Collaborative Ensemble Research Articles

A Multilingual Preschooler’s School Belonging: The Role of Translanguaging Pedagogy

ABSTRACT To engage in learning, students must feel a sense of belonging. And yet, children often go to schools where language practices are different from those of their homes and where they often feel alienated. In this article, we look closely at the effects of translanguaging pedagogical practices on one multilingual young child’s sense of belonging in a Luxembourgish preschool, and ultimately in society. The focused video analysis identifies seven significant moments of translanguaging pedagogical interactions between the teacher and the child as she (a) develops the child’s voice as creator/teller of stories, (b) raises the class’s consciousness of multilingualism, (c) emphasizes multilingualism as resource, (d) engages with children’s wondering, (e) elaborates children’s wonderings, (f) creates a sense of being a collaborative ensemble, and finally (g) develops a sense that Luxembourgish belongs to all. Within each moment, we zoom in on the manifestations of the child’s developing sense of belonging by identifying his multimodal interactions with the teacher and with his classmates in relationship to components of belonging: engagement, attachment, connectedness, and community. The analysis shows that the teachers’ use of translanguaging pedagogical practices is related to the child’s increased relationship to people (the teacher and peers), as well as to the place (the pre-school). Beyond the focused child, the analysis shows that translanguaging pedagogical practices also made possible all the children’s sense of belonging as multilingual Luxembourgers.

Domain-augmented meta ensemble learning for mechanical fault diagnosis from heterogeneous source domains to unseen target domains

Existing domain generalization (DG) fault diagnosis methods primarily use adversarial training to reduce shifts between source domains and learn domain-invariant features. However, such features are difficult to learn when dealing with substantial shifts between source domains. In addition, focusing only on domain-invariant and ignoring domain-specific information is not conducive to improving model generalization. Furthermore, these methods are typically developed under an assumption that source domains share the same label space. In situations where the source domains exhibit heterogeneity with inconsistent labels, as explored in this paper, aligning the source domains becomes more difficult due to severe class mismatches. To address the above challenges, this paper proposes a method named domain-augmented meta ensemble learning. Specifically, Dirichlet CutMix is developed to compensate for missing classes in a source domain by utilizing knowledge from other source domains. Moreover, a training strategy summarized as “learn to generalize to unseen domains through collaborative ensemble” is designed to balance the learning of domain-specific features with the ability to generalize across domains. The proposed method is applied to the bearing and gearbox fault diagnosis, and experimental results demonstrate the excellent generalization of the method from heterogeneous source domains to unseen target domains.

“If We Don’t Have a Good Relationship, We Won’t Deliver Anything Good”: Emotion Regulation in Small Music Ensembles, Insights from Higher Music Education

Situated within the context of higher music education, the empirical orientation of this study is on the reflective accounts of young musicians participating in collaborative ensemble work in an educational institution in Norway. Drawing on theories of regulated learning from educational psychology, this study explores the affective and relational aspects of music students’ experiences of small ensembles. Specifically, it examines students’ perceptions of an ideal ensemble environment, socio-emotional challenges encountered during rehearsals, and the emotion-regulation strategies employed within these contexts. Eleven participants, 4 women and 7 men, with a median age of 22, were interviewed. The data were analyzed using a combination of inductive and deductive approaches to thematic analysis. The findings reveal that music students highly value collaborative ensembles as a gateway to acquiring new knowledge and performance skills, which are predominantly gained through peer interaction and active participation in the learning processes. Respect and receptivity emerged as critical qualities for fruitful musical collaborations. Notably, participants prioritized the well-being of the socio-emotional climate over musical competency, underscoring the formative role of emotions in these social learning environments. Furthermore, the study explored the self-reported emotion-regulation strategies employed by student musicians to maintain and/or re-establish a positive socio-emotional group climate. These regulation strategies involved both self- and other- directed processes.

CEKD:Cross ensemble knowledge distillation for augmented fine-grained data

Data augmentation has been proved effective in training deep models. Existing data augmentation methods tackle the fine-grained problem by blending image pairs and fusing corresponding labels according to the statistics of mixed pixels, which produces additional noise harmful to the performance of networks. Motivated by this, we present a simple yet effective cross ensemble knowledge distillation (CEKD) model for fine-grained feature learning. We innovatively propose a cross distillation module to provide additional supervision to alleviate the noise problem, and propose a collaborative ensemble module to overcome the target conflict problem. The proposed model can be trained in an end-to-end manner, and only requires image-level label supervision. Extensive experiments on widely used fine-grained benchmarks demonstrate the effectiveness of our proposed model. Specifically, with the backbone of ResNet-101, CEKD obtains the accuracy of 89.59%, 95.96% and 94.56% in three datasets respectively, outperforming state-of-the-art API-Net by 0.99%, 1.06% and 1.16%.

Polar-Coded Spatial Modulation

In this paper, we propose a framework to attain the integrated design of polar coding and spatial modulation (SM) such that the performance of coded SM-MIMO system can be efficiently improved. This Polar-SM framework recognizes SM and polar coding from a unified perspective of polarization by which the original SM-MIMO channel is split into a series of bit polarized subchannels under the three-stage channel transform, i.e., index-symbol→modulation→bit partitions. This paradigm exploits the underlying weak polarization effect within the SM signal, then concatenates with the binary polarization in polar coding, forming a signal-coding cascaded polarization framework. In particular, the first stage channel transform serially decomposes the original SM-MIMO channel into the index subchannel and the symbol subchannel. This mechanism follows the chain rule of mutual information, which preserves the capacity and maximizes the polarization effect. Combining with modulation and bit partitions, we prove the capacity-achieving property of Polar-SM. From the point of practicality, we propose a rate-filling method to realize a fast and low-complexity code construction of Polar-SM. Guided by the three-stage channel transform, we design a glued successive cancellation list (gSCL) decoding algorithm at the receiver to integrate SM detection and polar decoding as a collaborative ensemble. Simulation results validate the performance gain of Polar-SM over state-of-the-art polar-coded MIMO systems and LDPC-coded SM systems.

Cross-Modality Person Re-Identification via Modality-aware Collaborative Ensemble Learning.

Visible thermal person re-identification (VT-ReID) is a challenging cross-modality pedestrian retrieval problem due to the large intra-class variations and modality discrepancy across different cameras. Existing VT-ReID methods mainly focus on learning cross-modality sharable feature representations by handling the modality-discrepancy in feature level. However, the modality difference in classifier level has received much less attention, resulting in limited discriminability. In this paper, we propose a novel modality-aware collaborative ensemble (MACE) learning method with middle-level sharable two-stream network (MSTN) for VT-ReID, which handles the modality-discrepancy in both feature level and classifier level. In feature level, MSTN achieves much better performance than existing methods by capturing sharable discriminative middlelevel features in convolutional layers. In classifier level, we introduce both modality-specific and modality-sharable identity classifiers for two modalities to handle the modality discrepancy. To utilize the complementary information among different classifiers, we propose an ensemble learning scheme to incorporate the modality sharable classifier and the modality specific classifiers. In addition, we introduce a collaborative learning strategy, which regularizes modality-specific identity predictions and the ensemble outputs. Extensive experiments on two cross-modality datasets demonstrate that the proposed method outperforms current state-of-the-art by a large margin, achieving rank- 1/mAP accuracy 51.64%/50.11% on the SYSU-MM01 dataset, and 72.37%/69.09% on the RegDB dataset.

Understanding Constellations of Technologies in Use in a Collaborative Nomadic Setting

This paper describes how people make sense of and use constellations of technologies in a nomadic setting, and it illustrates how maintaining and orchestrating a variety of applications and devices becomes an essential part of nomadic practices. The data were collected over a period of 3 years at a technical university by means of two field studies. Particular attention is drawn to how the situated orchestration of devices and applications within a group’s constellation reflects university students’ concern to manage their projects at a number of locations, as well as issues of time and circulation of resources. The analysis brings into focus how constellations of technologies emerge and dissolve within collaborative ensembles that only exist for the duration of a project, and how this can cause appropriation issues within groups.

Jam2jam

Jam2jam

Constructing the ‘Dossier Représentatif’

This paper analyzes the complex nature of collaboration in hospitals. Information-sharing under different technological regimes and work organizations is examined with special attention to the role of different types of screen-based records. The need for supporting local practices, professional distance and the different world views of the medical and nursing staff and administrators is stressed. Four meanings of information sharing based on the idea of a ‘dossier representatif’ are explored: (i) a core document of basic patient-related data which is shared by all organizational units and professions; (ii) using the (real time) transfer of data across a distributed environment to strengthen the opportunity for, dialogue; (iii) computer support for ‘browsing’ through a variety of folders that embed different practices; (iv) a unified dossier shared by a bounded collaborative ensemble.