Multi-Source cross-lingual transfer learning deals with the transfer of task knowledge from multiple labelled source languages to an unlabeled target language under the language shift. Existing methods typically focus on weighting the predictions produced by language-specific classifiers of different sources that follow a shared encoder. However, all source languages share the same encoder, which is updated by all these languages. The extracted representations inevitably contain different source languages' information, which may disturb the learning of the language-specific classifiers. Additionally, due to the language gap, language-specific classifiers trained with source labels are unable to make accurate predictions for the target language. Both facts impair the model's performance. To address these challenges, we propose a Disentangled and Adaptive Network ~(DA-Net). Firstly, we devise a feedback-guided collaborative disentanglement method that seeks to purify input representations of classifiers, thereby mitigating mutual interference from multiple sources. Secondly, we propose a class-aware parallel adaptation method that aligns class-level distributions for each source-target language pair, thereby alleviating the language pairs' language gap. Experimental results on three different tasks involving 38 languages validate the effectiveness of our approach.

The knowledge distillation-based approaches have recently yielded state-of-the-art (SOTA) results for cross-lingual NER tasks in zero-shot scenarios. These approaches typically employ a teacher network trained with the labelled source (rich-resource) language to infer pseudo-soft labels for the unlabelled target (zero-shot) language, and force a student network to approximate these pseudo labels to achieve knowledge transfer. However, previous works have rarely discussed the issue of pseudo-label noise caused by the source-target language gap, which can mislead the training of the student network and result in negative knowledge transfer. This paper proposes an discrepancy and uncertainty aware Denoising Knowledge Distillation model (DenKD) to tackle this issue. Specifically, DenKD uses a discrepancy-aware denoising representation learning method to optimize the class representations of the target language produced by the teacher network, thus enhancing the quality of pseudo labels and reducing noisy predictions. Further, DenKD employs an uncertainty-aware denoising method to quantify the pseudo-label noise and adjust the focus of the student network on different samples during knowledge distillation, thereby mitigating the noise's adverse effects. We conduct extensive experiments on 28 languages including 4 languages not covered by the pre-trained models, and the results demonstrate the effectiveness of our DenKD.

For named entity recognition (NER) in zero-resource languages, utilizing knowledge distillation methods to transfer language-independent knowledge from the rich-resource source languages to zero-resource languages is an effective means. Typically, these approaches adopt a teacher-student architecture, where the teacher network is trained in the source language, and the student network seeks to learn knowledge from the teacher network and is expected to perform well in the target language. Despite the impressive performance achieved by these methods, we argue that they have two limitations. Firstly, the teacher network fails to effectively learn language-independent knowledge shared across languages due to the differences in the feature distribution between the source and target languages. Secondly, the student network acquires all of its knowledge from the teacher network and ignores the learning of target language-specific knowledge. Undesirably, these limitations would hinder the model's performance in the target language. This paper proposes an unsupervised prototype knowledge distillation network (ProKD) to address these issues. Specifically, ProKD presents a contrastive learning-based prototype alignment method to achieve class feature alignment by adjusting the prototypes' distance from the source and target languages, boosting the teacher network's capacity to acquire language-independent knowledge. In addition, ProKD introduces a prototype self-training method to learn the intrinsic structure of the language by retraining the student network on the target data using samples' distance information from prototypes, thereby enhancing the student network's ability to acquire language-specific knowledge. Extensive experiments on three benchmark cross-lingual NER datasets demonstrate the effectiveness of our approach.

The robustness of graph classification models plays an essential role in providing highly reliable applications. Previous studies along this line primarily focus on seeking the stability of the model in terms of overall data metrics (e.g., accuracy) when facing data perturbations, such as removing edges. Empirically, we find that these graph classification models also suffer from semantic bias and confidence collapse issues, which substantially hinder their applicability in real-world scenarios. To address these issues, we present MGRL, a multi-view representation learning model for graph classification tasks that achieves robust results. Firstly, we proposes an instance-view consistency representation learning method, which utilizes multi-granularity contrastive learning technique to perform semantic constraints on instance representations at both the node and graph levels, thus alleviating the semantic bias issue. Secondly, we proposes a class-view discriminative representation learning method, which employs the prototype-driven class distance optimization technique to adjust intra- and inter-class distances, thereby mitigating the confidence collapse issue.Finally, extensive experiments and visualizations on eight benchmark dataset demonstrate the effectiveness of MGRL.

Abstract Pulmonary lobe segmentation is an important prerequisite for accurately quantifying pulmonary damage in many pulmonary diseases and planning treatment. However, due to the incomplete lobar structures and morphological changes caused by diseases, the lobe segmentation still encounters great challenges. In this study, a Learnable Interpolation and Extrapolation Network (LIE‐Net) is proposed to form complete and consecutive fissure surfaces by learning to extract information of the fissures from existing fissure points and absent points (unsegmented points belonging to fissures) to predict the z coordinate of the absent fissure points. The completed pulmonary fissures are further used for accurate pulmonary lobe segmentation. Specifically, LIE‐Net takes the coordinate information of existing fissure points (their ( x , y , z ) coordinates) and absent fissure points (their ( x , y ) coordinates) as two independent inputs, and predicts the z coordinates of absent points. The proposed LIE‐Net makes voxel‐wise predictions based on the spatial structure characteristics of the lung fissure, and is able to provide a consecutive fissure surface in space. According to the evaluation of radiologists, the lobe segmentation performance was remarkably enhanced in approximately 76% of patients in our additional dataset after the application of LIE‐Net, especially for those cases with large‐scale missing fissures.

Constructing a robust conversation graph based false information detection model is crucial for real social platforms. Recently, graph neural network (GNN) methods for false information detection have achieved significant advances. However, we empirically find that slight perturbations in the conversation graph can cause the predictions of existing models to collapse. To address this problem, we present RDCL, a contrastive learning framework for false information detection on social networks, to obtain robust detection results. RDCL leverages contrastive learning to maximize the consistency between perturbed graphs from the same original graph and minimize the distance between perturbed and original graphs from the same class, forcing the model to improve resistance to data perturbations. Moreover, we prove the importance of hard positive samples for contrastive learning and propose a hard positive sample pairs generation method (HPG) for conversation graphs, which can generate stronger gradient signals to improve the contrastive learning effect and make the model more robust. Experiments on various GNN encoders and datasets show that RDCL outperforms the current state-of-the-art models.

Enhancing the interpretability of text classification models can help increase the reliability of these models in real-world applications. Currently, most researchers focus on extracting task-specific words from inputs to improve the interpretability of the model. The competitive approaches exploit the Variational Information Bottleneck (VIB) to improve the performance of word masking at the word embedding layer to obtain task-specific words. However, these approaches ignore the multi-level semantics of the text, which can impair the interpretability of the model, and do not consider the risk of representation overlap caused by the VIB, which can impair the classification performance. In this paper, we propose an enhanced variational word masks approach, named E-VarM, to solve these two issues effectively. The E-VarM combines multi-level semantics from all hidden layers of the model to mask out task-irrelevant words and uses contrastive learning to readjust the distances between representations. Empirical studies on ten benchmark text classification datasets demonstrate that our approach outperforms the SOTA methods in simultaneously improving the interpretability and accuracy of the model.

Current works about false information detection based on conversation graphs on social networks focus primarily on two research streams from the standpoint of topic distribution: intopic and cross-topic techniques, which assume that the data topic distribution is identical or cross, respectively.This signifies that all test data topics are seen or unseen by the model.However, these assumptions are too harsh for actual social networks that contain both seen and unseen topics simultaneously, hence restricting their practical application.In light of this, this paper develops a novel open-topic scenario that is better suited to actual social networks.In this open-topic scenario, we empirically find that the existing models suffer from impairment in the detection performance for seen or unseen topic data, resulting in poor overall model performance.To address this issue, we propose a novel Contrastive Adversarial Learning Network, CALN, that employs an unsupervised topic clustering method to capture topic-specific features to enhance the model's performance for seen topics and an unsupervised adversarial learning method to align data representation distributions to enhance the model's generalisation to unseen topics.Experiments on two benchmark datasets and a variety of graph neural networks demonstrate the effectiveness of our approach.

Owing to the combination of high-speed data transmission and ubiquitous coverage, the hybrid light fidelity (LiFi) and wireless fidelity (WiFi) network (HLWNet) has been recently proposed as a promising scheme for the next generation indoor wireless network. The handover problem in the HLWNet, however, becomes critical, due to the small cell size of the LiFi access point and the line-of-sight propagation of the optical signal. To provide accurate and timely handover decisions for the HLWNet,$w$e regard the handover in HLWNet as a pattern recognition problem for the first time. In this paper, channel quality, optical channel blockage, user movement, and device orientation are characterized to model a practical simulation scenario. Two different pattern recognition techniques have been applied to design handover algorithms in the HLWNet. The simulation results show that the proposed handover algorithms are able to provide higher user throughput, lower handover rate, and better robustness performance as compared to benchmarks.

Customers can raise various aspects of concerns and anxieties during their participation in gamified social mobile marketing campaigns. To gain insights into how to address these anxieties, this research explores the impact of group-formation gamification mechanisms on users’ emotional anxiety and their intentions to participate in such campaigns. A research model depicting group-formation gamification strategies, user anxieties and participation intentions in gamified social mobile marketing campaigns was proposed and examined through experiments involving 232 participants, which were triangulated by electroencephalogram (EEG) tests and follow-up interviews. The results of this study showed that compared with weak-tie group-formation mechanisms, strong-tie mechanisms can result in a lower level of user emotional anxiety, including reductions in user manipulation anxiety, user privacy anxiety and social image anxiety, which in turn led to higher user intentions to participate in the gamified social mobile marketing campaign. Moreover, it was found that user gender and disposable incomes had significant moderating effects on user anxiety during their interactions with the campaign.

Abstract We present an efficient and stable framework, called Unified Intersection Resolver (UIR), for cloth simulation systems where not only impending collisions but also pre‐existing penetrations often arise. These two types of collisions are handled in a unified manner, by detecting edge‐face intersections first and then forming penetration stencils to be resolved iteratively. A stencil is a quadruple of vertices and it reveals either a vertex‐face or an edge‐edge collision event happened. Each quadruple also implicitly defines a collision normal, through which the four stencil vertices can be relocated, so that the corresponding edge‐face intersection disappear. We deduce three different ways, i.e., from predefined surface orientation, from history data and from global intersection analysis, to determine the collision normals of these stencils robustly. Multiple stencils that constitute a penetration region are processed simultaneously to eliminate penetrations. Cloth trapped in pinched environmental objects can be handled easily within our framework. We highlight its robustness by a number of challenging experiments involving collisions.

Abstract The cloth simulation systems often suffer from excessive extension on the polygonal mesh, so an additional strain‐limiting process is typically used as a remedy in the simulation pipeline. A cloth model can be discretized as either a quadrilateral mesh or a triangular mesh, and their strains are measured differently. The edge‐based strain‐limiting method for a quadrilateral mesh creates anisotropic behaviour by nature, as discretization usually aligns the edges along the warp and weft directions. We improve this anisotropic technique by replacing the traditionally used equality constraints with inequality ones in the mathematical optimization, and achieve faster convergence. For a triangular mesh, the state‐of‐the‐art technique measures and constrains the strains along the two principal (and constantly changing) directions in a triangle, resulting in an isotropic behaviour which prohibits shearing. Based on the framework of inequality‐constrained optimization, we propose a warp and weft strain‐limiting formulation. This anisotropic model is more appropriate for textile materials that do not exhibit isotropic strain behaviour.

To synthesize real-time and realistic facial animation, we present an effective algorithm which combines image- and geometry-based methods for facial animation simulation. Considering the numerous motion units in the expression coding system, we present a novel simplified motion unit based on the basic facial expression, and construct the corresponding basic action for a head model. As image features are difficult to obtain using the performance driven method, we develop an automatic image feature recognition method based on statistical learning, and an expression image semi-automatic labeling method with rotation invariant face detection, which can improve the accuracy and efficiency of expression feature identification and training. After facial animation redirection, each basic action weight needs to be computed and mapped automatically. We apply the blend shape method to construct and train the corresponding expression database according to each basic action, and adopt the least squares method to compute the corresponding control parameters for facial animation. Moreover, there is a pre-integration of diffuse light distribution and specular light distribution based on the physical method, to improve the plausibility and efficiency of facial rendering. Our work provides a simplification of the facial motion unit, an optimization of the statistical training process and recognition process for facial animation, solves the expression parameters, and simulates the subsurface scattering effect in real time. Experimental results indicate that our method is effective and efficient, and suitable for computer animation and interactive applications.