ACL Findings2024
FUSE: Measure-Theoretic Compact Fuzzy Set Representation for Taxonomy Expansion
Fred Xu, Song Jiang, Zijie Huang, Xiao Luo, Shichang Zhang, Yuanzhou Chen, Yizhou Sun
Abstract
Taxonomy Expansion, which models complex concepts and their relations, can be formulated as a set representation learning task. The generalization of set, fuzzy set, incorporates uncertainty and measures the information within a semantic concept, making it suitable for concept modeling. Existing works usually model sets as vectors or geometric objects such as boxes, which are not closed under set operations. In this work, we propose a sound and efficient formulation of set representation learning based on its volume approximation as a fuzzy set. The resulting embedding framework, Fuzzy Set Embedding (FUSE), satisfies all set operations and compactly approximates the underlying fuzzy set, hence preserving information while being efficient to learn, relying on minimum neural architecture. We empirically demonstrate the power of FUSE on the task of taxonomy expansion, where FUSE achieves remarkable improvements up to 23% compared with existing baselines. Our work marks the first attempt to understand and efficiently compute the embeddings of fuzzy sets.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
3 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs cites Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings
- Distributionally Robust Set Representation Learning Under Inference-Time Element Corruption cites Adversarial Encoding Perturbation and Synthesis for Set Representation Auxiliary Learning
Cited by top-tier papers3
- Adversarial Encoding Perturbation and Synthesis for Set Representation Auxiliary LearningYankai Chen, Xinni Zhang, Henry Peng Zou, Bowei He et al.ICLR 2026
- FLAIR: Steering LLM Mathematical Problem Solving based on A Fuzzy-Logic-AssIsted ReasonerHao Wu, Hongru Sun, Wanqing Li, Xinguo Yu et al.ACL 2026
- Distributionally Robust Set Representation Learning Under Inference-Time Element CorruptionYankai Chen, Hanrong Zhang, Bowei He, Philip Yu et al.ICML 2026
Builds on15
- Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box EmbeddingsHongyu Ren, Weihua Hu, Jure LeskovecICLR 2020 · 355 citations
- Structure-Augmented Text Representation Learning for Efficient Knowledge Graph CompletionBo Wang, Tao Shen, Guodong Long, Tianyi Zhou et al.WWW 2021 · 322 citations
- Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge GraphsHongyu Ren, Jure LeskovecNeurIPS 2020 · 267 citations
- TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural NetworkJiaming Shen, Zhihong Shen, Chenyan Xiong, Chi Wang et al.WWW 2020 · 85 citations
- Logic-induced Diagnostic Reasoning for Semi-supervised Semantic SegmentationChen Liang, Wenguan Wang, Jiaxu Miao, Yi YangICCV 2023 · 55 citations
Related papers
- TaxoBell: Gaussian Box Embeddings for Self-Supervised Taxonomy ExpansionSahil Mishra, Srinitish Srinivasan, Srikanta Bedathur, Tanmoy ChakrabortyWWW 2026 · 1 citation
- A Single Vector Is Not Enough: Taxonomy Expansion via Box EmbeddingsSong Jiang, Qiyue Yao, Qifan Wang, Yizhou SunWWW 2023 · 20 citations
- Universal Set Similarity Search via Multi-Task Representation LearningZhong Yang, Bolong Zheng, Guohui Li, Xi Zhao et al.ICDE 2025
- Word2Box: Capturing Set-Theoretic Semantics of Words using Box EmbeddingsShib Sankar Dasgupta, Michael Boratko, Siddhartha Mishra, Shriya Atmakuri et al.ACL 2022
- SetCSE: Set Operations using Contrastive Learning of Sentence EmbeddingsKang LiuICLR 2024 · 5 citations
