Towards Human-like Perception: Learning Structural Causal Model in
Heterogeneous Graph
- URL: http://arxiv.org/abs/2312.05757v1
- Date: Sun, 10 Dec 2023 04:34:35 GMT
- Title: Towards Human-like Perception: Learning Structural Causal Model in
Heterogeneous Graph
- Authors: Tianqianjin Lin, Kaisong Song, Zhuoren Jiang, Yangyang Kang, Weikang
Yuan, Xurui Li, Changlong Sun, Cui Huang, Xiaozhong Liu
- Abstract summary: This study introduces a novel solution, HG-SCM (Heterogeneous Graph as Structural Causal Model)
It can mimic the human perception and decision process through two key steps: constructing intelligible variables based on semantics derived from the graph schema and automatically learning task-level causal relationships among these variables by incorporating advanced causal discovery techniques.
HG-SCM achieved the highest average performance rank with minimal standard deviation, substantiating its effectiveness and superiority in terms of both predictive power and generalizability.
- Score: 26.361815957385417
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Heterogeneous graph neural networks have become popular in various domains.
However, their generalizability and interpretability are limited due to the
discrepancy between their inherent inference flows and human reasoning logic or
underlying causal relationships for the learning problem. This study introduces
a novel solution, HG-SCM (Heterogeneous Graph as Structural Causal Model). It
can mimic the human perception and decision process through two key steps:
constructing intelligible variables based on semantics derived from the graph
schema and automatically learning task-level causal relationships among these
variables by incorporating advanced causal discovery techniques. We compared
HG-SCM to seven state-of-the-art baseline models on three real-world datasets,
under three distinct and ubiquitous out-of-distribution settings. HG-SCM
achieved the highest average performance rank with minimal standard deviation,
substantiating its effectiveness and superiority in terms of both predictive
power and generalizability. Additionally, the visualization and analysis of the
auto-learned causal diagrams for the three tasks aligned well with domain
knowledge and human cognition, demonstrating prominent interpretability.
HG-SCM's human-like nature and its enhanced generalizability and
interpretability make it a promising solution for special scenarios where
transparency and trustworthiness are paramount.
Related papers
- CauSkelNet: Causal Representation Learning for Human Behaviour Analysis [6.880536510094897]
This study introduces a novel representation learning method based on causal inference to better understand human joint dynamics and complex behaviors.
Our approach advances human motion analysis and paves the way for more adaptive intelligent healthcare solutions.
arXiv Detail & Related papers (2024-09-23T21:38:49Z) - A Full DAG Score-Based Algorithm for Learning Causal Bayesian Networks with Latent Confounders [0.0]
Causal Bayesian networks (CBN) are popular graphical probabilistic models that encode causal relations among variables.
This paper introduces the first fully score-based structure learning algorithm searching the space of DAGs that is capable of identifying the presence of some latent confounders.
arXiv Detail & Related papers (2024-08-20T20:25:56Z) - Learning Divergence Fields for Shift-Robust Graph Representations [73.11818515795761]
In this work, we propose a geometric diffusion model with learnable divergence fields for the challenging problem with interdependent data.
We derive a new learning objective through causal inference, which can guide the model to learn generalizable patterns of interdependence that are insensitive across domains.
arXiv Detail & Related papers (2024-06-07T14:29:21Z) - Interpretable Imitation Learning with Dynamic Causal Relations [65.18456572421702]
We propose to expose captured knowledge in the form of a directed acyclic causal graph.
We also design this causal discovery process to be state-dependent, enabling it to model the dynamics in latent causal graphs.
The proposed framework is composed of three parts: a dynamic causal discovery module, a causality encoding module, and a prediction module, and is trained in an end-to-end manner.
arXiv Detail & Related papers (2023-09-30T20:59:42Z) - Homophily modulates double descent generalization in graph convolution
networks [33.703222768801574]
We show how risk is shaped by the interplay between the graph noise, feature noise, and the number of training labels.
We use our analytic insights to improve performance of state-of-the-art graph convolution networks on heterophilic datasets.
arXiv Detail & Related papers (2022-12-26T09:57:09Z) - Counterfactual Intervention Feature Transfer for Visible-Infrared Person
Re-identification [69.45543438974963]
We find graph-based methods in the visible-infrared person re-identification task (VI-ReID) suffer from bad generalization because of two issues.
The well-trained input features weaken the learning of graph topology, making it not generalized enough during the inference process.
We propose a Counterfactual Intervention Feature Transfer (CIFT) method to tackle these problems.
arXiv Detail & Related papers (2022-08-01T16:15:31Z) - Heterogeneous Graph Neural Networks using Self-supervised Reciprocally
Contrastive Learning [102.9138736545956]
Heterogeneous graph neural network (HGNN) is a very popular technique for the modeling and analysis of heterogeneous graphs.
We develop for the first time a novel and robust heterogeneous graph contrastive learning approach, namely HGCL, which introduces two views on respective guidance of node attributes and graph topologies.
In this new approach, we adopt distinct but most suitable attribute and topology fusion mechanisms in the two views, which are conducive to mining relevant information in attributes and topologies separately.
arXiv Detail & Related papers (2022-04-30T12:57:02Z) - Handling Distribution Shifts on Graphs: An Invariance Perspective [78.31180235269035]
We formulate the OOD problem on graphs and develop a new invariant learning approach, Explore-to-Extrapolate Risk Minimization (EERM)
EERM resorts to multiple context explorers that are adversarially trained to maximize the variance of risks from multiple virtual environments.
We prove the validity of our method by theoretically showing its guarantee of a valid OOD solution.
arXiv Detail & Related papers (2022-02-05T02:31:01Z) - Systematic Evaluation of Causal Discovery in Visual Model Based
Reinforcement Learning [76.00395335702572]
A central goal for AI and causality is the joint discovery of abstract representations and causal structure.
Existing environments for studying causal induction are poorly suited for this objective because they have complicated task-specific causal graphs.
In this work, our goal is to facilitate research in learning representations of high-level variables as well as causal structures among them.
arXiv Detail & Related papers (2021-07-02T05:44:56Z)
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.