1 code implementation • 29 Apr 2024 • Hong Jin Kang, Fabrice Harel-Canada, Muhammad Ali Gulzar, Violet Peng, Miryung Kim
INSPECTOR allows users to group related texts by their transformation provenance, i. e., the transformations applied to the original text, or feature provenance, the linguistic features of the original text.
no code implementations • 5 Mar 2024 • Waris Gill, Mohamed Elidrisi, Pallavi Kalapatapu, Ali Anwar, Muhammad Ali Gulzar
Caching is a natural solution to reduce LLM inference costs on repeated queries which constitute about 31% of the total queries.
no code implementations • 21 Dec 2023 • Waris Gill, Ali Anwar, Muhammad Ali Gulzar
Regardless of the quality of the global model or if it has a fault, understanding the model's origin is equally important for debugging, interpretability, and explainability in federated learning.
1 code implementation • 2 Jul 2023 • Waris Gill, Ali Anwar, Muhammad Ali Gulzar
Federated Learning (FL) is a privacy-preserving distributed machine learning technique that enables individual clients (e. g., user participants, edge devices, or organizations) to train a model on their local data in a secure environment and then share the trained model with an aggregator to build a global model collaboratively.
1 code implementation • 9 Jan 2023 • Waris Gill, Ali Anwar, Muhammad Ali Gulzar
FedDebug's interactive debugging incurs 1. 2% overhead during training, while it localizes a faulty client in only 2. 1% of a round's training time.
1 code implementation • Findings (ACL) 2022 • Fabrice Harel-Canada, Muhammad Ali Gulzar, Nanyun Peng, Miryung Kim
The vast majority of text transformation techniques in NLP are inherently limited in their ability to expand input space coverage due to an implicit constraint to preserve the original class label.