PaperMetrixEvidence-aware discovery
EN
Interface language English EN العربية AR Türkçe TR
Create account
Researcher profile

Petar Veličković

5 papers in the PaperMetrix corpus

Publications

Papers by this author

  1. Persistent Message Passing

    2021 · arXiv (Cornell University)

    Graph neural networks (GNNs) are a powerful inductive bias for modelling algorithmic reasoning procedures and data structures. Their prowess was mainly demonstrated on tasks featuring Markovian dynamics, where querying any associated data structure depends only …

  2. Round and Round We Go! What makes Rotary Positional Encodings useful?

    2024 · arXiv (Cornell University)

    Positional Encodings (PEs) are a critical component of Transformer-based Large Language Models (LLMs), providing the attention mechanism with important sequence-position information. One of the most popular types of encoding used today in LLMs are Rotary …

  3. Positional Attention: Expressivity and Learnability of Algorithmic Computation

    2024 · arXiv (Cornell University)

    There is a growing interest in the ability of neural networks to execute algorithmic tasks (e.g., arithmetic, summary statistics, and sorting). The goal of this work is to better understand the role of attention in …

  4. KNARsack: Teaching Neural Algorithmic Reasoners to Solve Pseudo-Polynomial Problems

    2025 · arXiv (Cornell University)

    Neural algorithmic reasoning (NAR) is a growing field that aims to embed algorithmic logic into neural networks by imitating classical algorithms. In this extended abstract, we detail our attempt to build a neural algorithmic reasoner …

  5. Deep Graph Infomax

    2018 · Apollo (University of Cambridge)

    We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs---both …