Search Results for author: Andreea Deac

Found 16 papers, 3 papers with code

Evolving Computation Graphs

no code implementations22 Jun 2023 Andreea Deac, Jian Tang

Graph neural networks (GNNs) have demonstrated success in modeling relational data, especially for data that exhibits homophily: when a connection between nodes tends to imply that they belong to the same class.

How does over-squashing affect the power of GNNs?

no code implementations6 Jun 2023 Francesco Di Giovanni, T. Konstantin Rusch, Michael M. Bronstein, Andreea Deac, Marc Lackenby, Siddhartha Mishra, Petar Veličković

In this paper, we provide a rigorous analysis to determine which function classes of node features can be learned by an MPNN of a given capacity.

Geometric Epitope and Paratope Prediction

no code implementations28 May 2023 Marco Pegoraro, Clémentine Dominé, Emanuele Rodolà, Petar Veličković, Andreea Deac

Antibody-antigen interactions play a crucial role in identifying and neutralizing harmful foreign molecules.

Equivariant MuZero

no code implementations9 Feb 2023 Andreea Deac, Théophane Weber, George Papamakarios

Model-based reinforcement learning algorithms, such as the highly successful MuZero, aim to accomplish this by learning a world model.

Model-based Reinforcement Learning reinforcement-learning +2

Continuous Neural Algorithmic Planners

no code implementations29 Nov 2022 Yu He, Petar Veličković, Pietro Liò, Andreea Deac

Neural algorithmic reasoning studies the problem of learning algorithms with neural networks, especially with graph architectures.

Continuous Control

Expander Graph Propagation

no code implementations6 Oct 2022 Andreea Deac, Marc Lackenby, Petar Veličković

Deploying graph neural networks (GNNs) on whole-graph classification or regression tasks is known to be challenging: it often requires computing node features that are mindful of both local interactions in their neighbourhood and the global context of the graph structure.

Graph Classification Graph Representation Learning +1

How to transfer algorithmic reasoning knowledge to learn new algorithms?

no code implementations NeurIPS 2021 Louis-Pascal A. C. Xhonneux, Andreea Deac, Petar Velickovic, Jian Tang

Due to the fundamental differences between algorithmic reasoning knowledge and feature extractors such as used in Computer Vision or NLP, we hypothesise that standard transfer techniques will not be sufficient to achieve systematic generalisation.

Learning to Execute Multi-Task Learning

Neural Algorithmic Reasoners are Implicit Planners

no code implementations NeurIPS 2021 Andreea Deac, Petar Veličković, Ognjen Milinković, Pierre-Luc Bacon, Jian Tang, Mladen Nikolić

We find that prior approaches either assume that the environment is provided in such a tabular form -- which is highly restrictive -- or infer "local neighbourhoods" of states to run value iteration over -- for which we discover an algorithmic bottleneck effect.

Self-Supervised Learning

Neural message passing for joint paratope-epitope prediction

no code implementations31 May 2021 Alice Del Vecchio, Andreea Deac, Pietro Liò, Petar Veličković

Antibodies are proteins in the immune system which bind to antigens to detect and neutralise them.

XLVIN: eXecuted Latent Value Iteration Nets

no code implementations25 Oct 2020 Andreea Deac, Petar Veličković, Ognjen Milinković, Pierre-Luc Bacon, Jian Tang, Mladen Nikolić

Value Iteration Networks (VINs) have emerged as a popular method to incorporate planning algorithms within deep reinforcement learning, enabling performance improvements on tasks requiring long-range reasoning and understanding of environment dynamics.

Graph Representation Learning Self-Supervised Learning

Graph neural induction of value iteration

no code implementations26 Sep 2020 Andreea Deac, Pierre-Luc Bacon, Jian Tang

Previously, such planning components have been incorporated through a neural network that partially aligns with the computational graph of value iteration.

reinforcement-learning Reinforcement Learning (RL)

Empowering Graph Representation Learning with Paired Training and Graph Co-Attention

no code implementations25 Sep 2019 Andreea Deac, Yu-Hsiang Huang, Petar Velickovic, Pietro Lio, Jian Tang

Through many recent advances in graph representation learning, performance achieved on tasks involving graph-structured data has substantially increased in recent years---mostly on tasks involving node-level predictions.

Graph Classification Graph Regression +2

Drug-Drug Adverse Effect Prediction with Graph Co-Attention

1 code implementation2 May 2019 Andreea Deac, Yu-Hsiang Huang, Petar Veličković, Pietro Liò, Jian Tang

Complex or co-existing diseases are commonly treated using drug combinations, which can lead to higher risk of adverse side effects.

Attentive cross-modal paratope prediction

no code implementations12 Jun 2018 Andreea Deac, Petar Veličković, Pietro Sormanni

Antibodies are a critical part of the immune system, having the function of directly neutralising or tagging undesirable objects (the antigens) for future destruction.

Computational Efficiency

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