Related papers: Decomposing the Generalization Gap in PROTAC Activ…

In recent years, machine learning has been proposed as a promising strategy to build accurate scoring functions for computational docking finalized to numerically empowered drug discovery. However, the latest studies have suggested that…

Many important problems involving molecular property prediction from 3D structures have limited data, posing a generalization challenge for neural networks. In this paper, we describe a pre-training technique based on denoising that…

Gradient-based hyperparameter optimization (HPO) have emerged recently, leveraging bilevel programming techniques to optimize hyperparameter by estimating hypergradient w.r.t. validation loss. Nevertheless, previous theoretical works mainly…

We propose a generalized method for boosting the generalization ability of pre-trained vision-language models (VLMs) while fine-tuning on downstream few-shot tasks. The idea is realized by exploiting out-of-distribution (OOD) detection to…

Using "soft" targets to improve model performance has been shown to be effective in classification settings, but the usage of soft targets for regression is a much less studied topic in machine learning. The existing literature on the usage…

Recently, extensive deep learning architectures and pretraining strategies have been explored to support downstream protein applications. Additionally, domain-specific models incorporating biological knowledge have been developed to enhance…

Protein mutations can have profound effects on biological function, making accurate prediction of property changes critical for drug discovery, protein engineering, and precision medicine. Current approaches rely on fine-tuning…

Data-driven molecular discovery leverages artificial intelligence/machine learning (AI/ML) and generative modeling to filter and design novel molecules. Discovering novel molecules requires accurate out-of-distribution (OOD) predictions,…

The promising zero-shot generalization of vision-language models such as CLIP has led to their adoption using prompt learning for numerous downstream tasks. Previous works have shown test-time prompt tuning using entropy minimization to…

Protein function annotation is an important yet challenging task in biology. Recent deep learning advancements show significant potential for accurate function prediction by learning from protein sequences and structures. Nevertheless,…

The Average Gradient Outer Product (AGOP) governs feature learning in neural networks: the Neural Feature Ansatz states that weight Gram matrices at each layer align with the corresponding AGOP matrices computed over the training…

Vision-language models (VLMs), such as CLIP, have demonstrated impressive zero-shot capabilities for various downstream tasks. Their performance can be further enhanced through few-shot prompt tuning methods. However, current studies…

Out-of-distribution generalization in reinforcement learning is hard to diagnose when benchmark shifts mix dynamics, observations, goals, and rewards. We address this with Tape, a controlled benchmark that isolates latent rule-shift in…

Distributed learning has shown great potential in medical image analysis. It allows to use multi-center training data with privacy protection. However, data distributions in local centers can vary from each other due to different imaging…

Leveraging the large body of work devoted in recent years to describe redundancy and synergy in multivariate interactions among random variables, we propose a novel approach to quantify cooperative effects in feature importance, one of the…

Leveraging the models' outputs, specifically the logits, is a common approach to estimating the test accuracy of a pre-trained neural network on out-of-distribution (OOD) samples without requiring access to the corresponding ground truth…

The diverse nature of protein prediction tasks has traditionally necessitated specialized models, hindering the development of broadly applicable and computationally efficient Protein Language Models (PLMs). In this work, we introduce…

The Area Under the ROC Curve (AUC) is a widely employed metric in long-tailed classification scenarios. Nevertheless, most existing methods primarily assume that training and testing examples are drawn i.i.d. from the same distribution,…

Risk prediction that capitalizes on emerging genetic findings holds great promise for improving public health and clinical care. However, recent risk prediction research has shown that predictive tests formed on existing common genetic…

In order to obtain reliable accuracy estimates for automatic MOOC dropout predictors, it is important to train and test them in a manner consistent with how they will be used in practice. Yet most prior research on MOOC dropout prediction…