Simulation of Graph Algorithms with Looped Transformers

• URL: http://arxiv.org/abs/2402.01107v3
• Date: Tue, 01 Oct 2024 20:30:37 GMT
• Title: Simulation of Graph Algorithms with Looped Transformers
• Authors: Artur Back de Luca, Kimon Fountoulakis,
• Abstract summary: We study the ability of transformer networks to simulate algorithms on graphs from a theoretical perspective. We prove by construction that this architecture can simulate individual algorithms such as Dijkstra's shortest path. We show a Turing Completeness result with constant width when the extra attention heads are utilized.
• Score: 6.0465914748433915
• License:
• Abstract: The execution of graph algorithms using neural networks has recently attracted significant interest due to promising empirical progress. This motivates further understanding of how neural networks can replicate reasoning steps with relational data. In this work, we study the ability of transformer networks to simulate algorithms on graphs from a theoretical perspective. The architecture we use is a looped transformer with extra attention heads that interact with the graph. We prove by construction that this architecture can simulate individual algorithms such as Dijkstra's shortest path, Breadth- and Depth-First Search, and Kosaraju's strongly connected components, as well as multiple algorithms simultaneously. The number of parameters in the networks does not increase with the input graph size, which implies that the networks can simulate the above algorithms for any graph. Despite this property, we show a limit to simulation in our solution due to finite precision. Finally, we show a Turing Completeness result with constant width when the extra attention heads are utilized.

Related papers

• Online Learning Of Expanding Graphs [14.952056744888916]
  This paper addresses the problem of online network inference for expanding graphs from a stream of signals. We introduce a strategy that enables different types of updates for nodes that just joined the network and for previously existing nodes.
  arXiv  Detail & Related papers  (2024-09-13T09:20:42Z)
• Understanding Transformer Reasoning Capabilities via Graph Algorithms [25.08208816144745]
  We study which transformer scaling regimes are able to perfectly solve different classes of algorithmic problems. Our results show that transformers excel at many graph reasoning tasks, even outperforming specialized graph neural networks.
  arXiv  Detail & Related papers  (2024-05-28T18:31:14Z)
• Layer-wise training for self-supervised learning on graphs [0.0]
  End-to-end training of graph neural networks (GNN) on large graphs presents several memory and computational challenges. We propose Layer-wise Regularized Graph Infomax, an algorithm to train GNNs layer by layer in a self-supervised manner.
  arXiv  Detail & Related papers  (2023-09-04T10:23:39Z)
• NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification [70.51126383984555]
  We introduce a novel all-pair message passing scheme for efficiently propagating node signals between arbitrary nodes. The efficient computation is enabled by a kernerlized Gumbel-Softmax operator. Experiments demonstrate the promising efficacy of the method in various tasks including node classification on graphs.
  arXiv  Detail & Related papers  (2023-06-14T09:21:15Z)
• SynGraphy: Succinct Summarisation of Large Networks via Small Synthetic Representative Graphs [4.550112751061436]
  We describe SynGraphy, a method for visually summarising the structure of large network datasets. It works by drawing smaller graphs generated to have similar structural properties to the input graphs.
  arXiv  Detail & Related papers  (2023-02-15T16:00:15Z)
• Learning Graph Search Heuristics [48.83557172525969]
  We present PHIL (Path Heuristic with Imitation Learning), a novel neural architecture and a training algorithm for discovering graph search and navigations from data. Our function learns graph embeddings useful for inferring node distances, runs in constant time independent of graph sizes, and can be easily incorporated in an algorithm such as A* at test time. Experiments show that PHIL reduces the number of explored nodes compared to state-of-the-art methods on benchmark datasets by 58.5% on average.
  arXiv  Detail & Related papers  (2022-12-07T22:28:00Z)
• Oversquashing in GNNs through the lens of information contraction and graph expansion [6.8222473597904845]
  We present a framework for analyzing oversquashing based on information contraction. We propose a graph rewiring algorithm aimed at alleviating oversquashing.
  arXiv  Detail & Related papers  (2022-08-06T08:44:39Z)
• Learning Graph Structure from Convolutional Mixtures [119.45320143101381]
  We propose a graph convolutional relationship between the observed and latent graphs, and formulate the graph learning task as a network inverse (deconvolution) problem. In lieu of eigendecomposition-based spectral methods, we unroll and truncate proximal gradient iterations to arrive at a parameterized neural network architecture that we call a Graph Deconvolution Network (GDN) GDNs can learn a distribution of graphs in a supervised fashion, perform link prediction or edge-weight regression tasks by adapting the loss function, and they are inherently inductive.
  arXiv  Detail & Related papers  (2022-05-19T14:08:15Z)
• Neighbor2Seq: Deep Learning on Massive Graphs by Transforming Neighbors to Sequences [55.329402218608365]
  We propose the Neighbor2Seq to transform the hierarchical neighborhood of each node into a sequence. We evaluate our method on a massive graph with more than 111 million nodes and 1.6 billion edges. Results show that our proposed method is scalable to massive graphs and achieves superior performance across massive and medium-scale graphs.
  arXiv  Detail & Related papers  (2022-02-07T16:38:36Z)
• Graph Kernel Neural Networks [53.91024360329517]
  We propose to use graph kernels, i.e. kernel functions that compute an inner product on graphs, to extend the standard convolution operator to the graph domain. This allows us to define an entirely structural model that does not require computing the embedding of the input graph. Our architecture allows to plug-in any type of graph kernels and has the added benefit of providing some interpretability.
  arXiv  Detail & Related papers  (2021-12-14T14:48:08Z)
• Geometrically Principled Connections in Graph Neural Networks [66.51286736506658]
  We argue geometry should remain the primary driving force behind innovation in the emerging field of geometric deep learning. We relate graph neural networks to widely successful computer graphics and data approximation models: radial basis functions (RBFs) We introduce affine skip connections, a novel building block formed by combining a fully connected layer with any graph convolution operator.
  arXiv  Detail & Related papers  (2020-04-06T13:25:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.