English
Related papers

Related papers: A Generalist Neural Algorithmic Learner

200 papers

Graph neural networks (GNNs) are a powerful tool to learn representations on graphs by iteratively aggregating features from node neighbourhoods. Many variant models have been proposed, but there is limited understanding on both how to…

Machine Learning · Computer Science 2019-11-14 Michael Lingzhi Li , Meng Dong , Jiawei Zhou , Alexander M. Rush

Continual learning, the ability of a model to adapt to an ongoing sequence of tasks without forgetting earlier ones, is a central goal of artificial intelligence. To better understand its underlying mechanisms, we study the limitations of…

Machine Learning · Statistics 2026-04-21 Hossein Taheri , Avishek Ghosh , Arya Mazumdar

Graph Neural Networks (GNNs) have emerged as powerful tools for learning representations from structured data. Despite their growing popularity and success across various applications, GNNs encounter several challenges that limit their…

Machine Learning · Computer Science 2026-02-03 Yassine Abbahaddou

This extended abstract describes a framework for analyzing the expressiveness, learning, and (structural) generalization of hypergraph neural networks (HyperGNNs). Specifically, we focus on how HyperGNNs can learn from finite datasets and…

Machine Learning · Computer Science 2023-03-10 Zhezheng Luo , Jiayuan Mao , Joshua B. Tenenbaum , Leslie Pack Kaelbling

Graph Neural Networks (GNNs) are a promising deep learning approach for circumventing many real-world problems on graph-structured data. However, these models usually have at least one of four fundamental limitations: over-smoothing,…

Machine Learning · Computer Science 2022-10-03 Xun Liu , Alex Hay-Man Ng , Fangyuan Lei , Yikuan Zhang , Zhengmin Li

The paper uses statistical and differential geometric motivation to acquire prior information about the learning capability of an artificial neural network on a given dataset. The paper considers a broad class of neural networks with…

Machine Learning · Computer Science 2020-12-02 Ankan Dutta , Arnab Rakshit

In this paper, we push forward the idea of machine learning systems whose operators can be modified and fine-tuned for each problem. This allows us to propose a learning paradigm where users can write (or adapt) their operators, according…

Deep learning relies on a very specific kind of neural networks: those superposing several neural layers. In the last few years, deep learning achieved major breakthroughs in many tasks such as image analysis, speech recognition, natural…

Artificial Intelligence · Computer Science 2018-02-01 Lê Nguyên Hoang , Rachid Guerraoui

Graph neural networks (GNNs) have been applied into a variety of graph tasks. Most existing work of GNNs is based on the assumption that the given graph data is optimal, while it is inevitable that there exists missing or incomplete edges…

Machine Learning · Computer Science 2022-05-13 Qianggang Ding , Deheng Ye , Tingyang Xu , Peilin Zhao

Graph neural networks (GNNs) have emerged as a powerful tool for learning software engineering tasks including code completion, bug finding, and program repair. They benefit from leveraging program structure like control flow graphs, but…

Machine Learning · Computer Science 2020-10-27 David Bieber , Charles Sutton , Hugo Larochelle , Daniel Tarlow

Deep neural networks (NN) have achieved great success in many applications. However, why do deep neural networks obtain good generalization at an over-parameterization regime is still unclear. To better understand deep NN, we establish the…

Machine Learning · Statistics 2021-12-02 Yueming Lyu , Ivor Tsang

The ability to continuously expand knowledge over time and utilize it to rapidly generalize to new tasks is a key feature of human linguistic intelligence. Existing models that pursue rapid generalization to new tasks (e.g., few-shot…

Computation and Language · Computer Science 2022-08-23 Xisen Jin , Bill Yuchen Lin , Mohammad Rostami , Xiang Ren

Is intelligence realized by connectionist or classicist? While connectionist approaches have achieved superhuman performance, there has been growing evidence that such task-specific superiority is particularly fragile in systematic…

Artificial Intelligence · Computer Science 2022-07-21 Chi Zhang , Sirui Xie , Baoxiong Jia , Ying Nian Wu , Song-Chun Zhu , Yixin Zhu

Neural Network has been successfully applied to many real-world problems, such as image recognition and machine translation. However, for the current architecture of neural networks, it is hard to perform complex cognitive tasks, for…

Neural and Evolutionary Computing · Computer Science 2018-04-11 Liyao Gao

Real-world planning problems often involve hundreds or even thousands of objects, straining the limits of modern planners. In this work, we address this challenge by learning to predict a small set of objects that, taken together, would be…

Machine Learning · Computer Science 2020-12-10 Tom Silver , Rohan Chitnis , Aidan Curtis , Joshua Tenenbaum , Tomas Lozano-Perez , Leslie Pack Kaelbling

Deep Reinforcement Learning has shown great success in a variety of control tasks. However, it is unclear how close we are to the vision of putting Deep RL into practice to solve real world problems. In particular, common practice in the…

Machine Learning · Computer Science 2019-02-21 Chenyang Zhao , Olivier Sigaud , Freek Stulp , Timothy M. Hospedales

Deep learning models have proven enormously successful at using multiple layers of representation to learn relevant features of structured data. Encoding physical symmetries into these models can improve performance on difficult tasks, and…

Machine Learning · Computer Science 2025-10-21 Cassidy Ashworth , Pietro Liò , Francesco Caso

Systematic generalization is the ability to combine known parts into novel meaning; an important aspect of efficient human learning, but a weakness of neural network learning. In this work, we investigate how two well-known modeling…

Artificial Intelligence · Computer Science 2022-02-23 Laura Ruis , Brenden Lake

This paper presents new and effective algorithms for learning kernels. In particular, as shown by our empirical results, these algorithms consistently outperform the so-called uniform combination solution that has proven to be difficult to…

Machine Learning · Computer Science 2024-05-01 Corinna Cortes , Mehryar Mohri , Afshin Rostamizadeh

The goal of this thesis is to develop the optimisation and generalisation theoretic foundations of learning in artificial neural networks. On optimisation, a new theoretical framework is proposed for deriving architecture-dependent…

Neural and Evolutionary Computing · Computer Science 2022-10-20 Jeremy Bernstein