Nghia Bui

Nghia Bui, Yue Ning, Lijing Wang

Deep recommender systems (DRS) often face challenges in balancing computational efficiency and model accuracy, especially when handling high-dimensional input features. Existing methods either focus on improving accuracy while neglecting training efficiency or prioritize efficiency at the cost of suboptimal accuracy across tasks. We propose Light-FMP: Lightweight Feature and Model Pruning for Enhanced DRS, a lightweight framework that addresses the challenges through three key phases: \textit{pretraining}, \textit{pruning}, and \textit{continued training}. Using a hard concrete distribution, a masking layer is efficiently pretrained on a small data subset to identify important features. The model and features are then pruned, and training continues on the remaining dataset with domain-adapted parameters. Experiments on benchmark datasets from real-world recommender systems demonstrate that Light-FMP outperforms existing methods in both efficiency and accuracy while maintaining scalability and robustness.

Nghia Bui, Lijing Wang

Fine-tuning pretrained models has become a standard approach to adapting pretrained knowledge to improve the accuracy on new sparse, imbalance datasets. However, issues arise when optimization falls into a collapsed state, where the model gets stuck, leading to degraded performance and unstable training. One possible reason for this is the cancellation of gradients across training examples. To address this problem, we propose a novel algorithm, dynamic scaled gradient descent (\mName), that directly modifies the gradients returned by training examples, specifically, scaling down the gradients of correctly classified examples using a dynamic scaler. This strategy offers both theoretical and empirical advantages in improving training stability. Experiments on a variety of benchmark datasets, spanning multiple tasks and large pretrained models, demonstrate that our method consistently reduces performance variance and surpasses the accuracy of existing approaches.

Nghia Bui, Guergana Savova, Lijing Wang

The impact of random seeds in fine-tuning large language models (LLMs) has been largely overlooked despite its potential influence on model performance.In this study, we systematically evaluate the effects of random seeds on LLMs using the GLUE and SuperGLUE benchmarks. We analyze the macro-level impact through traditional metrics like accuracy and F1, calculating their mean and variance to quantify performance fluctuations. To capture the micro-level effects, we introduce a novel metric, consistency, measuring the stability of individual predictions across runs. Our experiments reveal significant variance at both macro and micro levels, underscoring the need for careful consideration of random seeds in fine-tuning and evaluation.