Related papers: Removing Biases from Molecular Representations via…
Estimating mutual correlations between random variables or data streams is essential for intelligent behavior and decision-making. As a fundamental quantity for measuring statistical relationships, mutual information has been extensively…
Software developers frequently reuse source code from repositories as it saves development time and effort. Code clones accumulated in these repositories hence represent often repeated functionalities and are candidates for reuse in an…
Learning disentangled and interpretable representations is an important step towards accomplishing comprehensive data representations on the manifold. In this paper, we propose a novel representation learning algorithm which combines the…
The goal of contrasting learning is to learn a representation that preserves underlying clusters by keeping samples with similar content, e.g. the ``dogness'' of a dog, close to each other in the space generated by the representation. A…
Channel pruning is a promising method for accelerating and compressing convolutional neural networks. However, current pruning algorithms still remain unsolved problems that how to assign layer-wise pruning ratios properly and discard the…
In hospitals, data are siloed to specific information systems that make the same information available under different modalities such as the different medical imaging exams the patient undergoes (CT scans, MRI, PET, Ultrasound, etc.) and…
Conjugated organic molecules represent an important area of materials chemistry for both fundamental scientific exploration and technological applications. Using a genetic algorithm to computationally screen up to ~25-50 million molecules…
Image fusion aims to integrate complementary information from multiple source images to produce a more informative and visually consistent representation, benefiting both human perception and downstream vision tasks. Despite recent…
In therapeutic design, balancing various physiochemical properties is crucial for molecule development, similar to how Multiparameter Optimization (MPO) evaluates multiple variables to meet a primary goal. While many molecular features can…
Information bottleneck (IB) principle [1] has become an important element in information-theoretic analysis of deep models. Many state-of-the-art generative models of both Variational Autoencoder (VAE) [2; 3] and Generative Adversarial…
Integrated Computational Materials Engineering (ICME) calls for the integration of computational tools into the materials and parts development cycle, while the Materials Genome Initiative (MGI) calls for the acceleration of the materials…
This paper studies the mitigation of intersymbol interference in a diffusive molecular communication system using enzymes that freely diffuse in the propagation environment. The enzymes form reaction intermediates with information molecules…
Machine learning based methods have shown potential for optimizing existing molecules with more desirable properties, a critical step towards accelerating new chemical discovery. Here we propose QMO, a generic query-based molecule…
Composed image retrieval which combines a reference image and a text modifier to identify the desired target image is a challenging task, and requires the model to comprehend both vision and language modalities and their interactions.…
Constraint-Based Reconstruction and Analysis (COBRA) is currently the only methodology that permits integrated modeling of Metabolism and macromolecular Expression (ME) at genome-scale. Linear optimization computes steady-state flux…
A novel method to convert color/multi-spectral images to gray-level images is introduced to increase the performance of document binarization methods. The method uses the distribution of the pixel data of the input document image in a color…
Diffusion models (DMs) have become dominant in visual generation but suffer performance drop when tested on resolutions that differ from the training scale, whether lower or higher. In fact, the key challenge in generating variable-scale…
We investigate the recovery of structures from large-area, low dose exposures that distribute the dose over many identical copies of an object. The reconstruction is done via a maximum likelihood approach that does neither require to…
We present the GeneScore, a concept of feature reduction for Machine Learning analysis of biomedical data. Using expert knowledge, the GeneScore integrates different molecular data types into a single score. We show that the GeneScore is…
Synthetic healthcare data generation presents a viable approach to enhance data accessibility and support research by overcoming limitations associated with real-world medical datasets. However, ensuring fairness across protected attributes…