Enhances drug discovery by optimizing molecular structures.
problem Accelerate drug discovery through better optimization of precursor molecules.
method Integrates substructure components with atom-level encoding in a fully autoregressive graph decoder.
result Significantly outperforms previous state-of-the-art baselines on molecular optimization tasks.
STNN-DDI predicts drug interactions using substructure-aware neural networks.
problem Predicting drug-drug interactions (DDIs) to avoid side effects in poly-drug treatments.
method Designing a novel Substructure-ware Tensor Neural Network (STNN-DDI) that learns a 3-D tensor of substructure-substructure interactions.
result Significant improvement in AUC, AUPR, Accuracy, and Precision compared to state-of-the-art models.
Meta-materials simulation sped up with energy surrogates.
problem Challenging simulation of complex meta-materials due to high-fidelity PDEs.
method Learned component-level surrogates using neural networks to model stored potential energy.
result Surrogates enable accurate macroscopic behavior simulation without full structure simulation.
A new graph kernel uses Wasserstein distance for better graph comparison.
problem Graph kernels often discard valuable information and struggle with continuous attributes.
method Proposes a novel graph kernel using Wasserstein distance for node feature vector distributions.
result Improves prediction performance on graph classification tasks.
CORE optimizes molecules by copying or generating substructures, improving accuracy.
problem Inaccurate substructure prediction in molecule optimization.
method Copy & Refine (CORE) strategy combining scaffolding tree generation and adversarial training.
result Significant improvement in various molecule optimization metrics.
Graph neural networks struggle with counting certain substructures in graphs.
problem Detecting and counting specific substructures in graphs.
method Study of graph neural networks' ability to count attributed graph substructures.
result Graph neural networks like MPNNs, 2-WL, and 2-IGNs have limitations in counting certain substructures.
Machine learning helps infer dark matter substructure from strong lensing images.
problem Extracting information about dark matter substructure from strong lensing images is challenging.
method Simulation-based inference techniques and neural networks trained on simulator data.
result Efficiently trained neural networks can estimate likelihood ratios for substructure parameters.
DHGAK aligns substructures for better graph kernel performance.
problem Limited performance of traditional graph kernels due to missing substructure similarities.
method Hierarchically aligns relational substructures in deep embedding space, assigning same feature maps in RKHS.
result DHGAK outperforms state-of-the-art graph kernels on various benchmarks.
Graph Substructure Networks (GSN) improves GNN expressivity by counting subgraph isomorphisms.
problem Limited expressivity of GNNs in detecting and counting graph substructures.
method Topologically-aware message passing scheme based on substructure encoding.
result GSN is strictly more expressive than the Weisfeiler-Leman (WL) test and can disambiguate even hard graph isomorphism instances.
New Alexander quandles reveal more about link substructures.
problem Understanding sublinks through Alexander quandles.
method Analysis of sublink quandles within multivariate Alexander modules.
result Multivariate Alexander quandles uniquely identify sublink structures.
Generative model learns to create molecules with multiple properties using interpretable substructures.
problem Creating molecules with multiple chemical properties is challenging.
method Compose molecules from substructures identified as responsible for each property, using graph generative models.
result Significant improvements in accuracy, diversity, and novelty of generated compounds over state-of-the-art baselines.
Chemical structure elucidation is a serious bottleneck in analytical chemistry today. We address the problem of identifying an unknown chemical threat given its mass spectrum and its chemical formula, a task which might take well trained chemists several days to complete. Given a chemical formula, there could be over a…
We analyze geometrical structures necessary to represent bulk and surface interactions of standard and substructural nature in complex bodies. Our attention is mainly focused on the influence of diffuse interfaces on sharp discontinuity surfaces. In analyzing this phenomenon, we prove the covariance of surface balances…
In a previous article, we defined a very flexible notion of suborbifold and characterized those suborbifolds which can arise as the images of orbifold embeddings. In particular, suborbifolds are images of orbifold embeddings precisely when they are saturated and split. This article addresses the problem of orbifold str…
BERT learns molecular substructures for chemistry problems.
problem Predicting chemical properties and synthesizing molecules.
method Transformer-based BERT model on molecule string representations, attention visualization.
result BERT learns to represent functional groups and atoms for various chemical properties.
RSPFs combine multiple SPNs for better density estimation.
problem Creating large SPNs for complex data.
method Random sum-product forests with residual links.
result RSPFs outperform individual SPNs and improve with residual links.
Graph Polish optimizes molecular structures by minimizing changes and maximizing preservation.
problem Error-prone traditional molecular optimization methods.
method Graph Polish transforms optimization into a polishing task, focusing on optimization centers and minimizing changes.
result Significant advantage over state-of-the-art methods on multiple optimization tasks.
CASTER predicts drug interactions using chemical substructures.
problem Identifying potential drug-drug interactions during drug design.
method CASTER uses sequential pattern mining, auto-encoding, and dictionary learning to predict DDIs.
result CASTER outperformed state-of-the-art models and provided interpretable predictions.
Paper tackles brain tumor segmentation using weak labels and hierarchical training.
problem High manual labeling effort for fully supervised brain tumor segmentation.
method Uses scribbles and global labels for weak supervision, trains two networks in phases.
result Achieves competitive results on brain tumor segmentation and substructure segmentation.
Non-invasive detection of cardiovascular disorders from radiology scans requires quantitative image analysis of the heart and its substructures. There are well-established measurements that radiologists use for diseases assessment such as ejection fraction, volume of four chambers, and myocardium mass. These measuremen…
Geo2DR learns graph representations using substructure patterns.
problem Learning distributed representations of graphs efficiently.
method Unsupervised learning with discrete substructure patterns and neural language models.
result Geo2DR achieves high reproducibility and interoperability in graph classification.
SFP prunes ID features to improve OOD generalization without domain data.
problem Improving out-of-distribution (OOD) generalization in biased models.
method Spurious Feature-targeted model Pruning (SFP) framework.
result SFP achieves optimal OOD generalization by pruning ID features.
An important question that discrete approaches to quantum gravity must address is how continuum features of spacetime can be recovered from the discrete substructure. Here, we examine this question within the causal set approach to quantum gravity, where the substructure replacing the spacetime continuum is a locally f…
Study compares GNNs and classical molecular featurisations for molecular property and cliff prediction.
problem Comparing GNNs and classical featurisations for molecular property and cliff prediction.
method Systematic exploration and comparison of PDVs, ECFPs, and GNNs; introduction of substructure pooling.
result Sort & Slice outperforms hash-based folding in ECFP vectorization.
New method uses contrastively trained GNNs for more reliable graph model evaluation.
problem Need effective methods to evaluate Graph Generative Models.
method Use representations from contrastively trained Graph Neural Networks (GNNs) for evaluation.
result Contrastively trained GNNs provide more reliable evaluation metrics than traditional or GNN-based approaches.
Spectral algorithms solve optimal community detection and related problems.
problem Optimal detection of community structures and related substructures.
method Spectral algorithms applied to various planted substructures.
result Spectral algorithms achieve optimal performance for a wide range of planted substructures.
New method unfolds distribution moments directly from data without binning.
problem Deconvolving detector distortions in particle physics.
method Uses machine learning, inspired by GANs, to unfold moments directly.
result More precise than bin-based approaches and comparable to unbinned methods.
Jets from boosted heavy particles have a typical angular scale which can be used to distinguish them from QCD jets. We introduce a machine learning strategy for jet substructure analysis using a spectral function on the angular scale. The angular spectrum allows us to scan energy deposits over the angle between a pair …
OmniFold simultaneously unfolds all observables using machine learning.
problem Traditional unfolding methods are limited to individual observables and do not incorporate all detector information.
method OmniFold iteratively reweights a simulated dataset using machine learning to handle all available information.
result OmniFold enables the simultaneous measurement of all observables, including those not yet invented.
Properties of data are frequently seen to vary depending on the sampled situations, which usually changes along a time evolution or owing to environmental effects. One way to analyze such data is to find invariances, or representative features kept constant over changes. The aim of this paper is to identify one such fe…
We introduce the notion of left (and right) quasi-Loday algebroids and a "universal space" for them, called a left (right) omni-Loday algebroid, in such a way that Lie algebroids, omni-Lie algebras and omni-Loday algebroids are particular substructures.
Deep generative model for healthcare data identifies coherent substructures and mutational clusters.
problem Analytical challenges in healthcare data, including sparsity, missingness, and small sample sizes.
method Proposes a deep generative Bayesian model with collapsed Gibbs sampling for multinomial count data.
result Identifies coherent substructures and biologically meaningful mutational clusters in cancer data.
Paper detects common subtrees with identical labels in trees.
problem Finding common subtrees with identical label distribution in tree data.
method Developed an algorithm for tree isomorphism and a new compression scheme for trees.
result The method efficiently finds and compresses common subtrees with identical labels.
InfoGraph learns graph-level representations via mutual information maximization.
problem Learning graph-level representations for unsupervised and semi-supervised scenarios.
method Maximizes mutual information between graph-level representation and substructure representations.
result InfoGraph outperforms state-of-the-art methods on graph classification and molecular property prediction.
The aim of this paper is to study from the point of view of linear connections the data (M,D,g,W), with M a smooth (n+p) dimensional real manifold, (D,g) a \textit{n}\textit{\emph{dimensional semi-Riemannian distribution}}\emph{}on M, G the conformal structure generated by $g…
We describe a strategy for constructing a neural network jet substructure tagger which powerfully discriminates boosted decay signals while remaining largely uncorrelated with the jet mass. This reduces the impact of systematic uncertainties in background modeling while enhancing signal purity, resulting in improved di…
New tensor framework connects Fisher information, hypergraphs, and multi-observable correlations.
problem Missing structure in pairwise Fisher graphs for multi-observable radiation patterns.
method Higher-order Fisher tensors and natural exponential-family coordinates.
result Exact triality of Fisher tensors, cumulants, and hypergraphs.
DeepMap learns deep graph representations via CNNs, improving graph classification performance.
problem Quantifying graph similarities for tasks like classification.
method Proposes DeepMap framework extending CNNs to arbitrary graphs, learning dense low-dimensional vectors.
result DeepMap achieves state-of-the-art performance on graph classification benchmarks.
New methods identify local clusters in graphs with few labels.
problem Identifying specific substructures in large graphs without additional structural information.
method Random sampling, diffusion, and overlap analysis of local clusters.
result Proves the correctness of the proposed methods and achieves state-of-the-art results.
Recent advances in graph convolutional networks have significantly improved the performance of chemical predictions, raising a new research question: "how do we explain the predictions of graph convolutional networks?" A possible approach to answer this question is to visualize evidence substructures responsible for th…
We address a largely open problem of multilabel classification over graphs. Unlike traditional vector input, a graph has rich variable-size substructures which are related to the labels in some ways. We believe that uncovering these relations might hold the key to classification performance and explainability. We intro…
DE improves GNNs by distinguishing graph substructures, enhancing accuracy.
problem Limited expressive power of GNNs in representing graph substructures.
method Introduces Distance Encoding (DE) to assist GNNs in distinguishing graph substructures.
result DE distinguishes graph substructures that traditional GNNs cannot, improving accuracy.
New string kernels discover global properties through random feature maps, avoiding quadratic complexity.
problem Existing string kernels struggle with capturing long patterns, maintaining positive definiteness, and handling large datasets efficiently.
method Proposes a new class of global string kernels using random feature maps to discover global properties through global alignments, ensuring positive definiteness and linear computational cost.
result Random String Embeddings (RSE) achieve better or comparable accuracy to state-of-the-art methods, especially for longer strings.
A novel method for estimating Bayesian network (BN) parameters from data is presented which provides improved performance on test data. Previous research has shown the value of representing conditional probability distributions (CPDs) via neural networks(Neal 1992), noisy-OR gates (Neal 1992, Diez 1993)and decision tre…
Motivation: Prediction of the interaction affinity between proteins and compounds is a major challenge in the drug discovery process. WideDTA is a deep-learning based prediction model that employs chemical and biological textual sequence information to predict binding affinity. Results: WideDTA uses four text-based inf…
We introduce a rich class of graphical models for multi-armed bandit problems that permit both the state or context space and the action space to be very large, yet succinctly specify the payoffs for any context-action pair. Our main result is an algorithm for such models whose regret is bounded by the number of parame…
New method combines simulations and data for anomaly detection.
problem Detecting new particle signals without direct evidence.
method Hybrid approach using reweighting and interpolation.
result Improved background estimation and classification.
Tree++ graph kernel captures similarities at multiple granularities.
problem Lack of scale-adaptivity in existing graph kernels.
method Tree++ uses truncated BFS trees and super paths to represent graphs at different granularities.
result Tree++ achieves best classification accuracy on real-world graphs.