Related papers: CalPro: Prior-Aware Evidential--Conformal Predicti…

Backpropagation of error (backprop) is a powerful algorithm for training machine learning architectures through end-to-end differentiation. However, backprop is often criticised for lacking biological plausibility. Recently, it has been…

Calibrating deep learning models to yield uncertainty-aware predictions is crucial as deep neural networks get increasingly deployed in safety-critical applications. While existing post-hoc calibration methods achieve impressive results on…

Reliable uncertainty estimates are an important tool for helping autonomous agents or human decision makers understand and leverage predictive models. However, existing approaches to estimating uncertainty largely ignore the possibility of…

Despite the success of deep learning in dermoscopy image analysis, its inherent black-box nature hinders clinical trust, motivating the use of prototypical networks for case-based visual transparency. However, inevitable selection bias in…

Most estimators collapse all uncertainty modes into a single confidence score, preventing reliable reasoning about when to allocate more compute or adjust inference. We introduce Uncertainty-Guided Inference-Time Selection, a lightweight…

Protein function prediction is currently achieved by encoding its sequence or structure, where the sequence-to-function transcendence and high-quality structural data scarcity lead to obvious performance bottlenecks. Protein domains are…

In Dec 2020, the results of AlphaFold2 were presented at CASP14, sparking a revolution in the field of protein structure predictions. For the first time, a purely computational method could challenge experimental accuracy for structure…

Protein structures are important for understanding their functions and interactions. Currently, many protein structure prediction methods are enriching the structure database. Discriminating the origin of structures is crucial for…

Molecular docking, a key technique in structure-based drug design, plays pivotal roles in protein-ligand interaction modeling, hit identification and optimization, in which accurate prediction of protein-ligand binding mode is essential.…

Uncertainty is critical to reliable decision-making with machine learning. Conformal prediction (CP) handles uncertainty by predicting a set on a test input, hoping the set to cover the true label with at least $(1-\alpha)$ confidence. This…

Transformers have had a profound impact on the field of artificial intelligence, especially on large language models and their variants. However, as was the case with neural networks, their black-box nature limits trust and deployment in…

Despite extensive research on neural network calibration, existing methods typically apply global transformations that treat all predictions uniformly, overlooking the heterogeneous reliability of individual predictions. Furthermore, the…

Conformal prediction (CP) offers distribution-free marginal coverage guarantees under an exchangeability assumption, but these guarantees can fail if the data distribution shifts. We analyze the use of pseudo-calibration as a tool to…

Black-box machine learning models are now routinely used in high-risk settings, like medical diagnostics, which demand uncertainty quantification to avoid consequential model failures. Conformal prediction is a user-friendly paradigm for…

Albeit revealing impressive predictive performance for several computer vision tasks, deep neural networks (DNNs) are prone to making overconfident predictions. This limits the adoption and wider utilization of DNNs in many safety-critical…

A protein's function depends critically on its conformational ensemble, a collection of energy weighted structures whose balance depends on temperature and environment. Though recent deep learning (DL) methods have substantially advanced…

Reliable evaluation of protein structure predictions remains challenging, as metrics like pLDDT capture energetic stability but often miss subtle errors such as atomic clashes or conformational traps reflecting topological frustration…

Molecular docking that predicts the bound structures of small molecules (ligands) to their protein targets, plays a vital role in drug discovery. However, existing docking methods often face limitations: they either overlook crucial…

AlphaFold is a neural-network-based tool for the prediction of 3D structures of protein. In CASP14, a blind structure prediction challenge, it performed significantly better than other competitors, which makes it the best available…

The inapplicability of amino acid covariation methods to small protein families has limited their use for structural annotation of whole genomes. Recently, deep learning has shown promise in allowing accurate residue-residue contact…