Rethinking uncertainly missing and ambiguous visual modality in multi-modal entity alignment

Z Chen, L Guo, Y Fang, Y Zhang, J Chen… - International Semantic …, 2023 - Springer
As a crucial extension of entity alignment (EA), multi-modal entity alignment (MMEA) aims to
identify identical entities across disparate knowledge graphs (KGs) by exploiting associated …

Robust Link Prediction over Noisy Hyper-Relational Knowledge Graphs via Active Learning

W Yu, J Yang, D Yang - Proceedings of the ACM on Web Conference …, 2024 - dl.acm.org
Modern Knowledge Graphs (KGs) are inevitably noisy due to the nature of their construction
process. Existing robust learning techniques for noisy KGs mostly focus on triple facts, where …

ReliK: A Reliability Measure for Knowledge Graph Embeddings

MK Egger, W Ma, D Mottin, P Karras, I Bordino… - Proceedings of the …, 2024 - dl.acm.org
Can we assess a priori how well a knowledge graph embedding will perform on a specific
downstream task and in a specific part of the knowledge graph? Knowledge graph …

DiffusionE: Reasoning on Knowledge Graphs via Diffusion-based Graph Neural Networks

Z Cao, J Li, Z Wang, J Li - Proceedings of the 30th ACM SIGKDD …, 2024 - dl.acm.org
Graph Neural Networks (GNNs) have demonstrated powerful capabilities in reasoning
within Knowledge Graphs (KGs), gathering increasing attention. Our idea stems from the …

Position-Aware Active Learning for Multi-Modal Entity Alignment

B Xu, Y Lu, B Su, X Yan - ICASSP 2024-2024 IEEE …, 2024 - ieeexplore.ieee.org
Multi-Modal Entity Alignment (MMEA) aims to identify equivalent entities across different
knowledge graphs by utilizing auxiliary modalities such as images. While MMEA has made …

LLM+ KG@ VLDB'24 Workshop Summary

A Khan, T Wu, X Chen - arXiv preprint arXiv:2410.01978, 2024 - arxiv.org
The unification of large language models (LLMs) and knowledge graphs (KGs) has emerged
as a hot topic. At the LLM+ KG'24 workshop, held in conjunction with VLDB 2024 in …

[PDF][PDF] Tabular Embeddings for Tables with Bi-Dimensional Hierarchical Metadata and Nesting

G Shrestha, C Jiang, S Akula, V Yannam, A Pyayt… - EDBT, 2025 - openproceedings.org
Embeddings serve as condensed vector representations for real-world entities, finding
applications in Natural Language Processing (NLP), Computer Vision, and Data …

Robust Link Prediction over Noisy Hyper-Relational Knowledge Graphs

W Yu, J Yang, D Yang - The Web Conference 2024 - openreview.net
Modern Knowledge Graphs (KGs) are inevitably noisy due to the nature of their construction
process. Such noise could significantly impair the performance of link prediction over KGs …

[PDF][PDF] NEMO-A Neural, Emotional Architecture for Human-AI Teaming

S Costantini, P Dell'Acqua, G De Gasperis… - 39th Italian Conference …, 2024 - ceur-ws.org
In this work, we propose a novel architecture for agents to be employed in Human-AI
Teaming in various, even critical, domains based upon affective computing, empathy, and …

[PDF][PDF] The NEMO co-pilot

S Costantini, P Dell'Acqua, G De Gasperis… - 3d National Conference …, 2024 - ceur-ws.org
In this work, we describe an agent to be employed in Human-AI Teaming in various, even
critical, domains, based upon affective computing, empathy, and Theory of Mind, and a …