El Mehdi Benyoussef
El Mehdi Benyoussef has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Abdellatif Sassioui
C3S Laboratory, Higher School of Technology, Hassan II University, Casablanca 20010, Morocco
2 shared publications - Meriyem Chergui
C3S Laboratory, Higher School of Technology, Hassan II University, Casablanca 20010, Morocco
2 shared publications - Mohamed El Kamili
C3S Laboratory, Higher School of Technology, Hassan II University, Casablanca 20010, Morocco
2 shared publications - Mohammed Ouzzif
C3S Laboratory, Higher School of Technology, Hassan II University, Casablanca 20010, Morocco
2 shared publications - Rachid Benouini
Leyton, Casablanca 20190, Morocco
2 shared publications - Yasser Elouargui
C3S Laboratory, Higher School of Technology, Hassan II University, Casablanca 20010, Morocco
2 shared publications
Latest Publications
- Open Access
- 25 April 2026
- Published by MDPI AG in Technologies
- Vol. 14 (5) , 258
ESG-Graph: Hierarchical Residual Graph Attention Network with Analyst-Defined ESG Taxonomy
Environmental, Social, and Governance (ESG) text classification is important for applications in sustainable finance. However, it remains a challenging task due to domain terminology and regulatory constraints. While transformer-based models achieve strong predictive performance, they often lead to high energy costs and provide limited interpretability. To address these limitations, we introduce ESG-Graph, a lightweight and interpretable graph-based framework for modeling ESG disclosures. In our approach, each sentence is represented as a token-level dependency graph augmented with virtual nodes initialized from a European Sustainability Reporting Standards (ESRS)-based taxonomy, enabling the addition of new ESG concepts without retraining. A multi-layer Graph Attention Network is used instead of transformer encoders, allowing grammatical structure and domain semantics to be modeled jointly. Experiments on three ESG benchmark datasets show that ESG-Graph achieves performance comparable to efficient transformer baselines while consuming up to 60× less energy and using 10× fewer parameters. Additional attribution and ablation studies suggest the method’s policy alignment, interpretability, and robustness.
- 25 April 2026
- Published by MDPI AG in Technologies
- Vol. 14 (5) , 258
Open AccessESG-Graph: Hierarchical Residual Graph Attention Network with Analyst-Defined ESG Taxonomy
Environmental, Social, and Governance (ESG) text classification is important for applications in sustainable finance. However, it remains a challenging task due to domain terminology and regulatory constraints. While transformer-based models achieve strong predictive performance, they often lead to high energy costs and provide limited interpretability. To address these limitations, we introduce ESG-Graph, a lightweight and interpretable graph-based framework for modeling ESG disclosures. In our approach, each sentence is represented as a token-level dependency graph augmented with virtual nodes initialized from a European Sustainability Reporting Standards (ESRS)-based taxonomy, enabling the addition of new ESG concepts without retraining. A multi-layer Graph Attention Network is used instead of transformer encoders, allowing grammatical structure and domain semantics to be modeled jointly. Experiments on three ESG benchmark datasets show that ESG-Graph achieves performance comparable to efficient transformer baselines while consuming up to 60× less energy and using 10× fewer parameters. Additional attribution and ablation studies suggest the method’s policy alignment, interpretability, and robustness.
- Open Access
- 23 April 2026
- Published by MDPI AG in Technologies
- Vol. 14 (5) , 250
AMD-Proj: Adaptive Memory-Driven Selective Gradient Projection for Continual Learning in Document Understanding
Visually rich document understanding (VrDU) models rely on tightly coupled textual, layout, and visual representations. In real-world deployments, these models must continuously adapt to new document domains over time. However, naïve sequential fine-tuning leads to severe catastrophic forgetting due to shared parameters and strong cross-task interference. Existing continual learning approaches either constrain parameter updates, preserve output distributions, or uniformly suppress gradient directions associated with previous tasks. While effective in limited settings, these strategies fail to balance stability and plasticity in large multimodal transformers. We propose AMD-Proj, an adaptive memory-driven selective gradient projection framework for continual learning in document understanding. It models task knowledge using specific gradient subspaces and adaptively modulates incoming gradients based on their alignment with this memory, selectively blocking interfering directions while reinforcing reusable ones. An efficient truncated SVD mechanism with online subspace merging ensures bounded memory usage and scalability to large transformer-based architectures. We evaluate AMD-Proj on four VrDU benchmarks (FUNSD, SROIE, CORD, and BuDDIE) under a task-incremental learning setting using LayoutLMv2 and LayoutLMv3 backbones. Results show that AMD-Proj reduces catastrophic forgetting and improves F1-based stability over EWC, GPM, LwF, OWM, CUBER, TRGP and parameter-efficient fine-tuning methods. Extensive mechanistic analyses, including gradient spectrum decomposition and layer-wise reuse versus block dynamics, provide insight into how selective gradient projection controls optimization geometry during continual adaptation. These findings establish selective gradient projection as a principled and interpretable approach for continual learning in visually rich document understanding.
- 23 April 2026
- Published by MDPI AG in Technologies
- Vol. 14 (5) , 250
Open AccessAMD-Proj: Adaptive Memory-Driven Selective Gradient Projection for Continual Learning in Document Understanding
Visually rich document understanding (VrDU) models rely on tightly coupled textual, layout, and visual representations. In real-world deployments, these models must continuously adapt to new document domains over time. However, naïve sequential fine-tuning leads to severe catastrophic forgetting due to shared parameters and strong cross-task interference. Existing continual learning approaches either constrain parameter updates, preserve output distributions, or uniformly suppress gradient directions associated with previous tasks. While effective in limited settings, these strategies fail to balance stability and plasticity in large multimodal transformers. We propose AMD-Proj, an adaptive memory-driven selective gradient projection framework for continual learning in document understanding. It models task knowledge using specific gradient subspaces and adaptively modulates incoming gradients based on their alignment with this memory, selectively blocking interfering directions while reinforcing reusable ones. An efficient truncated SVD mechanism with online subspace merging ensures bounded memory usage and scalability to large transformer-based architectures. We evaluate AMD-Proj on four VrDU benchmarks (FUNSD, SROIE, CORD, and BuDDIE) under a task-incremental learning setting using LayoutLMv2 and LayoutLMv3 backbones. Results show that AMD-Proj reduces catastrophic forgetting and improves F1-based stability over EWC, GPM, LwF, OWM, CUBER, TRGP and parameter-efficient fine-tuning methods. Extensive mechanistic analyses, including gradient spectrum decomposition and layer-wise reuse versus block dynamics, provide insight into how selective gradient projection controls optimization geometry during continual adaptation. These findings establish selective gradient projection as a principled and interpretable approach for continual learning in visually rich document understanding.