Search Results - "Deac, Andreea"
-
1
Scientific discovery in the age of artificial intelligence
Published in Nature (London) (03-08-2023)“…Artificial intelligence (AI) is being increasingly integrated into scientific discovery to augment and accelerate research, helping scientists to generate…”
Get full text
Journal Article -
2
Geometric epitope and paratope prediction
Published in Bioinformatics (Oxford, England) (01-07-2024)“…Identifying the binding sites of antibodies is essential for developing vaccines and synthetic antibodies. In this article, we investigate the optimal…”
Get full text
Journal Article -
3
Publisher Correction: Scientific discovery in the age of artificial intelligence
Published in Nature (London) (14-09-2023)Get full text
Journal Article -
4
Evolving Computation Graphs
Published 22-06-2023“…Graph neural networks (GNNs) have demonstrated success in modeling relational data, especially for data that exhibits homophily: when a connection between…”
Get full text
Journal Article -
5
Equivariant MuZero
Published 09-02-2023“…Deep reinforcement learning repeatedly succeeds in closed, well-defined domains such as games (Chess, Go, StarCraft). The next frontier is real-world…”
Get full text
Journal Article -
6
Expander Graph Propagation
Published 06-10-2022“…Deploying graph neural networks (GNNs) on whole-graph classification or regression tasks is known to be challenging: it often requires computing node features…”
Get full text
Journal Article -
7
Geometric Epitope and Paratope Prediction
Published 28-05-2023“…Antibody-antigen interactions play a crucial role in identifying and neutralizing harmful foreign molecules. In this paper, we investigate the optimal…”
Get full text
Journal Article -
8
Continuous Neural Algorithmic Planners
Published 28-11-2022“…Neural algorithmic reasoning studies the problem of learning algorithms with neural networks, especially with graph architectures. A recent proposal, XLVIN,…”
Get full text
Journal Article -
9
Graph neural induction of value iteration
Published 26-09-2020“…Many reinforcement learning tasks can benefit from explicit planning based on an internal model of the environment. Previously, such planning components have…”
Get full text
Journal Article -
10
Neural message passing for joint paratope-epitope prediction
Published 31-05-2021“…Antibodies are proteins in the immune system which bind to antigens to detect and neutralise them. The binding sites in an antibody-antigen interaction are…”
Get full text
Journal Article -
11
How does over-squashing affect the power of GNNs?
Published 06-06-2023“…Graph Neural Networks (GNNs) are the state-of-the-art model for machine learning on graph-structured data. The most popular class of GNNs operate by exchanging…”
Get full text
Journal Article -
12
Attentive cross-modal paratope prediction
Published 12-06-2018“…Antibodies are a critical part of the immune system, having the function of directly neutralising or tagging undesirable objects (the antigens) for future…”
Get full text
Journal Article -
13
How to transfer algorithmic reasoning knowledge to learn new algorithms?
Published 26-10-2021“…Learning to execute algorithms is a fundamental problem that has been widely studied. Prior work~\cite{veli19neural} has shown that to enable systematic…”
Get full text
Journal Article -
14
Neural Algorithmic Reasoners are Implicit Planners
Published 11-10-2021“…Implicit planning has emerged as an elegant technique for combining learned models of the world with end-to-end model-free reinforcement learning. We study the…”
Get full text
Journal Article -
15
XLVIN: eXecuted Latent Value Iteration Nets
Published 25-10-2020“…Value Iteration Networks (VINs) have emerged as a popular method to incorporate planning algorithms within deep reinforcement learning, enabling performance…”
Get full text
Journal Article -
16
A Generalist Neural Algorithmic Learner
Published 22-09-2022“…The cornerstone of neural algorithmic reasoning is the ability to solve algorithmic tasks, especially in a way that generalises out of distribution. While…”
Get full text
Journal Article -
17
Large-scale graph representation learning with very deep GNNs and self-supervision
Published 20-07-2021“…Effectively and efficiently deploying graph neural networks (GNNs) at scale remains one of the most challenging aspects of graph representation learning. Many…”
Get full text
Journal Article -
18
Drug-Drug Adverse Effect Prediction with Graph Co-Attention
Published 01-05-2019“…Complex or co-existing diseases are commonly treated using drug combinations, which can lead to higher risk of adverse side effects. The detection of…”
Get full text
Journal Article