Causal Representation Research Articles

Causal-ARG: a causality-guided framework for annotating properties of antibiotic resistance genes.

The crisis of antibiotic resistance, which causes antibiotics used to treat bacterial infections to become less effective, has emerged as one of the foremost challenges to public health. Identifying the properties of antibiotic resistance genes (ARGs) is an essential way to mitigate this issue. Although numerous methods have been proposed for this task, most of these approaches concentrate solely on predicting antibiotic class, disregarding other important properties of ARGs. In addition, existing methods for simultaneously predicting multiple properties of ARGs fail to account for the causal relationships among these properties, limiting the predictive performance. In this study, we propose a causality-guided framework for annotating properties of ARGs, in which causal inference is utilized for representation learning. More specifically, the hidden biological patterns determining the properties of ARGs are described by a Gaussian Mixture Model, and procedure of causal representation learning is used to derive the hidden features. In addition, a causal graph among different properties is constructed to capture the causal relationships among properties of ARGs, which is integrated into the task of annotating properties of ARGs. The experimental results on a real-world dataset demonstrate the effectiveness of the proposed framework on the task of annotating properties of ARGs. The data and source codes are available in GitHub at https://github.com/David-WZhao/CausalARG.

Mastering Context-to-Label Representation Transformation for Event Causality Identification with Diffusion Models

To understand event structures of documents, event causality identification (ECI) emerges as a crucial task, aiming to discern causal relationships among event mentions. The latest approach for ECI has introduced advanced deep learning models where transformer-based encoding models, complemented by enriching components, are typically leveraged to learn effective event context representations for causality prediction. As such, an important step for ECI models is to transform the event context representations into causal label representations to perform logits score computation for training and inference purposes. Within this framework, event context representations might encapsulate numerous complicated and noisy structures due to the potential long context between the input events while causal label representations are intended to capture pure information about the causal relations to facilitate score estimation. Nonetheless, a notable drawback of existing ECI models stems from their reliance on simple feed-forward networks to handle the complex context-to-label representation transformation process, which might require drastic changes in the representations to hinder the learning process. To overcome this issue, our work introduces a novel method for ECI where, instead abrupt transformations, event context representations are gradually updated to achieve effective label representations. This process will be done incrementally to allow filtering of irrelevant structures at varying levels of granularity for causal relations. To realize this, we present a diffusion model to learn gradual representation transition processes between context and causal labels. It operates through a forward pass for causal label representation noising and a reverse pass for reconstructing label representations from random noise. Our experiments on different datasets across multiple languages demonstrate the advantages of the diffusion model with state-of-the-art performance for ECI.

Causal Representation Learning via Counterfactual Intervention

Existing causal representation learning methods are based on the causal graph they build. However, due to the omission of bias within the causal graph, they essentially encourage models to learn biased causal effects in latent space. In this paper, we propose a novel causally disentangling framework that aims to learn unbiased causal effects. We first introduce inductive and dataset biases into traditional causal graph for the physical concepts of interest. Then, we eliminate the negative effects from these two biases by counterfactual intervention with reweighted loss function for learning unbiased causal effects. Finally, we employ the causal effects into the VAE to endow the latent representations with causality. In particular, we highlight that removing biases in this paper is regarded as a part of learning process for unbiased causal effects, which is crucial for causal disentanglement performance improvement. Through extensive experiments on real-world and synthetic datasets, we show that our method outperforms different baselines and obtains the state-of-the-art results for achieving causal representation learning.

GaitSCM: Causal representation learning for gait recognition

Gait recognition is a promising biometric technology that aims to identify the target subject via walking pattern. Most existing appearance-based methods focus on learning discriminative spatio-temporal representations from gait silhouettes. However, these methods pay less attention to probing the causality between identity factors and identity labels, which often mislead the model to learn gait representations that are susceptible to identity-irrelevant factors. In this paper, we attribute the cause that leads to the decline of model generalization under different external conditions to identity-irrelevant factors. We formulate the causalities among the identity factors, identity-irrelevant factors, and identity labels as a structural causal model (SCM). We accordingly propose a novel gait recognition framework named GaitSCM to learn covariate invariant gait representations, which is mainly composed of three components, including feature extraction module, feature disentanglement module, and backdoor adjustment. Specifically, we design a feature extractor with regard to the movement patterns of different body parts to learn fine-grained gait motion features, and then present a two-branch feature decoupling module to disentangle identity features and identity-irrelevant features with the aid of the classification confusion loss. To relieve the negative effect of identity-irrelevant factors, we develop a backdoor adjustment strategy to eliminate spurious associations between identity and identity-irrelevant features, which further facilitates the proposed framework to generate more powerful identity representations. Extensive experiments conducted on two public datasets validate the effectiveness of our method. The average Rank-1 can reach 93.2% and 90.4% on CASIA-B and OU-MVLP datasets, respectively, which verifies the superiority of GaitSCM. Source code is released at: https://github.com/HuoweiCode/GaitSCM.

Spectral Time-Varying Pattern Causality and Its Application.

In this paper, a new method based on delayed pattern causality is proposed, called spectral time-varying pattern causality. Specifically, this method uses symbolic dynamics and phase space reconstruction to infer causality, systematically quantifies the causal relationship between different frequency components of the signal, and the generated spectrum provides a rich information representation of the time-varying potential causality. The causal intensity at different times is quantified by a sliding window, providing a dynamic perspective for the study of causality in complex systems. Through the simulation data, we verified the effectiveness of the method and its robustness to noise, and then applied it to physiological data to compare the differences in coupling between electrodes in different brain regions between normal and Parkinson's patients in the resting state. The study of causality in complex systems provides a new perspective to better capture the latent and elusive dynamic structures.

Causal Network Representations in Factor Investing

Causal Network Representations in Factor Investing

Generalizing Graph Neural Networks on Out-of-Distribution Graphs.

Graph Neural Networks (GNNs) are proposed without considering the agnostic distribution shifts between training graphs and testing graphs, inducing the degeneration of the generalization ability of GNNs in Out-Of-Distribution (OOD) settings. The fundamental reason for such degeneration is that most GNNs are developed based on the I.I.D hypothesis. In such a setting, GNNs tend to exploit subtle statistical correlations existing in the training set for predictions, even though it is a spurious correlation. This learning mechanism inherits from the common characteristics of machine learning approaches. However, such spurious correlations may change in the wild testing environments, leading to the failure of GNNs. Therefore, eliminating the impact of spurious correlations is crucial for stable GNN models. To this end, in this paper, we argue that the spurious correlation exists among subgraph-level units and analyze the degeneration of GNN in causal view. Based on the causal view analysis, we propose a general causal representation framework for stable GNN, called StableGNN. The main idea of this framework is to extract high-level representations from raw graph data first and resort to the distinguishing ability of causal inference to help the model get rid of spurious correlations. Particularly, to extract meaningful high-level representations, we exploit a differentiable graph pooling layer to extract subgraph-based representations by an end-to-end manner. Furthermore, inspired by the confounder balancing techniques from causal inference, based on the learned high-level representations, we propose a causal variable distinguishing regularizer to correct the biased training distribution by learning a set of sample weights. Hence, GNNs would concentrate more on the true connection between discriminative substructures and labels. Extensive experiments are conducted on both synthetic datasets with various distribution shift degrees and eight real-world OOD graph datasets. The results well verify that the proposed model StableGNN not only outperforms the state-of-the-arts but also provides a flexible framework to enhance existing GNNs. In addition, the interpretability experiments validate that StableGNN could leverage causal structures for predictions.

A Domain Generalization Network Exploiting Causal Representations and Non-Causal Representations for Three-Phase Converter Fault Diagnosis

A Domain Generalization Network Exploiting Causal Representations and Non-Causal Representations for Three-Phase Converter Fault Diagnosis

Controllable image generation based on causal representation learning

Controllable image generation based on causal representation learning

Information Theoretic Learning-Enhanced Dual-Generative Adversarial Networks With Causal Representation for Robust OOD Generalization.

Recently, machine/deep learning techniques are achieving remarkable success in a variety of intelligent control and management systems, promising to change the future of artificial intelligence (AI) scenarios. However, they still suffer from some intractable difficulty or limitations for model training, such as the out-of-distribution (OOD) issue, in modern smart manufacturing or intelligent transportation systems (ITSs). In this study, we newly design and introduce a deep generative model framework, which seamlessly incorporates the information theoretic learning (ITL) and causal representation learning (CRL) in a dual-generative adversarial network (Dual-GAN) architecture, aiming to enhance the robust OOD generalization in modern machine learning (ML) paradigms. In particular, an ITL-and CRL-enhanced Dual-GAN (ITCRL-DGAN) model is presented, which includes an autoencoder with CRL (AE-CRL) structure to aid the dual-adversarial training with causality-inspired feature representations and a Dual-GAN structure to improve the data augmentation in both feature and data levels. Following a newly designed feature separation strategy, a causal graph is built and improved based on the information theory, which can enhance the causally related factors among the separated core features and further enrich the feature representation with the counterfactual features via interventions based on the refined causal relationships. The ITL is incorporated to improve the extraction of low-dimensional feature representations and learn the optimized causal representations based on the idea of "information flow." A dual-adversarial training mechanism is then developed, which not only enables the generator to expand the boundary of feature distribution in accordance with the optimized feature representation from AE-CRL, but also allows the discriminator to further verify and improve the quality of the augmented data for OOD generalization. Experiment and evaluation results based on an open-source dataset demonstrate the outstanding learning efficiency and classification performance of our proposed model for robust OOD generalization in modern smart applications compared with three baseline methods.

Revisiting Drug Recommendation From a Causal Perspective.

Drug recommendation that aims to provide a prescription for a patient is an essential task in healthcare. Drug molecular graphs provide valuable support for drug recommendation. Existing methods tend to overlook drugs' molecular graphs or use the core substructures of molecular graphs with a rule-based segmentation strategy. However, such methods have several limitations: (1) The rule-based segmentation strategy is inflexible and sub-optimal for extremely complex scenarios. (2) The core substructures derived only consider the drug's chemical characteristics and ignore the patient's health condition. (3) The spurious correlation brought by trivial substructures is disregarded. To address these limitations, we design a novel drug recommendation method from a causal perspective, where a conditional causal representation learner for drug recommendation is proposed. Specifically, we first separate the drug molecular representation into causal and spurious parts depending on various patients' health conditions. Then, we eliminate the spurious correlation caused by the spurious part with causal intervention. Extensive experiments on the MIMIC-III and MIMIC-IV datasets demonstrate that our approach achieves new state-of-the-art performance (e.g., 6.68% Jaccard improvements on MIMIC-III with p-value << 0.05). Source codes are available at https://github.com/junjzhang7/CRec.

Les discours de la mémoire en Europe. La représentation de la Seconde Guerre mondiale dans le discours des manuels français et polonais. Causalité et agentivité

This paper deals with the educational discourse used in French and Polish history textbooks addressed to adolescents and published in a so-called modern-day model of textbooks. The study falls under the continuity of the French discourse analysis in a contrastive dimension, the object of which is the description of different “discursive cultures” based on their verbal productions. The hypothesis developed in this study is that French and Polish textbooks diff er in their representation of causality and agentivity, which contributes, through discourse infl ections, to the construction of two different memories of the course of events. The two concepts mentioned are, indeed, organizing principles of the educational discourse analysed, since indicating explanatory causes and links between phenomena, anticipating and providing an understanding of consequences are an integral part of the educational activity supported by the popularization discourse we analyse. Our analysis is based on the principles of discourse semantics in a comparative perspective.

Social representations of cancer in patients from Medellín, Colombia: a qualitative study.

Cancer has different explanatory theories that address its etiology and treatment. It is usually associated with pain and suffering. Recently, new technologies, knowledge, and therapies have been developed, which may have transformed the classic social representations of the disease. This study aimed to understand the social representations (SRs) of cancer in patients from Medellín, Colombia. This study used a grounded theory in 16 patients with cancer. The information was collected between June 2020 and May 2021. Information was analyzed following the open, axial, and selective coding stages. SRs of cancer at the time of diagnosis evoke negative connotations. However, cancer is redefined as a positive event as the clinical course of the disease progresses, and patients interact with health professionals and respond to treatment. The resignification of the disease depends on the etiological models of the patients, which include genetic, socio-anthropological, psychosocial, and psychogenic factors. In line with the SRs of etiology, patients seek out treatments complementary to the biomedical ones that can be socio-anthropological and psychogenic. In this group negative representations about cancer persist, this way of understanding the disease is determined by the convergence of cultural meanings and personal experiences. The causal representation is connected to the actions and willingness of the patients to face their diagnosis. In this sense, two categories stand out: the first expresses that cancer is the consequence of a body subjected to excessive productivity; the second subsumes a psychogenic predisposition caused by the context where the ideology of happiness appears to be a social norm. This double saturation in which an individual is immersed results in new burdens that are not visible to caregivers and healthcare workers.

Interpretability Is in the Mind of the Beholder: A Causal Framework for Human-Interpretable Representation Learning.

Research on Explainable Artificial Intelligence has recently started exploring the idea of producing explanations that, rather than being expressed in terms of low-level features, are encoded in terms of interpretable concepts learned from data. How to reliably acquire such concepts is, however, still fundamentally unclear. An agreed-upon notion of concept interpretability is missing, with the result that concepts used by both post hoc explainers and concept-based neural networks are acquired through a variety of mutually incompatible strategies. Critically, most of these neglect the human side of the problem: a representation is understandable only insofar as it can be understood by the human at the receiving end. The key challenge in human-interpretable representation learning (hrl) is how to model and operationalize this human element. In this work, we propose a mathematical framework for acquiring interpretable representations suitable for both post hoc explainers and concept-based neural networks. Our formalization of hrl builds on recent advances in causal representation learning and explicitly models a human stakeholder as an external observer. This allows us derive a principled notion of alignment between the machine's representation and the vocabulary of concepts understood by the human. In doing so, we link alignment and interpretability through a simple and intuitive name transfer game, and clarify the relationship between alignment and a well-known property of representations, namely disentanglement. We also show that alignment is linked to the issue of undesirable correlations among concepts, also known as concept leakage, and to content-style separation, all through a general information-theoretic reformulation of these properties. Our conceptualization aims to bridge the gap between the human and algorithmic sides of interpretability and establish a stepping stone for new research on human-interpretable representations.

Causal Factor Disentanglement for Few-Shot Domain Adaptation in Video Prediction.

An important challenge in machine learning is performing with accuracy when few training samples are available from the target distribution. If a large number of training samples from a related distribution are available, transfer learning can be used to improve the performance. This paper investigates how to do transfer learning more effectively if the source and target distributions are related through a Sparse Mechanism Shift for the application of next-frame prediction. We create Sparse Mechanism Shift-TempoRal Intervened Sequences (SMS-TRIS), a benchmark to evaluate transfer learning for next-frame prediction derived from the TRIS datasets. We then propose to exploit the Sparse Mechanism Shift property of the distribution shift by disentangling the model parameters with regard to the true causal mechanisms underlying the data. We use the Causal Identifiability from TempoRal Intervened Sequences (CITRIS) model to achieve this disentanglement via causal representation learning. We show that encouraging disentanglement with the CITRIS extensions can improve performance, but their effectiveness varies depending on the dataset and backbone used. We find that it is effective only when encouraging disentanglement actually succeeds in increasing disentanglement. We also show that an alternative method designed for domain adaptation does not help, indicating the challenging nature of the SMS-TRIS benchmark.

Relationships between Anxiety, Depression, and Illness Perceptions in Lung and Breast Cancer Patients throughout the Cancer Continuum.

Cancer is a devastating disease that has significant psychological and biological impacts. Generally, lung cancer primarily affects men while breast cancer primarily affects women. Thus, this study aimed to investigate the levels of anxiety and depression in patients with these prevalent cancer types, as well as their perceptions of the illness and any potential connections between them. The study included a total of 252 participants, consisting of 110 breast cancer patients, 112 lung cancer patients, and 30 healthy individuals as controls. The Beck Depression Inventory (BDI) and Beck Anxiety Inventory (BAI) were administered to assess mood, while the Illness Perception Questionnaire (IPQ) was used to evaluate cancer perceptions. Results revealed that both breast cancer and lung cancer patients had significantly higher BDI and BAI scores compared to the control group. Furthermore, the BDI and BAI scores were lower in breast cancer patients compared to lung cancer patients. The IPQ causal representation-immunity score was significantly higher in lung cancer patients than in breast cancer patients (p = 0.01). Positive correlations were found between BDI scores and BAI scores, as well as between BDI scores and certain subscale scores of the IPQ related to illness representation and causal representation. Additionally, a positive correlation was observed between BAI scores and the IPQ illness representation-timeline acute/chronic subscale, while a negative correlation was found between BAI scores and the IPQ causal representation-accident or chance scores. Overall, the study findings demonstrated that breast and lung cancer patients possess negative perceptions of their disease and experience high levels of anxiety and depression. To enhance the quality of life and promote resilience in these patients, it is recommended to incorporate psychological interventions that consider anxiety, depression, and disease perception.

Assessing the impact of blockchain technology on the overall performance of sustainable supply chains: an analytical perspective.

Supply chain control and sustainability can be significantly improved using distributed ledger technologies such as blockchain. The blockchain has the potential to facilitate responsible sourcing appropriately, compliance with weather requirements, and sustainable delivery chains. The purpose of this study is to address the hassle of managing conservatism when approaching era adoption and to explore the performance enhancements in blockchain-generated implementations. To achieve this goal, we introduce a scientific approach aimed at studying the outcomes of various factors in the adoption process in the blockchain era and verifying their impact on the overall performance of the delivery chain. Furthermore, a team of multidisciplinary professionals will establish causal relationships among these elements through a consensus-based approach. Ultimately, fuzzy reasoning tools can be used to determine the relative weights between identified factors and delivery chain performance goals. We will assemble causal representations of diagnoses using a dense scientific map model and dynamically generate scenarios for each. The study demonstrates that the integration of blockchain power generation can significantly improve the effectiveness of mineral supply chains. It uses smart contracts to promote environmental sustainability, traceability, and transparency.

Unbiased Scene Graph Generation via Two-Stage Causal Modeling.

Despite the impressive performance of recent unbiased Scene Graph Generation (SGG) methods, the current debiasing literature mainly focuses on the long-tailed distribution problem, whereas it overlooks another source of bias, i.e., semantic confusion, which makes the SGG model prone to yield false predictions for similar relationships. In this paper, we explore a debiasing procedure for the SGG task leveraging causal inference. Our central insight is that the Sparse Mechanism Shift (SMS) in causality allows independent intervention on multiple biases, thereby potentially preserving head category performance while pursuing the prediction of high-informative tail relationships. However, the noisy datasets lead to unobserved confounders for the SGG task, and thus the constructed causal models are always causal-insufficient to benefit from SMS. To remedy this, we propose Two-stage Causal Modeling (TsCM) for the SGG task, which takes the long-tailed distribution and semantic confusion as confounders to the Structural Causal Model (SCM) and then decouples the causal intervention into two stages. The first stage is causal representation learning, where we use a novel Population Loss (P-Loss) to intervene in the semantic confusion confounder. The second stage introduces the Adaptive Logit Adjustment (AL-Adjustment) to eliminate the long-tailed distribution confounder to complete causal calibration learning. These two stages are model agnostic and thus can be used in any SGG model that seeks unbiased predictions. Comprehensive experiments conducted on the popular SGG backbones and benchmarks show that our TsCM can achieve state-of-the-art performance in terms of mean recall rate. Furthermore, TsCM can maintain a higher recall rate than other debiasing methods, which indicates that our method can achieve a better tradeoff between head and tail relationships.

Counterfactual Graph Learning for Anomaly Detection on Attributed Networks

Graph anomaly detection is attracting remarkable multidisciplinary research interests ranging from finance, healthcare, and social network analysis. Recent advances on graph neural networks have substantially improved the detection performance via semi-supervised representation learning. However, prior work suggests that deep graph-based methods tend to learn spurious correlations. As a result, they fail to generalize beyond training data distribution. In this paper, we aim to identify structural and contextual anomaly nodes in an attributed graph. Based on our preliminary data analyses, spurious correlations can be eliminated with causal subgraph interventions. Therefore, we propose a new graph-based anomaly detection model that can learn causal relations for anomaly detection while generalizing to new environments. To handle situations with varying environments, we steer the generative model to manufacture synthetic environment features, which are exerted on realistic subgraphs to generate counterfactual subgraphs. Further, these counterfactual subgraphs help a few-shot anomaly detection model learn transferable and causal relations across different environments. The experiments on three real-world attributed graphs show that the proposed approach achieves the best performance compared to the state-of-the-art baselines and learns robust causal representations resistant to noises and spurious correlations.

Unsupervised Domain Adaptation by Causal Learning for Biometric Signal-based HCI

Biometric signal based human-computer interface (HCI) has attracted increasing attention due to its wide application in healthcare, entertainment, neurocomputing, and so on. In recent years, deep learning-based approaches have made great progress on biometric signal processing. However, the state-of-the-art (SOTA) approaches still suffer from model degradation across subjects or sessions. In this work, we propose a novel unsupervised domain adaptation approach for biometric signal-based HCI via causal representation learning. Specifically, three kinds of interventions on biometric signals (i.e., subjects, sessions, and trials) can be selected to generalize deep models across the selected intervention. In the proposed approach, a generative model is trained for producing intervened features that are subsequently used for learning transferable and causal relations with three modes. Experiments on the EEG-based emotion recognition task and sEMG-based gesture recognition task are conducted to confirm the superiority of our approach. An improvement of +0.21% on the task of inter-subject EEG-based emotion recognition is achieved using our approach. Besides, on the task of inter-session sEMG-based gesture recognition, our approach achieves improvements of +1.47%, +3.36%, +1.71%, and +1.01% on sEMG datasets including CSL-HDEMG, CapgMyo DB-b, 3DC, and Ninapro DB6, respectively. The proposed approach also works on the task of inter-trial sEMG-based gesture recognition and an average improvement of +0.66% on Ninapro databases is achieved. These experimental results show the superiority of the proposed approach compared with the SOTA unsupervised domain adaptation methods on HCIs based on biometric signal.