Domain Adaptation Research Articles

Learn from Simulations, Adapt to Observations: Super-Resolution of Isoprene Emissions via Unpaired Domain Adaptation

Plants emit biogenic volatile organic compounds (BVOCs), such as isoprene, significantly influencing atmospheric chemistry and climate. BVOC emissions estimated from bottom-up (BU) approaches (derived from numerical simulations) usually exhibit denser and more detailed spatial information compared to those estimated through top-down (TD) approaches (derived from satellite observations). Moreover, numerically simulated emissions are typically easier to obtain, even if they are less reliable than satellite acquisitions, which, being derived from actual measurements, are considered a more trustworthy instrument for performing chemistry and climate investigations. Given the coarseness and relative lack of satellite-derived measurements, fine-grained numerically simulated emissions could be exploited to enhance them. However, simulated (BU) and observed (TD) emissions usually differ regarding value range and spatiotemporal resolution. In this work, we present a novel deep learning (DL)-based approach to increase the spatial resolution of satellite-derived isoprene emissions, investigating the adoption of efficient domain adaptation (DA) techniques to bridge the gap between numerically simulated emissions and satellite-derived emissions, avoiding the need for retraining a specific super-resolution (SR) algorithm on them. For this, we propose a methodology based on the cycle generative adversarial network (CycleGAN) architecture, which has been extensively used for adapting natural images (like digital photographs) of different domains. In our work, we depart from the standard CycleGAN framework, proposing additional loss terms that allow for better DA and emissions’ SR. We extensively demonstrate the proposed method’s effectiveness and robustness in restoring fine-grained patterns of observed isoprene emissions. Moreover, we compare different setups and validate our approach using different emission inventories from both domains. Eventually, we show that the proposed DA strategy paves the way towards robust SR solutions even in the case of spatial resolution mismatch between the training and testing domains and in the case of unknown testing data.

Approximate Geometric Structure Transfer for Cross-Domain Image Classification

The main purpose of domain adaptation (DA) is to conduct cross-domain related knowledge transfer. Considering the issue of unsupervised DA (UDA), learning a transformation that reduces the differences between domains is the primary goal. In addition to minimizing both the marginal and conditional distributions between the source and target domains, many methods explore potential factors that show the commonalities among domains to yield improved learning efficiency. However, geometric structure information is overlooked by most existing approaches, indicating that the shared information between domains has not been fully exploited. On account of this finding, by taking advantage of more potential shared factors to further enhance the results of DA, we propose an approximate geometric structure transfer (AGST) method for cross-domain image classification in this paper. By combining structural consistency and sample reweighting techniques, AGST encodes the geometric structure information taken from the samples in both domains, enabling it to easily obtain richer interdomain features and effectively facilitate knowledge transfer. Extensive experiments are conducted on several cross-domain data benchmarks. The experimental results indicate that our AGST method can outperform many state-of-the-art algorithms.

Adversarial Unsupervised Domain Adaptation for 3D Semantic Segmentation with 2D Image Fusion of Dense Depth

AbstractUnsupervised domain adaptation (UDA) is increasingly used for 3D point cloud semantic segmentation tasks due to its ability to address the issue of missing labels for new domains. However, most existing unsupervised domain adaptation methods focus only on uni‐modal data and are rarely applied to multi‐modal data. Therefore, we propose a cross‐modal UDA on multi‐modal datasets that contain 3D point clouds and 2D images for 3D Semantic Segmentation. Specifically, we first propose a Dual discriminator‐based Domain Adaptation (Dd‐bDA) module to enhance the adaptability of different domains. Second, given that the robustness of depth information to domain shifts can provide more details for semantic segmentation, we further employ a Dense depth Feature Fusion (DdFF) module to extract image features with rich depth cues. We evaluate our model in four unsupervised domain adaptation scenarios, i.e., dataset‐to‐dataset (A2D2 → SemanticKITTI), Day‐to‐Night, country‐to‐country (USA → Singapore), and synthetic‐to‐real (VirtualKITTI → SemanticKITTI). In all settings, the experimental results achieve significant improvements and surpass state‐of‐the‐art models.

Domain reinforcement feature adaptation methodology with correlation alignment for compound fault diagnosis of rolling bearing

In the long-term operation process, rolling bearings often have multiple single faults or cascade faults, which are coupled with each other to form the compound fault. The complex coupling components of compound fault lead to difficultly building a correlation between compound fault feature and fault class. Moreover, for the transfer learning based on domain adaptation, compound fault feature of source domain is pretty different from that of target domain, thus knowledge of source domain is hard to be transferred into the cross-domain unsupervised learning process of target domain. To solve above mentioned problems well, this paper proposes a domain reinforcement feature adaptation methodology with correlation alignment (CA-DRFA) to complete the cross-domain compound fault diagnosis of bearings. Specifically, a deep reinforcement learning model is improved by being combined with the domain adversarial training way, and meanwhile the correlation alignment metrics is adopted to enhance the generalization performance in feature alignment. In addition, two experiments and an engineering application are performed to demonstrate that CA-DRFA outperforms other popular cross-domain fault diagnosis methods in cross cutting condition and speed transfer tasks. Overall, CA-DRFA is able to implement cross-domain compound fault diagnosis with high accuracy, and effectively reduce the cost of labeling target samples.

Anti-forgetting source-free domain adaptation method for machine fault diagnosis

Unsupervised domain adaptation methods have made significant progress in the field of machine fault diagnosis. However, these methods generally assume the accessibility of source domain data during the cross-domain transfer phase. In practice, this assumption is often impractical due to data privacy requirements and the burden of data transmission and storage. Additionally, a key challenge lies in preventing the forgetting of source domain knowledge while performing cross-domain diagnosis in a source-free scenario. To address these issues, this paper proposes an anti-forgetting source-free domain adaptation method for machine fault diagnosis. Specifically, a prototype-based pseudo-label generation strategy, combined with a nearest-neighbor constraint, is employed to deeply explore diagnosis information in the unlabeled target domain data. Then, a fast nuclear-norm maximization constraint is introduced to reduce the density of target domain samples near the classification boundary, thereby decreasing the probability of misdiagnosis. Furthermore, a weighted Fisher regularization is designed to retain the diagnosis information of healthy states inherent in the source domain, thus mitigating information forgetting. Finally, comprehensive experiments are conducted to validate the superiority of our method in source-free cross-domain diagnosis from multiple perspectives, while also demonstrating its anti-forgetting properties.

Cross-domain intelligent diagnostics for rotating machinery using domain adaptive and adversarial networks

Accurate fault diagnosis of rotating machinery is critical to avoid catastrophic accidents. However, insufficient fault data seriously limit the performance of fault diagnosis in industrial applications. In this paper, a novel domain adaptive and adversarial network (DAAN) is proposed for data-driven fault diagnosis of the rotating machinery, which consists of a deep feature extractor, a domain classifier, and a label adaptive predictor. The deep feature extractor and domain classifier are constructed to obtain domain-invariant features by domain-adversarial training. Then, in the label adaptive predictor, a domain adaptation technique is used to reduce the feature discrepancy between the source domain and the target domain, so as to establish a mapping relationship between the data feature distribution of the two domains. Furtherly, a new transfer diagnosis method is proposed by using the DAAN, which combines the data generated by experimental simulation with deep transfer learning, to realize end-to-end intelligent fault diagnosis of the in-service machinery with few unlabeled fault samples. The proposed method explores a new solution for applying laboratory data to intelligent fault diagnosis in real scenarios. Several transfer experiments are implemented to verify the effectiveness of the proposed method by using 55 roller bearings and 4 gearboxes under various scenarios. The experimental results show that the diagnostic performance of proposed method is much better than other transfer learning methods and non-transfer learning methods.

An effective unsupervised domain adaptation for in-field potato disease recognition

Accurate disease recognition through computer vision is crucial for the intelligent management of potato production. Popular data-driven classification methods face challenges including limited labelled data and poor model portability. Unsupervised Domain Adaptation (UDA) addresses these challenges with a novel learning strategy. However, the complex field environment introduces a significant domain shift problem due to varying conditions. Existing UDA methods usually concentrate on aligning global data distribution and employ a single structure for disease feature extraction, thereby limiting their efficacy in true field environment. To tackle this challenge of potato disease recognition, the Multi-Representation Adaptive Network (MRSAN) based on subdomain alignment is presented. MRSAN effectively aligns feature distributions across diverse data by minimising distribution differences among relevant subdomains. Simultaneously, the multi-representation extraction method captures finer details from various perspectives in the disease images. The combination of these two approaches efficiently mitigates the adverse effects caused by various interference factors in field environment. Based on the acquisition conditions of light variation and disease progression, two field potato disease image datasets are created, containing five and six kinds of potato leaf disease, respectively. Extensive transfer experiments are conducted on the two datasets. MRSAN achieves average classification accuracies of 87.03% and 80.06% on the datasets for the corresponding transfer tasks, outperforming the other compared methods. This not only validates the effectiveness of MRSAN but also demonstrates its robust ability to generalise across changes in regard to light variation and disease progression.

Adaptive soft-sensor update by Latest Sample Targeting Frustratingly Easy Domain Adaptation

Soft-sensors are widely used in manufacturing processes to estimate key process variables; however, their performance may deteriorate when process characteristics change. Although Just-In-Time (JIT) modeling techniques have been proposed for adaptive soft-sensor design, they do not always adapt to abrupt changes. Transfer learning (TL) has been suggested as a means to address this issue, with Frustratingly Easy Domain Adaptation (FEDA) being used for soft-sensor design. This study proposes a new TL method called Latest Sample Targeting-FEDA (LST-FEDA) for JIT-based soft-sensor, which can handle both sudden and gradual changes in process characteristics. LST-FEDA updates soft-sensors using a fixed number of latest samples whenever a new sample is obtained. The effectiveness of the proposed method was demonstrated using simulation data from a vinyl acetate monomer (VAM) process and actual operation data from a fluorine-based monomer (FM) process. LST-FEDA accurately estimated objective variables during sudden malfunctions and scheduled maintenance, contributing to efficient and safe process operation.

Source free domain adaptation for kidney and tumor image segmentation with wavelet style mining

Kidney cancer is a serious malignant disease, and early diagnosis along with precise segmentation are crucial for effective treatment. However, due to the scarcity of labelled medical image data, the development of the intelligent diagnosis of kidney cancer is restricted. To address this challenge, we propose a novel unsupervised domain adaptation (UDA) framework specifically designed for kidney and tumor CT image segmentation. Our framework consists of a generation phase and an adaptation phase. In the generation phase, we employ a wavelet-based style mining generator to create class-specific source-like images, facilitating domain alignment. In the adaptation phase, we introduce contrastive domain extraction and compact-aware domain consistency modules, enhancing feature-level and output-level adaptability through data augmentation techniques. Experimental results demonstrate that our method performs better in kidney and tumor segmentation tasks, exhibiting higher accuracy and generalization capability than state-of-the-art domain adaptation methods. This indicates that our approach has significant advantages in medical image segmentation for kidneys and tumors.

Unsupervised domain adaptation for drive-by condition monitoring of multiple railway tracks

Monitoring railway tracks through drive-by vibration data collected by in-service trains offers a cost-effective and adaptable solution for inspecting multiple railway lines. However, numerous existing drive-by monitoring methods rely on supervised learning models, necessitating extensive labelled data for each line. In this paper, a novel framework is proposed based on Unsupervised Domain Adaptation (UDA) concept which facilitates the transfer of a geometric defects diagnosis model learned from one line to a new line without the need for any labelled data from the new line. The proposed framework learns the dynamic-based features that are sensitive to damage and also invariant to different railway tracks. It comprises three components: data pre-processing, UDA implementation, and damage diagnosis. The framework uses the data from the source domain, including corresponding labels, as well as the unlabelled data from the target domain as input. The outputs of the framework consist of the predicted labels for the target domain. The performance of the proposed framework is evaluated using a comprehensive dataset of field measurements of a high-speed train passing 4 different lines within the French high-speed rail network. The proposed UDA framework is implemented using four common UDA algorithms including Information-Theoretical Learning (ITL), Geodesic Flow Kernel (GFK), Transfer Component Analysis (TCA), and Subspace Alignment (SA). The results show that the proposed framework has a 14% increase in the anomaly detection accuracy compared to traditional unsupervised learning methods in which UDA is not used. Furthermore, this study investigates the impact of incorporating a percentage of target data labels during training (semi-supervised domain adaptation), along with various sensor layouts and different tuning parameters, on the accuracy of the proposed approach. The results show that the proposed framework can significantly facilitate the monitoring of railway track conditions using the data collected by in-service trains which could be great interest of railway owners.

Health Care Language Models and Their Fine-Tuning for Information Extraction: Scoping Review.

In response to the intricate language, specialized terminology outside everyday life, and the frequent presence of abbreviations and acronyms inherent in health care text data, domain adaptation techniques have emerged as crucial to transformer-based models. This refinement in the knowledge of the language models (LMs) allows for a better understanding of the medical textual data, which results in an improvement in medical downstream tasks, such as information extraction (IE). We have identified a gap in the literature regarding health care LMs. Therefore, this study presents a scoping literature review investigating domain adaptation methods for transformers in health care, differentiating between English and non-English languages, focusing on Portuguese. Most specifically, we investigated the development of health care LMs, with the aim of comparing Portuguese with other more developed languages to guide the path of a non-English-language with fewer resources. This study aimed to research health care IE models, regardless of language, to understand the efficacy of transformers and what are the medical entities most commonly extracted. This scoping review was conducted using the PRISMA-ScR (Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews) methodology on Scopus and Web of Science Core Collection databases. Only studies that mentioned the creation of health care LMs or health care IE models were included, while large language models (LLMs) were excluded. The latest were not included since we wanted to research LMs and not LLMs, which are architecturally different and have distinct purposes. Our search query retrieved 137 studies, 60 of which met the inclusion criteria, and none of them were systematic literature reviews. English and Chinese are the languages with the most health care LMs developed. These languages already have disease-specific LMs, while others only have general-health care LMs. European Portuguese does not have any public health care LM and should take examples from other languages to develop, first, general-health care LMs and then, in an advanced phase, disease-specific LMs. Regarding IE models, transformers were the most commonly used method, and named entity recognition was the most popular topic, with only a few studies mentioning Assertion Status or addressing medical lexical problems. The most extracted entities were diagnosis, posology, and symptoms. The findings indicate that domain adaptation is beneficial, achieving better results in downstream tasks. Our analysis allowed us to understand that the use of transformers is more developed for the English and Chinese languages. European Portuguese lacks relevant studies and should draw examples from other non-English languages to develop these models and drive progress in AI. Health care professionals could benefit from highlighting medically relevant information and optimizing the reading of the textual data, or this information could be used to create patient medical timelines, allowing for profiling.

Beyond borders: The effects of perceived cultural distance, cultural intelligence, cross-cultural adaptation on academic performance among international students of higher education

Perceived cultural distance (PCD) has been established as a significant factor influencing academic performance; however, limited knowledge exists regarding the intricate mediating and moderating mechanisms that underlie this relationship. The present study seeks to contribute to the existing literature by exploring the potential mediating role of cross-cultural adaptation and the moderating influence of cultural intelligence (CQ) in the relationships between PCD and academic performance among international students in China. The theoretical model was tested using survey data that measured international students' PCD, CQ, and cross-cultural adaptation in academic, psychological, and sociocultural domains, along with their academic performance. The findings revealed that (1) PCD exhibits a direct and negative influence on academic performance; (2) Three dimensions of cross-cultural adaptation, namely academic, psychological, and sociocultural adaptation, operate as mediators in the link between PCD and academic performance; (3) CQ, functioning as a moderator, weakens the negative association between PCD and academic performance. These results underscore the pivotal role of PCD in the realm of cross-cultural learning for international students, particularly those engaged in educational pursuits within the Chinese higher education landscape. The study also highlights the protective effects of all four aspects of CQ (metacognitive, cognitive, motivational, and behavioral CQ) on the adaptation processes and academic performance of these sojourning students in the face of cultural differences.

Improving cross-regional model transfer performance in crop classification by crop time series correction

ABSTRACT Cross-Regional Model Transfer (CRMT) provides a solution to crop classification challenges in target regions with limited labeled samples. However, when the source region (source domain) and the target region (target domain) are spatially distant, a shift in crop Satellite Image Time Series (SITS) occurs, resulting in suboptimal performance of SITS-based classification models in the target domain. To address this issue, we propose a novel domain adaptation method, named SITS Correction. This method mitigates the SITS shift by introducing correction factors to improve the classification performance of CRMT. The correction factors consist of source domain correction units and target domain correction units, which are from variables associated with the SITS shift. In cases where labeled samples are available in the target domain, the SITS have calculated Barycenter (i.e. SitsB) as the correction units, which then combine the source domain and the target domain’s SitsB to form a SITS-based correction factor. When no labeled samples are available, the correction units are substituted by Barycenter of the temperature variables time series (i.e. temperature indicator) influencing crop growth, and the correction factors are composed of temperature indicators from both the source and target domains. We validate SITS Correction through transfer experiments conducted in four regions, encompassing various years, crops, and classification methods. Experimental results demonstrate a significant improvement in crop classification performance with SITS Correction in both scenarios – target domain with labeled samples (accuracy increased by 39.1%) and target domain without labeled samples (accuracy increased by 14.8%). This research provides a practical option for crop classification in target regions with either limited or no labeled samples.

Structure preservation constraints for unsupervised domain adaptation intracranial vessel segmentation.

Unsupervised domain adaptation (UDA) has received interest as a means to alleviate the burden of data annotation. Nevertheless, existing UDA segmentation methods exhibit performance degradation in fine intracranial vessel segmentation tasks due to the problem of structure mismatch in the image synthesis procedure. To improve the image synthesis quality and the segmentation performance, a novel UDA segmentation method with structure preservation approaches, named StruP-Net, is proposed. The StruP-Net employs adversarial learning for image synthesis and utilizes two domain-specific segmentation networks to enhance the semantic consistency between real images and synthesized images. Additionally, two distinct structure preservation approaches, feature-level structure preservation (F-SP) and image-level structure preservation (I-SP), are proposed to alleviate the problem of structure mismatch in the image synthesis procedure. The F-SP, composed of two domain-specific graph convolutional networks (GCN), focuses on providing feature-level constraints to enhance the structural similarity between real images and synthesized images. Meanwhile, the I-SP imposes constraints on structure similarity based on perceptual loss. The cross-modality experimental results from magnetic resonance angiography (MRA) images to computed tomography angiography (CTA) images indicate that StruP-Net achieves better segmentation performance compared with other state-of-the-art methods. Furthermore, high inference efficiency demonstrates the clinical application potential of StruP-Net. The code is available at https://github.com/Mayoiuta/StruP-Net .

Threshold-optimized and features-fused semi-supervised domain adaptation method for rotating machinery fault diagnosis

In the field of intelligent fault diagnosis, domain adaptation (DA) technology achieves significant breakthroughs, particularly in reducing reliance on large volumes of labeled samples. Despite these advancements, challenges persist when unlabeled data do not accurately represent actual application scenarios. Additionally, the impact of pseudo-labels on conditional domain adaptation raises concerns. To overcome the above challenges, a novel DA approach based on chaos sparrow search algorithm (CSSOA) optimized threshold parameters and feature fusion deep belief network (DBN) is proposed, named CSS-DADBN. Firstly, this method, by integrating pseudo-label updating with semi-supervised domain adaptation (SSDA) and employing confidence and entropy threshold parameters as corrective rules for pseudo-label filtering, along with the introduction of iterative conditions as an additional selection criterion, effectively alleviates the aforementioned issues. Furthermore, combining the feature extraction capabilities of DBN with a domain feature fusion strategy significantly enhances cross-domain feature learning, thereby substantially improving diagnostic accuracy. Ultimately, to validate the effectiveness and practicality of the CSS-DADBN method, a series of experiments conducted on the PT700 and Case Western Reserve University (CWRU) rolling bearing test platform clearly demonstrate its utility and efficiency in intelligent fault diagnosis.

Domain adaptation for semantic segmentation of road scenes via two-stage alignment of traffic elements

Unsupervised domain adaptation has been used to reduce the domain shift, which would improve the performance of semantic segmentation on unlabeled real-world data. However, existing methodologies fall short in effectively addressing the domain shift issue prevalent in traffic scenarios, leading to less than satisfactory segmentation results. In this paper, we propose a novel domain adaptation method for semantic segmentation via unsupervised alignment of traffic elements. Firstly, we introduce a two-stage self-training framework that leverages a blended set of training samples to enhance the training process. In the first stage, we leverage generated mixup training samples as inputs within our two-stage self-training framework and have developed corresponding loss functions for both the source and target domains to direct the training process. Then, the alignment modules for dynamic and static traffic elements are designed to achieve accurate matching between the source and the target domain images. The cosine similarity maximization is applied to the alignment of dynamic traffic elements, while the prototype learning is utilized for the static traffic elements. Additionally, we present a new technique for reducing noise in pseudo labels by constructing thresholds that adjust to each class. Meanwhile, we formulate the associated target domain loss function for vacant pseudo label pixels. The experimental results demonstrate that the proposed method is superior to the existing methods on five different domain adaptation tasks, which is more applicable to semantic segmentation of road scenes.

A Novel Fault Diagnosis Method for Rolling Bearings Based on Multi-Domain Adaptation Neural Network

In recent years, data-driven approaches have shown promise in fault diagnosis. However, in practical industrial applications, challenges such as discrepancies between source domain and target domain data distributions, coupled with limited labeled fault data, have hindered the performance of traditional domain adaptation algorithms in bearing fault diagnosis. To address this issue, this study introduces a novel method based on MDANN (Multi Domain Adaptation Neural Network) for diagnosing rolling bearing faults using unlabeled data. Initially, the raw vibration signals are preprocessed using wavelet packet decomposition and reconstruction (WPT), which helps minimize signal redundancy while preserving critical features. Following this, the multi-kernel maximum mean discrepancy (MK-MMD) algorithm is employed to compute the differences in input feature values, and the MDANN network parameters are adjusted via backpropagation, allowing the network to extract domain-invariant features. To ensure the unlabeled target domain data can be effectively used in training, a pseudo-labeling strategy is applied, where the label with the highest probability is treated as the true label, thereby enabling the model to learn from the target domain data and improve the acquisition of reliable diagnostic knowledge. The method is validated using two publicly available datasets, CWRU and PU, with experimental results demonstrating that it outperforms conventional domain adaptation techniques in terms of diagnostic accuracy. This indicates the proposed approach is highly effective in capturing transferable features and addressing the distributional differences between datasets.

The localized radial basis function collocation method for dendritic solidification, solid phase sintering and wetting phenomenon based on phase field

Phase-field has been effectively applied to many complex problems according to the mesh based method. However, the computational speed of the numerical method based on phase-field still needs improved. In this paper, an improved localized radial basis function collocation method (LRBFCM) based on the adaptive support domain is employed to the phase-field methods. The proposed adaptive support domain can increase the stability of the LRBFCM, and the improved LRBFCM is much more efficient than the traditional finite element method (FEM) in coupling with phase-field methods. The proposed approach is further applied to the single-phase dendrite solidification, two-phase sintering, and three-phase wetting phenomena. We compare the efficiency of the proposed LRBFCM with different numerical methods, which show that the LRBFCM combined with the Fourier spectral method can deal with the three-phase model with more than ten million nodes easily.

Reducing semantic ambiguity in domain adaptive semantic segmentation via probabilistic prototypical pixel contrast

Domain adaptation aims to reduce the model degradation on the target domain caused by the domain shift between the source and target domains. Although encouraging performance has been achieved by combining contrastive learning with the self-training paradigm, they suffer from ambiguous scenarios caused by scale, illumination, or overlapping when deploying deterministic embedding. To address these issues, we propose probabilistic prototypical pixel contrast (PPPC), a universal adaptation framework that models each pixel embedding as a probability via multivariate Gaussian distribution to fully exploit the uncertainty within them, eventually improving the representation quality of the model. In addition, we derive prototypes from probability estimation posterior probability estimation which helps to push the decision boundary away from the ambiguity points. Moreover, we employ an efficient method to compute similarity between distributions, eliminating the need for sampling and reparameterization, thereby significantly reducing computational overhead. Further, we dynamically select the ambiguous crops at the image level to enlarge the number of boundary points involved in contrastive learning, which benefits the establishment of precise distributions for each category. Extensive experimentation demonstrates that PPPC not only helps to address ambiguity at the pixel level, yielding discriminative representations but also achieves significant improvements in both synthetic-to-real and day-to-night adaptation tasks. It surpasses the previous state-of-the-art (SOTA) by +5.2% mIoU in the most challenging daytime-to-nighttime adaptation scenario, exhibiting stronger generalization on other unseen datasets. The code and models are available at https://github.com/DarlingInTheSV/Probabilistic-Prototypical-Pixel-Contrast.

ADA-UDA: A transferable transformer framework for rumor detection using Adversarial Domain Alignment within Unsupervised Domain Adaptation

The rapid spread of misinformation on social media has posed significant challenges, particularly in the early detection of rumors, which is critical to mitigating their negative impact. However, the limited data available during the initial stages of trending topics poses significant challenges, including analysis constraints and model overfitting. Therefore, the adoption of specific methods are needed to identify patterns from historical sample data and enable effective knowledge transfer, facilitating inductive reasoning with limited data on new topics. To address these challenges, we propose an Adversarial Domain Alignment Unsupervised Domain Adaptation (ADA-UDA) method based on the Transformer architecture. Our approach leverages labeled historical data from the source domain alongside a limited quantity of unlabeled data from new trending topics in the target domain. At the heart of our method is the Parameter Transferable Module (PTM), which guides the Transformer to focus on transferable and distinguishable features, thereby enhancing the model’s ability to perform effective inductive reasoning with limited data. We conducted extensive experiments to evaluate our method, benchmarking it against current mainstream rumor detection techniques. The findings indicate that our ADA-UDA method outperforms existing approaches, underscoring its potential for early and accurate rumor detection in emerging topics.