Search Results for author: Veronika Thost

Found 16 papers, 9 papers with code

Representing Molecules as Random Walks Over Interpretable Grammars

no code implementations13 Mar 2024 Michael Sun, Minghao Guo, Weize Yuan, Veronika Thost, Crystal Elaine Owens, Aristotle Franklin Grosz, Sharvaa Selvan, Katelyn Zhou, Hassan Mohiuddin, Benjamin J Pedretti, Zachary P Smith, Jie Chen, Wojciech Matusik

Recent research in molecular discovery has primarily been devoted to small, drug-like molecules, leaving many similarly important applications in material design without adequate technology.

Property Prediction

Improving Self-supervised Molecular Representation Learning using Persistent Homology

1 code implementation NeurIPS 2023 Yuankai Luo, Lei Shi, Veronika Thost

Self-supervised learning (SSL) has great potential for molecular representation learning given the complexity of molecular graphs, the large amounts of unlabelled data available, the considerable cost of obtaining labels experimentally, and the hence often only small training datasets.

Molecular Property Prediction molecular representation +3

Hierarchical Grammar-Induced Geometry for Data-Efficient Molecular Property Prediction

1 code implementation4 Sep 2023 Minghao Guo, Veronika Thost, Samuel W Song, Adithya Balachandran, Payel Das, Jie Chen, Wojciech Matusik

Still, these techniques are faced with a common challenge in practice: Labeled data are limited by the cost of manual extraction from literature and laborious experimentation.

Drug Discovery Molecular Property Prediction +1

Data-Efficient Graph Grammar Learning for Molecular Generation

1 code implementation ICLR 2022 Minghao Guo, Veronika Thost, Beichen Li, Payel Das, Jie Chen, Wojciech Matusik

This is a non-trivial task for neural network-based generative models since the relevant chemical knowledge can only be extracted and generalized from the limited training data.

Revisiting Virtual Nodes in Graph Neural Networks for Link Prediction

no code implementations29 Sep 2021 EunJeong Hwang, Veronika Thost, Shib Sankar Dasgupta, Tengfei Ma

It is well known that the graph classification performance of graph neural networks often improves by adding an artificial virtual node to the graphs, which is connected to all nodes in the graph.

Clustering Graph Classification +1

Improving Inductive Link Prediction Using Hyper-Relational Facts

2 code implementations10 Jul 2021 Mehdi Ali, Max Berrendorf, Mikhail Galkin, Veronika Thost, Tengfei Ma, Volker Tresp, Jens Lehmann

In this work, we classify different inductive settings and study the benefits of employing hyper-relational KGs on a wide range of semi- and fully inductive link prediction tasks powered by recent advancements in graph neural networks.

Inductive Link Prediction Knowledge Graphs

CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks

1 code implementation25 May 2021 Ruchir Puri, David S. Kung, Geert Janssen, Wei zhang, Giacomo Domeniconi, Vladimir Zolotov, Julian Dolby, Jie Chen, Mihir Choudhury, Lindsey Decker, Veronika Thost, Luca Buratti, Saurabh Pujar, Shyam Ramji, Ulrich Finkler, Susan Malaika, Frederick Reiss

In addition to its large scale, CodeNet has a rich set of high-quality annotations to benchmark and help accelerate research in AI techniques for a variety of critical coding tasks, including code similarity and classification, code translation between a large variety of programming languages, and code performance (runtime and memory) improvement techniques.

BIG-bench Machine Learning Code Classification +1

An Experimental Study of Formula Embeddings for Automated Theorem Proving in First-Order Logic

no code implementations2 Feb 2020 Ibrahim Abdelaziz, Veronika Thost, Maxwell Crouse, Achille Fokoue

Automated theorem proving in first-order logic is an active research area which is successfully supported by machine learning.

Automated Theorem Proving

Improving Graph Neural Network Representations of Logical Formulae with Subgraph Pooling

1 code implementation arXiv 2020 Maxwell Crouse, Ibrahim Abdelaziz, Cristina Cornelio, Veronika Thost, Lingfei Wu, Kenneth Forbus, Achille Fokoue

Recent advances in the integration of deep learning with automated theorem proving have centered around the representation of logical formulae as inputs to deep learning systems.

Automated Theorem Proving

Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional Networks

no code implementations5 Nov 2019 Pavan Kapanipathi, Veronika Thost, Siva Sankalp Patel, Spencer Whitehead, Ibrahim Abdelaziz, Avinash Balakrishnan, Maria Chang, Kshitij Fadnis, Chulaka Gunasekara, Bassem Makni, Nicholas Mattei, Kartik Talamadupula, Achille Fokoue

A few approaches have shown that information from external knowledge sources like knowledge graphs (KGs) can add value, in addition to the textual content, by providing background knowledge that may be critical for a task.

Knowledge Graphs Natural Language Inference

RuDaS: Synthetic Datasets for Rule Learning and Evaluation Tools

1 code implementation16 Sep 2019 Cristina Cornelio, Veronika Thost

Logical rules are a popular knowledge representation language in many domains, representing background knowledge and encoding information that can be derived from given facts in a compact form.

Inductive knowledge graph completion Inductive logic programming +2

Cannot find the paper you are looking for? You can Submit a new open access paper.