Related papers: Don't Sweat the Small Stuff: Segment-Level Meta-Ev…

Pairwise comparisons are widely used in decision analysis, preference modeling, and evaluation problems. In many practical situations, the observed comparison matrix is not reciprocal. This lack of reciprocity is often treated as a defect…

Parameter-Efficient Fine-Tuning (PEFT) has gained prominence through low-rank adaptation methods like LoRA. In this paper, we focus on sparsity-based PEFT (SPEFT), which introduces trainable sparse adaptations to the weight matrices in the…

When pre-processing observational data via matching, we seek to approximate each unit with maximally similar peers that had an alternative treatment status--essentially replicating a randomized block design. However, as one considers a…

Despite the state-of-the-art performance of Large Language Models (LLMs) achieved on many tasks, their massive scale often leads to high computational and environmental costs, limiting their accessibility. Parameter-Efficient Fine-Tuning…

Reliable evaluation protocols are of utmost importance for reproducible NLP research. In this work, we show that sometimes neither metric nor conventional human evaluation is sufficient to draw conclusions about system performance. Using…

Feature subset selection, as a special case of the general subset selection problem, has been the topic of a considerable number of studies due to the growing importance of data-mining applications. In the feature subset selection problem…

Large language models (LLMs) are commonly adapted to downstream tasks through fine-tuning, but fine-tuning data often contains sensitive information that may be leaked by the resulting model. Differential privacy (DP) offers formal…

Small object detection aims to localize and classify small objects within images. With recent advances in large-scale vision-language pretraining, finetuning pretrained object detection models has emerged as a promising approach. However,…

The Pearson-Matthews correlation coefficient (usually abbreviated MCC) is considered to be one of the most useful metrics for the performance of a binary classification or hypothesis testing method (for the sake of conciseness we will use…

Pre-trained models have brought significant improvements to many NLP tasks and have been extensively analyzed. But little is known about the effect of fine-tuning on specific tasks. Intuitively, people may agree that a pre-trained model…

Purpose: Magnetic polarizability tensors (MPTs) provide an economical characterisation of conducting magnetic metallic objects and their spectral signature can aid in the solution of metal detection inverse problems, such as scrap metal…

This article introduces a sensitivity analysis method for Multiple Testing Procedures (MTPs) using marginal $p$-values. The method is based on the Dirichlet process (DP) prior distribution, specified to support the entire space of MTPs,…

In few-shot classification tasks (so-called episodes), a small set of labeled support samples is provided during inference to aid the classification of unlabeled query samples. Metric-based models typically operate by computing similarities…

Data-parallel (DP) training with synchronous all-reduce is a dominant paradigm for full-parameter fine-tuning of large language models (LLMs). While parameter synchronization guarantees numerical equivalence of model weights after each…

Software defect prediction heavily relies on the metrics collected from software projects. Earlier studies often used machine learning techniques to build, validate, and improve bug prediction models using either a set of metrics collected…

This paper introduces a task- and model-aware framework for measuring similarity between wireless datasets, enabling applications such as dataset selection/augmentation, simulation-to-real (sim2real) comparison, task-specific synthetic data…

The problem of model selection is inevitable in an increasingly large number of applications involving partial theoretical knowledge and vast amounts of information, like in medicine, biology or economics. The associated techniques are…

Fine-tuning large language models on downstream tasks is crucial for realizing their cross-domain potential but often relies on sensitive data, raising privacy concerns. Differential privacy (DP) offers rigorous privacy guarantees and has…

Semantic scene parsing is suffering from the fact that pixel-level annotations are hard to be collected. To tackle this issue, we propose a Point-based Distance Metric Learning (PDML) in this paper. PDML does not require dense annotated…

Pairwise learning or dyadic prediction concerns the prediction of properties for pairs of objects. It can be seen as an umbrella covering various machine learning problems such as matrix completion, collaborative filtering, multi-task…