Subgraph isomorphism counting is an important problem on graphs, as many graph-based tasks exploit recurring subgraph patterns. Classical methods usually boil down to a backtracking framework that needs to navigate a huge search space with prohibitive computational costs. Some recent studies resort to graph neural networks (GNNs) to learn a low-dimensional representation for both the query and input graphs, in order to predict the number of subgraph isomorphisms on the input graph. However, typical GNNs employ a node-centric message passing scheme that receives and aggregates messages on nodes, which is inadequate in complex structure matching for isomorphism counting. Moreover, on an input graph, the space of possible query graphs is enormous, and different parts of the input graph will be triggered to match different queries. Thus, expecting a fixed representation of the input graph to match diversely structured query graphs is unrealistic. In this paper, we propose a novel GNN called Count-GNN for subgraph isomorphism counting, to deal with the above challenges. At the edge level, given that an edge is an atomic unit of encoding graph structures, we propose an edge-centric message passing scheme, where messages on edges are propagated and aggregated based on the edge adjacency to preserve fine-grained structural information. At the graph level, we modulate the input graph representation conditioned on the query, so that the input graph can be adapted to each query individually to improve their matching. Finally, we conduct extensive experiments on a number of benchmark datasets to demonstrate the superior performance of Count-GNN.

Much of the world's most valued data is stored in relational databases and data warehouses, where the data is organized into many tables connected by primary-foreign key relations. However, building machine learning models using this data is both challenging and time consuming. The core problem is that no machine learning method is capable of learning on multiple tables interconnected by primary-foreign key relations. Current methods can only learn from a single table, so the data must first be manually joined and aggregated into a single training table, the process known as feature engineering. Feature engineering is slow, error prone and leads to suboptimal models. Here we introduce an end-to-end deep representation learning approach to directly learn on data laid out across multiple tables. We name our approach Relational Deep Learning (RDL). The core idea is to view relational databases as a temporal, heterogeneous graph, with a node for each row in each table, and edges specified by primary-foreign key links. Message Passing Graph Neural Networks can then automatically learn across the graph to extract representations that leverage all input data, without any manual feature engineering. Relational Deep Learning leads to more accurate models that can be built much faster. To facilitate research in this area, we develop RelBench, a set of benchmark datasets and an implementation of Relational Deep Learning. The data covers a wide spectrum, from discussions on Stack Exchange to book reviews on the Amazon Product Catalog. Overall, we define a new research area that generalizes graph machine learning and broadens its applicability to a wide set of AI use cases.

Neuralizing Retrieval: Infusing Symbolic Reasoning into Language Models through Algorithmic Alignment ↗ Retrieval-augmented generation (RAG) has emerged as…

Welcome to Topology, Algebra, and Geometry in Data Science (TAG-DS). This site is intended to bring together researchers who are applying mathematical techniques to the rapidly growing field of data science. The three identified fields encompass more than 100-years of finely tuned machinery that

Trends and recent advancements in Graph and Geometric Deep Learning

Trends and recent advancements in Graph and Geometric Deep Learning

Python open source projects; natural language meets graph technologies; graph topological transformations; graph levels of detail (abstraction layers)

This blog post summarizes the findings of our new contribution:

Neural algorithmic reasoning focuses on building models that can execute classic algorithms. It allows one to combine the advantages of neural networks, such as handling raw and noisy input data, with theoretical guarantees and strong generalization of algorithms. Assuming we have a neural network capable of solving a classic algorithmic task, we can incorporate it into a more complex pipeline and train end-to-end. For instance, if we have a neural solver aligned to the shortest path problem, it can be used as a building block for a routing system that accounts for complex and dynamically changing traffic conditions. In our work [ref1], we study algorithmic reasoners trained only from input-output pairs, in contrast to current state-of-the-art approaches that utilize the trajectory of a given algorithm. We propose several architectural modifications and demonstrate how standard contrastive learning techniques can regularize intermediate computations of the models without appealing to any predefined algorithm’s trajectory.

The numerical representation of data is often ambiguous. This leads to a gauge theoretic view on data, requiring covariant or equivariant neural networks which are reviewed in this blog post.

In this article, we will talk about classical computation: the kind of computation typically found in an undergraduate Computer Science course on Algorithms and Data Structures [1]. Think shortest path-finding, sorting, clever ways to break problems down into simpler problems, incredible ways to organise data for efficient retrieval and updates.

MESH: A Flexible Distributed Hypergraph Processing System

Preview

We deal with these things Transformer and Geometric graph improvement room

By request, here are the slides from our #neurips2023 presentation yesterday! We really enjoyed the opportunity to present the different aspects of the work… | 18 comments on LinkedIn

A new message-passing paradigm where every node can choose to either ‘listen’, ‘broadcast’, ‘listen & broadcast’ or ‘isolate’.

Nature - A protocol using large-scale training of graph networks enables high-throughput discovery of novel stable structures and led to the identification of 2.2 million crystal structures, of...

A new research area that generalizes graph machine learning and broadens its applicability to a wide set of #AI use cases

Graph plays a significant role in representing and analyzing complex relationships in real-world applications such as citation networks, social networks, and biological data. Recently, Large Language Models (LLMs), which have achieved tremendous success in various domains, have also been leveraged in graph-related tasks to surpass traditional Graph Neural Networks (GNNs) based methods and yield state-of-the-art performance. In this survey, we first present a comprehensive review and analysis of existing methods that integrate LLMs with graphs. First of all, we propose a new taxonomy, which organizes existing methods into three categories based on the role (i.e., enhancer, predictor, and alignment component) played by LLMs in graph-related tasks. Then we systematically survey the representative methods along the three categories of the taxonomy. Finally, we discuss the remaining limitations of existing studies and highlight promising avenues for future research. The relevant papers are summarized and will be consistently updated at: https://github.com/yhLeeee/Awesome-LLMs-in-Graph-tasks.

We are excited to announce the open-source release of GraphStorm 0.1, a low-code enterprise graph machine learning (ML) framework to build, train, and deploy graph ML solutions on complex enterprise-scale graphs in days instead of months. With GraphStorm, you can build solutions that directly take into account the structure of relationships or interactions between billions […]

Molecular generation is crucial for advancing drug discovery, materials science, and chemical exploration. It expedites the search for new drug candidates, facilitates tailored material creation, and enhances our understanding of molecular diversity. By employing artificial intelligence techniques such as molecular generative models based on molecular graphs, researchers have tackled the challenge of identifying efficient molecules with desired properties. Here, we propose a new molecular generative model combining a graph-based deep neural network and a reinforcement learning technique. We evaluated the validity, novelty, and optimized physicochemical properties of the generated molecules. Importantly, the model explored uncharted regions of chemical space, allowing for the efficient discovery and design of new molecules. This innovative approach has considerable potential to revolutionize drug discovery, materials science, and chemical research for accelerating scientific innovation. By leveraging advanced techniques and exploring previously unexplored chemical spaces, this study offers promising prospects for the efficient discovery and design of new molecules in the field of drug development.

Opinion: The Pentagon should match its big investment in attritable autonomy with smarter targeting, the author argues.

Graph-based data is ubiquitous in enterprise, across the industry verticals, and increasingly needed for machine learning use cases…

Our state-of-the-art model delivers 10-day weather predictions at unprecedented accuracy in under one minute

A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests

Where does current work on graph technologies intersect with large language models, for building AI apps?

Building enterprise knowledge graphs as property graphs of billions of nodes / edges holding organizational knowledge to power your…

Graphs are a powerful tool for representing and analyzing complex relationships in real-world applications such as social networks, recommender systems, and computational finance. Reasoning on graphs is essential for drawing inferences about the relationships between entities in a complex system, and to identify hidden patterns and trends. Despite the remarkable progress in automated reasoning with natural text, reasoning on graphs with large language models (LLMs) remains an understudied problem. In this work, we perform the first comprehensive study of encoding graph-structured data as text for consumption by LLMs. We show that LLM performance on graph reasoning tasks varies on three fundamental levels: (1) the graph encoding method, (2) the nature of the graph task itself, and (3) interestingly, the very structure of the graph considered. These novel results provide valuable insight on strategies for encoding graphs as text. Using these insights we illustrate how the correct choice of encoders can boost performance on graph reasoning tasks inside LLMs by 4.8% to 61.8%, depending on the task.