Related papers: Uncertainty-Aware Metabolic Stability Prediction w…

Low-frequency word prediction remains a challenge in modern neural machine translation (NMT) systems. Recent adaptive training methods promote the output of infrequent words by emphasizing their weights in the overall training objectives.…

Precise yield prediction is essential for agricultural sustainability and food security. However, climate change complicates accurate yield prediction by affecting major factors such as weather conditions, soil fertility, and farm…

This paper studies a text classification algorithm based on an improved Transformer to improve the performance and efficiency of the model in text classification tasks. Aiming at the shortcomings of the traditional Transformer model in…

A common problem with segmentation of medical images using neural networks is the difficulty to obtain a significant number of pixel-level annotated data for training. To address this issue, we proposed a semi-supervised segmentation…

In visual Reinforcement Learning (RL), learning from pixel-based observations poses significant challenges on sample efficiency, primarily due to the complexity of extracting informative state representations from high-dimensional data.…

Computer vision leveraging deep learning has achieved significant success in the last decade. Despite the promising performance of the existing deep models in the recent literature, the extent of models' reliability remains unknown.…

Interest has been growing in decision-focused machine learning methods which train models to account for how their predictions are used in downstream optimization problems. Doing so can often improve performance on subsequent decision…

Accurate trajectory prediction is crucial for autonomous driving, yet uncertainty in agent behavior and perception noise makes it inherently challenging. While multi-modal trajectory prediction models generate multiple plausible future…

Deep neural networks have proven to be extremely powerful, however, they are also vulnerable to adversarial attacks which can cause hazardous incorrect predictions in safety-critical applications. Certified robustness via randomized…

Accurate and efficient uncertainty estimation is crucial to build reliable Machine Learning (ML) models capable to provide calibrated uncertainty estimates, generalize and detect Out-Of-Distribution (OOD) datasets. To this end,…

Continual learning aims to learn new tasks without forgetting previously learned ones. This is especially challenging when one cannot access data from previous tasks and when the model has a fixed capacity. Current regularization-based…

Graph Neural Networks (GNNs) have become the de facto standard for analyzing graph-structured data, leveraging message-passing techniques to capture both structural and node feature information. However, recent studies have raised concerns…

Without manually annotated identities, unsupervised multi-object trackers are inferior to learning reliable feature embeddings. It causes the similarity-based inter-frame association stage also be error-prone, where an uncertainty problem…

Diabetes remains a significant health challenge globally, contributing to severe complications like kidney disease, vision loss, and heart issues. The application of machine learning (ML) in healthcare enables efficient and accurate disease…

Molecule representation learning is crucial for understanding and predicting molecular properties. However, conventional atom-centric models, which treat chemical bonds merely as pairwise interactions, often overlook complex bond-level…

Accurate drug-target interaction (DTI) prediction is essential for computational drug discovery, yet existing models often rely on single-modality predefined molecular descriptors or sequence-based embeddings with limited…

Uncertainty Quantification aims to determine when the prediction from a Machine Learning model is likely to be wrong. Computer Vision research has explored methods for determining epistemic uncertainty (also known as model uncertainty),…

Trapped by the label scarcity in molecular property prediction and drug design, graph contrastive learning (GCL) came forward. Leading contrastive learning works show two kinds of view generators, that is, random or learnable data…

Trajectory prediction models that can infer both finite future trajectories and their associated uncertainties of the target vehicles in an online setting (e.g., real-world application scenarios) is crucial for ensuring the safe and robust…

Current deep learning models often suffer from catastrophic forgetting of old knowledge when continually learning new knowledge. Existing strategies to alleviate this issue often fix the trade-off between keeping old knowledge (stability)…