to General Graphs](https://mlsanity.com/paper/2410.12609/) (2024)
- [PseudoReasoner: Leveraging Pseudo Labels for Commonsense Knowledge Base Population](https://mlsanity.com/paper/2210.07988/) (2022)
- [Relational Sentence Embedding for Flexible Semantic Matching](https://mlsanity.com/paper/2212.08802/) (2022)
- [Commonsense Knowledge Graph Completion Via Contrastive Pretraining and Node Clustering](https://mlsanity.com/paper/2305.17019/) (2023)
- [Gold: A Global and Local-aware Denoising Framework for Commonsense Knowledge Graph Noise Detection](https://mlsanity.com/paper/2310.12011/) (2023)
- [Towards One-Shot Learning for Text Classification using Inductive Logic Programming](https://mlsanity.com/paper/2308.15885/) (2023)
- [EntailE: Introducing Textual Entailment in Commonsense Knowledge Graph Completion](https://mlsanity.com/paper/2402.09666/) (2024)

## Abstract (arXiv)

Commonsense knowledge graph (CKG) is a special type of knowledge graph (KG), where entities are composed of free-form text. However, most existing CKG completion methods focus on the setting where all the entities are presented at training time. Although this setting is standard for conventional KG completion, it has limitations for CKG completion. At test time, entities in CKGs can be unseen because they may have unseen text/names and entities may be disconnected from the training graph, since CKGs are generally very sparse. Here, we propose to study the inductive learning setting for CKG completion where unseen entities may present at test time. We develop a novel learning framework named InductivE. Different from previous approaches, InductiveE ensures the inductive learning capability by directly computing entity embeddings from raw entity attributes/text. InductiveE consists of a free-text encoder, a graph encoder, and a KG completion decoder. Specifically, the free-text encoder first extracts the textual representation of each entity based on the pre-trained language model and word embedding. The graph encoder is a gated relational graph convolutional neural network that learns from a densified graph for more informative entity representation learning. We develop a method that densifies CKGs by adding edges among semantic-related entities and provide more supportive information for unseen entities, leading to better generalization ability of entity embedding for unseen entities. Finally, inductiveE employs Conv-TransE as the CKG completion decoder. Experimental results show that InductiveE significantly outperforms state-of-the-art baselines in both standard and inductive settings on ATOMIC and ConceptNet benchmarks. InductivE performs especially well on inductive scenarios where it achieves above 48% improvement over present methods.