# A Generalist Neural Algorithmic Learner

arXiv: https://arxiv.org/abs/2209.11142 · HTML: https://mlsanity.com/paper/2209.11142/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 74 references that are in the map.
- First posted on arXiv 22 Sep 2022.

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks](https://mlsanity.com/paper/1810.02244/) (2018)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [Learning Combinatorial Optimization Algorithms over Graphs](https://mlsanity.com/paper/1704.01665/) (2017)
- [Leveraging Procedural Generation to Benchmark Reinforcement Learning](https://mlsanity.com/paper/1912.01588/) (2019)
- [Combinatorial optimization and reasoning with graph neural networks](https://mlsanity.com/paper/2102.09544/) (2021)
- [Graph networks as learnable physics engines for inference and control](https://mlsanity.com/paper/1806.01242/) (2018)
- [How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks](https://mlsanity.com/paper/2009.11848/) (2020)
- [The NetHack Learning Environment](https://mlsanity.com/paper/2006.13760/) (2020)
- [Learning Latent Permutations with Gumbel-Sinkhorn Networks](https://mlsanity.com/paper/1802.08665/) (2018)
- [What Can Neural Networks Reason About?](https://mlsanity.com/paper/1905.13211/) (2019)
- [From Local Structures to Size Generalization in Graph Neural Networks](https://mlsanity.com/paper/2010.08853/) (2020)
- [Neural Execution of Graph Algorithms](https://mlsanity.com/paper/1910.10593/) (2019)
- [The CLRS Algorithmic Reasoning Benchmark](https://mlsanity.com/paper/2205.15659/) (2022)
- [MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research](https://mlsanity.com/paper/2109.13202/) (2021)
- [Neural Algorithmic Reasoning](https://mlsanity.com/paper/2105.02761/) (2021)
- [A data-driven approach for learning to control computers](https://mlsanity.com/paper/2202.08137/) (2022)
- [Size-Invariant Graph Representations for Graph Classification Extrapolations](https://mlsanity.com/paper/2103.05045/) (2021)
- [My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control](https://mlsanity.com/paper/2010.01856/) (2020)
- [In Defense of the Unitary Scalarization for Deep Multi-Task Learning](https://mlsanity.com/paper/2201.04122/) (2022)
- [The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization](https://mlsanity.com/paper/2110.07732/) (2021)
- [Graph Neural Networks are Dynamic Programmers](https://mlsanity.com/paper/2203.15544/) (2022)
- [Pointer Graph Networks](https://mlsanity.com/paper/2006.06380/) (2020)
- [Structured agents for physical construction](https://mlsanity.com/paper/1904.03177/) (2019)
- [Relational inductive bias for physical construction in humans and machines](https://mlsanity.com/paper/1806.01203/) (2018)
- [End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking](https://mlsanity.com/paper/2202.05826/) (2022)
- [DeepPermNet: Visual Permutation Learning](https://mlsanity.com/paper/1704.02729/) (2017)

## Built on by (most cited first, 30 of 59)

- [Randomized Positional Encodings Boost Length Generalization of Transformers](https://mlsanity.com/paper/2305.16843/) (2023)
- [Position: Graph Foundation Models are Already Here](https://mlsanity.com/paper/2402.02216/) (2024)
- [Transformers Can Do Arithmetic with the Right Embeddings](https://mlsanity.com/paper/2405.17399/) (2024)
- [Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions](https://mlsanity.com/paper/2212.10561/) (2022)
- [Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks](https://mlsanity.com/paper/2502.14546/) (2025)
- [GOAL: A Generalist Combinatorial Optimization Agent Learner](https://mlsanity.com/paper/2406.15079/) (2024)
- [Relational Attention: Generalizing Transformers for Graph-Structured Tasks](https://mlsanity.com/paper/2210.05062/) (2022)
- [Neural Algorithmic Reasoning with Causal Regularisation](https://mlsanity.com/paper/2302.10258/) (2023)
- [Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks](https://mlsanity.com/paper/2211.00692/) (2022)
- [Simulation of Graph Algorithms with Looped Transformers](https://mlsanity.com/paper/2402.01107/) (2024)
- [The CLRS-Text Algorithmic Reasoning Language Benchmark](https://mlsanity.com/paper/2406.04229/) (2024)
- [Adaptive Computation with Elastic Input Sequence](https://mlsanity.com/paper/2301.13195/) (2023)
- [Dual Algorithmic Reasoning](https://mlsanity.com/paper/2302.04496/) (2023)
- [Neural Algorithmic Reasoning for Combinatorial Optimisation](https://mlsanity.com/paper/2306.06064/) (2023)
- [Neural Algorithmic Reasoning Without Intermediate Supervision](https://mlsanity.com/paper/2306.13411/) (2023)
- [SymbolicAI: A framework for logic-based approaches combining generative models and solvers](https://mlsanity.com/paper/2402.00854/) (2024)
- [MatSciML: A Broad, Multi-Task Benchmark for Solid-State Materials Modeling](https://mlsanity.com/paper/2309.05934/) (2023)
- [GraphFM: A generalist graph transformer that learns transferable representations across diverse domains](https://mlsanity.com/paper/2407.11907/) (2024)
- [Asynchronous Algorithmic Alignment with Cocycles](https://mlsanity.com/paper/2306.15632/) (2023)
- [SALSA-CLRS: A Sparse and Scalable Benchmark for Algorithmic Reasoning](https://mlsanity.com/paper/2309.12253/) (2023)
- [Are Graph Neural Networks Optimal Approximation Algorithms?](https://mlsanity.com/paper/2310.00526/) (2023)
- [Towards Principled Graph Transformers](https://mlsanity.com/paper/2401.10119/) (2024)
- [On the Markov Property of Neural Algorithmic Reasoning: Analyses and Methods](https://mlsanity.com/paper/2403.04929/) (2024)
- [Recursive Algorithmic Reasoning](https://mlsanity.com/paper/2307.00337/) (2023)
- [Discrete Neural Algorithmic Reasoning](https://mlsanity.com/paper/2402.11628/) (2024)
- [Differentiable graph-structured models for inverse design of lattice materials](https://mlsanity.com/paper/2304.05422/) (2023)
- [Benchmarking ChatGPT on Algorithmic Reasoning](https://mlsanity.com/paper/2404.03441/) (2024)
- [Latent Space Representations of Neural Algorithmic Reasoners](https://mlsanity.com/paper/2307.08874/) (2023)
- [Learning Graph Algorithms With Recurrent Graph Neural Networks](https://mlsanity.com/paper/2212.04934/) (2022)
- [Parallel Algorithms Align with Neural Execution](https://mlsanity.com/paper/2307.04049/) (2023)

## Abstract (arXiv)

The cornerstone of neural algorithmic reasoning is the ability to solve algorithmic tasks, especially in a way that generalises out of distribution. While recent years have seen a surge in methodological improvements in this area, they mostly focused on building specialist models. Specialist models are capable of learning to neurally execute either only one algorithm or a collection of algorithms with identical control-flow backbone. Here, instead, we focus on constructing a generalist neural algorithmic learner -- a single graph neural network processor capable of learning to execute a wide range of algorithms, such as sorting, searching, dynamic programming, path-finding and geometry. We leverage the CLRS benchmark to empirically show that, much like recent successes in the domain of perception, generalist algorithmic learners can be built by "incorporating" knowledge. That is, it is possible to effectively learn algorithms in a multi-task manner, so long as we can learn to execute them well in a single-task regime. Motivated by this, we present a series of improvements to the input representation, training regime and processor architecture over CLRS, improving average single-task performance by over 20% from prior art. We then conduct a thorough ablation of multi-task learners leveraging these improvements. Our results demonstrate a generalist learner that effectively incorporates knowledge captured by specialist models.