mlsanityData to 7 Oct 2026

MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation

arXiv 2210.07570 ↗First posted 14 Oct 2022cs.CLcited by 6

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Commonsense reasoning tasks such as commonsense knowledge graph completion and commonsense question answering require powerful representation learning. In this paper, we propose to learn commonsense knowledge representation by MICO, a Multi-alternative contrastve learning framework on COmmonsense knowledge graphs (MICO). MICO generates the commonsense knowledge representation by contextual interaction between entity nodes and relations with multi-alternative contrastive learning. In MICO, the head and tail entities in an (h,r,t) knowledge triple are converted to two relation-aware sequence pairs (a premise and an alternative) in the form of natural language. Semantic representations generated by MICO can benefit the following two tasks by simply comparing the distance score between the representations: 1) zero-shot commonsense question answering task; 2) inductive commonsense knowledge graph completion task. Extensive experiments show the effectiveness of our method.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 32 of its 50 references that are in the map. First posted on arXiv 14 Oct 2022.

Builds on

32 of 50 references.

References · 32

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,818
  6. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  7. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  8. 2019Contrastive Multiview Codingcited by 1,297
  9. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  10. 2016Complex Embeddings for Simple Link Predictioncited by 897
  11. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 893
  12. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
20 more
  1. 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
  2. 2019COMET: Commonsense Transformers for Automatic Knowledge Graph Constructioncited by 450
  3. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  4. 2018SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inferencecited by 333
  5. 2019KG-BERT: BERT for Knowledge Graph Completioncited by 323
  6. 2020COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphscited by 254
  7. 2019KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoningcited by 216
  8. 2022GreaseLM: Graph REASoning Enhanced Language Models for Question Answeringcited by 170
  9. 2020Unsupervised Commonsense Question Answering with Self-Talkcited by 161
  10. 2018End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completioncited by 136
  11. 2020Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answeringcited by 122
  12. 2019Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answeringcited by 68
  13. 2019Commonsense Knowledge Base Completion with Structural and Semantic Contextcited by 61
  14. 2020Fusing Context Into Knowledge Graph for Commonsense Question Answeringcited by 33
  15. 2020Self-supervised Knowledge Triplet Learning for Zero-shot Question Answeringcited by 29
  16. 2021DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledgecited by 26
  17. 2019Ranking and Selecting Multi-Hop Knowledge Paths to Better Predict Human Needscited by 22
  18. 2020Inductive Learning on Commonsense Knowledge Graph Completioncited by 22
  19. 2022Zero-shot Commonsense Question Answering with Cloze Translation and Consistency Optimizationcited by 13
  20. 2022CAKE: A Scalable Commonsense-Aware Framework For Multi-View Knowledge Graph Completioncited by 13

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 2.

6 papers.

  1. 2023CAT: A Contextualized Conceptualization and Instantiation Framework for Commonsense Reasoningcited by 25
  2. 2023Commonsense Knowledge Graph Completion Via Contrastive Pretraining and Node Clusteringcited by 4
  3. 2023Gold: A Global and Local-aware Denoising Framework for Commonsense Knowledge Graph Noise Detectioncited by 4
  4. 2023BUCA: A Binary Classification Approach to Unsupervised Commonsense Question Answeringcited by 3
  5. 2024PipeNet: Question Answering with Semantic Pruning over Knowledge Graphscited by 1
  6. 2024EntailE: Introducing Textual Entailment in Commonsense Knowledge Graph Completioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022elBERto: Self-supervised Commonsense Learning for Question Answering
  2. 2023Visual Commonsense based Heterogeneous Graph Contrastive Learning
  3. 2024G-SAP: Graph-based Structure-Aware Prompt Learning over Heterogeneous Knowledge for Commonsense Reasoning
  4. 2023Multi-hop Commonsense Knowledge Injection Framework for Zero-Shot Commonsense Question Answering
  5. 2022CIKQA: Learning Commonsense Inference with a Unified Knowledge-in-the-loop QA Paradigm
  6. 2022Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
  7. 2024ZEBRA: Zero-Shot Example-Based Retrieval Augmentation for Commonsense Question Answering
  8. 2022TSGP: Two-Stage Generative Prompting for Unsupervised Commonsense Question Answering