Related papers: Most Ligand-Based Classification Benchmarks Reward…
Generating labeled training datasets has become a major bottleneck in Machine Learning (ML) pipelines. Active ML aims to address this issue by designing learning algorithms that automatically and adaptively select the most informative…
The aim of Active Learning is to select the most informative samples from an unlabelled set of data. This is useful in cases where the amount of data is large and labelling is expensive, such as in machine vision or medical imaging. Two…
Assisted by the availability of data and high performance computing, deep learning techniques have achieved breakthroughs and surpassed human performance empirically in difficult tasks, including object recognition, speech recognition, and…
Artificial neural networks (ANNs) require tremendous amount of data to train on. However, in classification models, most data features are often similar which can lead to increase in training time without significant improvement in the…
Representation learning has overcome the often arduous and manual featurization of networks through (unsupervised) feature learning as it results in embeddings that can apply to a variety of downstream learning tasks. The focus of…
As large language models (LLMs) become increasingly capable and widely adopted, benchmarks play a central role in assessing their practical utility. For example, SWE-Bench Verified has emerged as a critical benchmark for evaluating LLMs'…
Achieving backward compatibility when rolling out new models can highly reduce costs or even bypass feature re-encoding of existing gallery images for in-production visual retrieval systems. Previous related works usually leverage losses…
Amortized Bayesian inference (ABI) offers fast, scalable approximations to posterior densities by training neural surrogates on data simulated from the statistical model. However, ABI methods are highly sensitive to model misspecification:…
Verifying whether the machine unlearning process has been properly executed is critical but remains underexplored. Some existing approaches propose unlearning verification methods based on backdooring techniques. However, these methods…
Supervised (linear) embedding models like Wsabie and PSI have proven successful at ranking, recommendation and annotation tasks. However, despite being scalable to large datasets they do not take full advantage of the extra data due to…
Alignment faking (AF) refers to a model strategically complying with a training objective to avoid behavioural modification while preserving its deployment preferences. Understanding when and why AF arises matters as models grow better at…
Fine-tuning is becoming widely used for leveraging the power of pre-trained foundation models in new downstream tasks. While there are many successes of fine-tuning on various tasks, recent studies have observed challenges in the…
Neural networks have revolutionized numerous fields, yet they remain vulnerable to a critical flaw: the tendency to learn implicit biases, spurious correlations between certain attributes and target labels in training data. These biases are…
Large Language Models (LLMs) have recently improved mathematical reasoning through Reinforcement Learning with Verifiable Reward (RLVR). However, existing RLVR algorithms require large query budgets, making annotation costly. We investigate…
Class imbalance poses a challenge for developing unbiased, accurate predictive models. In particular, in image segmentation neural networks may overfit to the foreground samples from small structures, which are often heavily…
The most popular classification algorithms are designed to maximize classification accuracy during training. However, this strategy may fail in the presence of class imbalance since it is possible to train models with high accuracy by…
Value function estimation is an indispensable subroutine in reinforcement learning, which becomes more challenging in the offline setting. In this paper, we propose Hybrid Value Estimation (HVE) to reduce value estimation error, which…
Adversarial Training (AT) has been found to substantially improve the robustness of deep learning classifiers against adversarial attacks. AT involves obtaining robustness by including adversarial examples in training a classifier. Most…
Farquhar et al. [2021] show that correcting for active learning bias with underparameterised models leads to improved downstream performance. For overparameterised models such as NNs, however, correction leads either to decreased or…
An active learner is given a class of models, a large set of unlabeled examples, and the ability to interactively query labels of a subset of these examples; the goal of the learner is to learn a model in the class that fits the data well.…