Efficient Causal Graph Discovery Using Large Language Models
- URL: http://arxiv.org/abs/2402.01207v4
- Date: Sat, 20 Jul 2024 18:51:58 GMT
- Title: Efficient Causal Graph Discovery Using Large Language Models
- Authors: Thomas Jiralerspong, Xiaoyin Chen, Yash More, Vedant Shah, Yoshua Bengio,
- Abstract summary: The proposed framework uses a breadth-first search (BFS) approach which allows it to use only a linear number of queries.
In addition to being more time and data-efficient, the proposed framework achieves state-of-the-art results on real-world causal graphs of varying sizes.
- Score: 42.724534747353665
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We propose a novel framework that leverages LLMs for full causal graph discovery. While previous LLM-based methods have used a pairwise query approach, this requires a quadratic number of queries which quickly becomes impractical for larger causal graphs. In contrast, the proposed framework uses a breadth-first search (BFS) approach which allows it to use only a linear number of queries. We also show that the proposed method can easily incorporate observational data when available, to improve performance. In addition to being more time and data-efficient, the proposed framework achieves state-of-the-art results on real-world causal graphs of varying sizes. The results demonstrate the effectiveness and efficiency of the proposed method in discovering causal relationships, showcasing its potential for broad applicability in causal graph discovery tasks across different domains.
Related papers
- Large Language Models are Effective Priors for Causal Graph Discovery [6.199818486385127]
Causal structure discovery from observations can be improved by integrating background knowledge provided by an expert to reduce the hypothesis space.
Recently, Large Language Models (LLMs) have begun to be considered as sources of prior information given the low cost of querying them relative to a human expert.
arXiv Detail & Related papers (2024-05-22T11:39:11Z) - Localized RETE for Incremental Graph Queries [1.3858051019755282]
We propose an extension semantics that enables local yet fully incremental execution graph queries.
The proposed technique can significantly improve performance regarding memory consumption and execution time in favorable cases, but may incur a noticeable linear overhead unfavorable cases.
arXiv Detail & Related papers (2024-05-02T10:00:37Z) - Parameter-Efficient Tuning Large Language Models for Graph Representation Learning [62.26278815157628]
We introduce Graph-aware.
Efficient Fine-Tuning - GPEFT, a novel approach for efficient graph representation learning.
We use a graph neural network (GNN) to encode structural information from neighboring nodes into a graph prompt.
We validate our approach through comprehensive experiments conducted on 8 different text-rich graphs, observing an average improvement of 2% in hit@1 and Mean Reciprocal Rank (MRR) in link prediction evaluations.
arXiv Detail & Related papers (2024-04-28T18:36:59Z) - Beyond Scaling: Predicting Patent Approval with Domain-specific Fine-grained Claim Dependency Graph [28.13334909565348]
In this paper, we unveil that simple domain-specific graph methods outperform the model, using the intrinsic dependencies within the patent data.
We propose a novel Fine-grained cLAim depeNdency (FLAN) Graph through meticulous patent data analyses.
arXiv Detail & Related papers (2024-04-22T17:22:31Z) - Simple Ingredients for Offline Reinforcement Learning [86.1988266277766]
offline reinforcement learning algorithms have proven effective on datasets highly connected to the target downstream task.
We show that existing methods struggle with diverse data: their performance considerably deteriorates as data collected for related but different tasks is simply added to the offline buffer.
We show that scale, more than algorithmic considerations, is the key factor influencing performance.
arXiv Detail & Related papers (2024-03-19T18:57:53Z) - Efficient Large Language Models Fine-Tuning On Graphs [23.19795835873144]
Learning from Text-Attributed Graphs (TAGs) has attracted significant attention due to its wide range of real-world applications.
We introduce a novel and efficient approach for the end-to-end fine-tuning of Large Language Models (LLMs) on TAGs, named LEADING.
arXiv Detail & Related papers (2023-12-07T22:35:16Z) - Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis [50.972595036856035]
We present a code that successfully replicates results from six popular and recent graph recommendation models.
We compare these graph models with traditional collaborative filtering models that historically performed well in offline evaluations.
By investigating the information flow from users' neighborhoods, we aim to identify which models are influenced by intrinsic features in the dataset structure.
arXiv Detail & Related papers (2023-08-01T09:31:44Z) - Towards Sequence Utility Maximization under Utility Occupancy Measure [53.234101208024335]
In the database, although utility is a flexible criterion for each pattern, it is a more absolute criterion due to neglect of utility sharing.
We first define utility occupancy on sequence data and raise the problem of High Utility-Occupancy Sequential Pattern Mining.
An algorithm called Sequence Utility Maximization with Utility occupancy measure (SUMU) is proposed.
arXiv Detail & Related papers (2022-12-20T17:28:53Z) - Pooling Architecture Search for Graph Classification [36.728077433219916]
Graph neural networks (GNNs) are designed to learn node-level representation based on neighborhood aggregation schemes.
Pooling methods are applied after the aggregation operation to generate coarse-grained graphs.
It is a challenging problem to design a universal pooling architecture to perform well in most cases.
We propose to use neural architecture search (NAS) to search for adaptive pooling architectures for graph classification.
arXiv Detail & Related papers (2021-08-24T09:03:03Z) - Probabilistic Case-based Reasoning for Open-World Knowledge Graph
Completion [59.549664231655726]
A case-based reasoning (CBR) system solves a new problem by retrieving cases' that are similar to the given problem.
In this paper, we demonstrate that such a system is achievable for reasoning in knowledge-bases (KBs)
Our approach predicts attributes for an entity by gathering reasoning paths from similar entities in the KB.
arXiv Detail & Related papers (2020-10-07T17:48:12Z)
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.