Efficient data selection is essential for improving the training efficiency of deep neural networks and reducing the associated annotation costs. However, traditional methods tend to be computationally expensive, limiting their scalability and real-world applicability. We introduce PruneFuse, a novel method that combines pruning and network fusion to enhance data selection and accelerate network training. In PruneFuse, the original dense network is pruned to generate a smaller surrogate model that efficiently selects the most informative samples from the dataset. Once this iterative data selection selects sufficient samples, the insights learned from the pruned model are seamlessly integrated with the dense model through network fusion, providing an optimized initialization that accelerates training. Extensive experimentation on various datasets demonstrates that PruneFuse significantly reduces computational costs for data selection, achieves better performance than baselines, and accelerates the overall training process.

Fine-tuning on task-specific data to boost downstream performance is a crucial step for leveraging Large Language Models (LLMs). However, previous studies have demonstrated that fine-tuning the models on several adversarial samples or even benign data can greatly comprise the model's pre-equipped alignment and safety capabilities. In this work, we propose SEAL, a novel framework to enhance safety in LLM fine-tuning. SEAL learns a data ranker based on the bilevel optimization to up rank the safe and high-quality fine-tuning data and down rank the unsafe or low-quality ones. Models trained with SEAL demonstrate superior quality over multiple baselines, with 8.5% and 9.7% win rate increase compared to random selection respectively on Llama-3-8b-Instruct and Merlinite-7b models. Our code is available on github https://github.com/hanshen95/SEAL.

Yet, existing low-resource learning techniques, such as Active Learning (AL), that aim to support human annotators mostly focus on the label while neglecting the natural language explanation of a data point. This work proposes a novel AL architecture to support experts' real-world need for label and explanation annotations in low-resource scenarios. Our AL architecture leverages an explanationgeneration model to produce explanations guided by human explanations, a prediction model that utilizes generated explanations toward prediction faithfully, and a novel data diversity-based AL sampling strategy that benefits from the explanation annotations. Automated and human evaluations demonstrate the effectiveness of incorporating explanations Figure 1: Our dual-model AL system architecture at into AL sampling and the improved human annotation every iteration: 1) the AL data selector chooses a few efficiency and trustworthiness with our unlabeled examples; 2) human annotators provide an AL architecture. Additional ablation studies illustrate explanation and label for each data instance; 3) the annotated the potential of our AL architecture explanations are used to finetune the explanationgeneration for transfer learning, generalizability, and integration model; 4) the annotated labels and generated with large language models (LLMs).

In my previous posts, I described what is Active Learning (introduction to Active Learning and the main approaches) and how one can implement such a pipeline in a simple and generic way (architecture for Active Learning pipeline). This post is based on a talk I gave at Reversim Summit 2021. I want to jump a few steps forward and talk about how I evaluate my Active Learning models' results and how it helped me to catch a huge bug. In general, when we talk about Active Learning, we talk about creating a Data Selector. An automatic algorithm that will be able to choose a subset from our unlabeled data and will give our model the largest performance gain, so it will be able to learn and improve its accuracy.

Partial domain adaptation (PDA) extends standard domain adaptation to a more realistic scenario where the target domain only has a subset of classes from the source domain. The key challenge of PDA is how to select the relevant samples in the shared classes for knowledge transfer. Previous PDA methods tackle this problem by re-weighting the source samples based on the prediction of classifier or discriminator, thus discarding the pixel-level information. In this paper, to utilize both high-level and pixel-level information, we propose a reinforced transfer network (RTNet), which is the first work to apply reinforcement learning to address the PDA problem. The RTNet simultaneously mitigates the negative transfer by adopting a reinforced data selector to filter out outlier source classes, and promotes the positive transfer by employing a domain adaptation model to minimize the distribution discrepancy in the shared label space. Extensive experiments indicate that RTNet can achieve state-of-the-art performance for partial domain adaptation tasks on several benchmark datasets. Codes and datasets will be available online.