---
_id: '67339'
abstract:
- lang: eng
  text: Explainable artificial intelligence (XAI) is essential for critical domains
    such as healthcare and autonomous systems to build trust and confidence in real-world
    deployment. In this context, description logic knowledge bases (KBs) provide structured
    and semantically rich representations that support reasoning and informed decision-making.
    A core task in applying KBs to XAI is class expression learning (CEL), which generates
    explainable logical descriptions for classifying instances within KBs. Unlike
    black-box models with opaque internal mechanisms, CEL provides global explainability
    and ease of integration with domain knowledge. However, current approaches to
    CEL face significant limitations such as poor scalability, failure to capture
    rare patterns, and limited exploration of the vast class expression search space.
    To overcome these limitations, we introduce LYRA, a novel multi-agent deep reinforcement
    learning framework that formulates CEL as a collaborative planning task under
    uncertainty. The integration of the Dempster–Shafer theory enables agents to effectively
    reason under ambiguity and manage conflicting or inconsistent information. Our
    experiments show that LYRA outperforms state-of-the-art methods on seven out of
    eight datasets, demonstrating robust and scalable CEL. Additionally, LYRA offers
    interpretable decisions and employs advanced search strategies, enabling the discovery
    of more precise and expressive class expressions than existing approaches.
author:
- first_name: Amgad
  full_name: Abdulmaqsod, Amgad
  last_name: Abdulmaqsod
- first_name: Yasir
  full_name: Mahmood, Yasir
  last_name: Mahmood
- first_name: Axel-Cyrille
  full_name: Ngonga Ngomo, Axel-Cyrille
  last_name: Ngonga Ngomo
- first_name: Mohamed Ahmed
  full_name: Sherif, Mohamed Ahmed
  last_name: Sherif
citation:
  ama: 'Abdulmaqsod A, Mahmood Y, Ngonga Ngomo A-C, Sherif MA. LYRA: Belief-Driven
    Scalable Class Expression Learning in Description Logics. In: <i>The Semantic
    Web – ISWC 2026</i>. ; 2026.'
  apa: 'Abdulmaqsod, A., Mahmood, Y., Ngonga Ngomo, A.-C., &#38; Sherif, M. A. (2026).
    LYRA: Belief-Driven Scalable Class Expression Learning in Description Logics.
    <i>The Semantic Web – ISWC 2026</i>.'
  bibtex: '@inproceedings{Abdulmaqsod_Mahmood_Ngonga Ngomo_Sherif_2026, place={Bari,
    Italy}, title={LYRA: Belief-Driven Scalable Class Expression Learning in Description
    Logics}, booktitle={The Semantic Web – ISWC 2026}, author={Abdulmaqsod, Amgad
    and Mahmood, Yasir and Ngonga Ngomo, Axel-Cyrille and Sherif, Mohamed Ahmed},
    year={2026} }'
  chicago: 'Abdulmaqsod, Amgad, Yasir Mahmood, Axel-Cyrille Ngonga Ngomo, and Mohamed
    Ahmed Sherif. “LYRA: Belief-Driven Scalable Class Expression Learning in Description
    Logics.” In <i>The Semantic Web – ISWC 2026</i>. Bari, Italy, 2026.'
  ieee: 'A. Abdulmaqsod, Y. Mahmood, A.-C. Ngonga Ngomo, and M. A. Sherif, “LYRA:
    Belief-Driven Scalable Class Expression Learning in Description Logics,” 2026.'
  mla: 'Abdulmaqsod, Amgad, et al. “LYRA: Belief-Driven Scalable Class Expression
    Learning in Description Logics.” <i>The Semantic Web – ISWC 2026</i>, 2026.'
  short: 'A. Abdulmaqsod, Y. Mahmood, A.-C. Ngonga Ngomo, M.A. Sherif, in: The Semantic
    Web – ISWC 2026, Bari, Italy, 2026.'
date_created: 2026-10-02T07:50:24Z
date_updated: 2026-10-02T08:00:46Z
keyword:
- amgad dice enexa fairomics mahmood ngonga sailproject sherif simba whale
place: Bari, Italy
publication: The Semantic Web – ISWC 2026
status: public
title: 'LYRA: Belief-Driven Scalable Class Expression Learning in Description Logics'
type: conference
user_id: '67234'
year: '2026'
...