1 code implementation • ACL 2022 • Xin Mao, Meirong Ma, Hao Yuan, Jianchao Zhu, ZongYu Wang, Rui Xie, Wei Wu, Man Lan
Entity alignment (EA) aims to discover the equivalent entity pairs between KGs, which is a crucial step for integrating multi-source KGs. For a long time, most researchers have regarded EA as a pure graph representation learning task and focused on improving graph encoders while paying little attention to the decoding process. In this paper, we propose an effective and efficient EA Decoding Algorithm via Third-order Tensor Isomorphism (DATTI). Specifically, we derive two sets of isomorphism equations: (1) Adjacency tensor isomorphism equations and (2) Gramian tensor isomorphism equations. By combining these equations, DATTI could effectively utilize the adjacency and inner correlation isomorphisms of KGs to enhance the decoding process of EA. Extensive experiments on public datasets indicate that our decoding algorithm can deliver significant performance improvements even on the most advanced EA methods, while the extra required time is less than 3 seconds.
no code implementations • 2 Mar 2024 • Li Cai, Xin Mao, Yuhao Zhou, Zhaoguang Long, Changxu Wu, Man Lan
Knowledge graph representation learning aims to learn low-dimensional vector embeddings for entities and relations in a knowledge graph.
no code implementations • 2 Mar 2024 • Li Cai, Xin Mao, Zhihong Wang, Shangqing Zhao, Yuhao Zhou, Changxu Wu, Man Lan
Temporal knowledge graph completion (TKGC) aims to fill in missing facts within a given temporal knowledge graph at a specific time.
Knowledge Graph Completion Temporal Knowledge Graph Completion
1 code implementation • 25 Feb 2024 • Xin Mao, Feng-Lin Li, Huimin Xu, Wei zhang, Anh Tuan Luu
While Reinforcement Learning from Human Feedback (RLHF) significantly enhances the generation quality of Large Language Models (LLMs), recent studies have raised concerns regarding the complexity and instability associated with the Proximal Policy Optimization (PPO) algorithm, proposing a series of order-based calibration methods as viable alternatives.
1 code implementation • 9 Oct 2023 • Bolin Zhu, Xiaoze Liu, Xin Mao, Zhuo Chen, Lingbing Guo, Tao Gui, Qi Zhang
The objective of Entity Alignment (EA) is to identify equivalent entity pairs from multiple Knowledge Graphs (KGs) and create a more comprehensive and unified KG.
1 code implementation • 12 Jul 2023 • Li Cai, Xin Mao, Youshao Xiao, Changxu Wu, Man Lan
Entity alignment (EA) aims to find the equivalent entity pairs between different knowledge graphs (KGs), which is crucial to promote knowledge fusion.
2 code implementations • 19 Oct 2022 • Xin Mao, Wenting Wang, Yuanbin Wu, Man Lan
Entity Alignment (EA) aims to find equivalent entity pairs between KGs, which is the core step of bridging and integrating multi-source KGs.
Ranked #1 on Entity Alignment on DBP1M DE-EN
1 code implementation • COLING 2022 • Li Cai, Xin Mao, Meirong Ma, Hao Yuan, Jianchao Zhu, Man Lan
However, we believe that it is not necessary to learn the embeddings of temporal information in KGs since most TKGs have uniform temporal representations.
1 code implementation • EMNLP 2021 • Xin Mao, Wenting Wang, Yuanbin Wu, Man Lan
Cross-lingual entity alignment (EA) aims to find the equivalent entities between crosslingual KGs, which is a crucial step for integrating KGs.
Ranked #4 on Entity Alignment on dbp15k fr-en (using extra training data)
1 code implementation • 11 Aug 2021 • Xin Mao, Wenting Wang, Yuanbin Wu, Man Lan
Entity alignment (EA) aims to find the equivalent entities in different KGs, which is a crucial step in integrating multiple KGs.
Ranked #6 on Entity Alignment on dbp15k ja-en (using extra training data)
1 code implementation • 29 Mar 2021 • Xin Mao, Wenting Wang, Yuanbin Wu, Man Lan
Seeking the equivalent entities among multi-source Knowledge Graphs (KGs) is the pivotal step to KGs integration, also known as \emph{entity alignment} (EA).
Ranked #2 on Entity Alignment on YAGO-WIKI50K
2 code implementations • 18 Aug 2020 • Xin Mao, Wenting Wang, Huimin Xu, Yuanbin Wu, Man Lan
Entity alignment aims to identify equivalent entity pairs from different Knowledge Graphs (KGs), which is essential in integrating multi-source KGs.
Ranked #3 on Entity Alignment on DICEWS-1K
1 code implementation • The International Conference on Web Search and Data Mining (WSDM) 2020 • Xin Mao, Wenting Wang, Huimin Xu, Man Lan, Yuanbin Wu
To tackle these challenges, we propose a novel Meta Relation Aware Entity Alignment (MRAEA) to directly model cross-lingual entity embeddings by attending over the node's incoming and outgoing neighbors and its connected relations' meta semantics.
Ranked #17 on Entity Alignment on DBP15k zh-en
no code implementations • 2 Dec 2019 • Xin Mao, Zhaoyu Su, Pin Siang Tan, Jun Kang Chow, Yu-Hsing Wang
From this perspective and combined with further analyses, we found that to avoid mode collapse, the features extracted by the discriminator are not guided to be different for the real samples, but divergence without noise is indeed allowed and occupies a large proportion of the feature space.
2 code implementations • ACL 2019 • Huimin Xu, Wenting Wang, Xin Mao, Xinyu Jiang, Man Lan
Supplementing product information by extracting attribute values from title is a crucial task in e-Commerce domain.
no code implementations • SEMEVAL 2018 • Xingwu Lu, Xin Mao, Man Lan, Yuanbin Wu
This paper describes our submissions to Task 2 in SemEval 2018, i. e., Multilingual Emoji Prediction.