Motivation: This is a complete paper. There was a sudden shift from traditional learning to online learning in Spring 2020 with the outbreak of COVID-19. Although online learning is not a new topic of discussion, universities, faculty, and students were not prepared for this sudden change in learning. According to a recent article in ‘The Chronicle of Higher Education, “even under the best of circumstances, virtual learning requires a different, carefully crafted approach to engagement”. The Design Thinking course under study is a required freshmen level course offered in a Mid-western University. The Design Thinking course is offered in a flipped format where all the content to be learned is given to students beforehand and the in-class session is used for active discussions and hands-on learning related to the content provided at the small group level. The final learning objective of the course is a group project where student groups are expected to come up with functional prototypes to solve a real-world problem following the Design Thinking process. There were eighteen sections of the Design Thinking course offered in Spring 2020, and with the outbreak of COVID-19, a few instructors decided to offer synchronous online classes (where instructors were present online during class time and provided orientation and guidance just like a normal class) and a few others decided to offer asynchronous online classes (where orientation from the instructor was delivered asynchronous and the instructor was online during officially scheduled class time but interactions were more like office hours). Students were required to be present synchronously at the team level during the class time in a synchronous online class. In an asynchronous online class, students could be synchronous at the team level to complete their assignment any time prior to the deadline such that they could work during class time but they were not required to work at that time. Through this complete paper, we are trying to understand student learning, social presence and learner satisfaction with respect to different modes of instruction in a freshmen level Design Thinking course. Background: According to literature, synchronous online learning has advantages such as interaction, a classroom environment, and better course quality whereas asynchronous online learning has advantages such as self-controlled and self-directed learning. The disadvantages of synchronous online learning include the learning process, technology issues, and distraction. Social isolation, lack of interaction, and technology issue are a few disadvantages related to asynchronous online learning. Problem Being Addressed: There is a limited literature base investigating different modes of online instruction in a Design Thinking course. Through this paper, we are trying to understand and share the effectiveness of synchronous and asynchronous modes of instruction in an online Flipped Design Thinking Course. The results of the paper could also help in this time of pandemic by shedding light on the more effective way to teach highly active group-based classrooms for better student learning, social presence, and learner satisfaction. Method/Assessment: An end of semester survey was monitored in Spring 2020 to understand student experiences in synchronous and asynchronous Design Thinking course sections. The survey was sent to 720 students enrolled in the course in Spring 2020 and 324 students responded to the survey. Learning was measured using the survey instrument developed by Walker (2003) and the social presence and learner satisfaction was measured by the survey modified by Richardson and Swan (2003). Likert scale was used to measure survey responses. Anticipated Results: Data would be analyzed and the paper would be completed by draft paper submission. As the course under study is a flipped and active course with a significant component of group work, the anticipated results after analysis could be that one mode of instruction has higher student learning, social presence, and learner satisfaction compared to the other.
more »
« less
Few-Shot Image Recognition with Manifolds
In this paper, we extend the traditional few-shot learning (FSL) problem to the situation when the source-domain data is not accessible but only high-level information in the form of class prototypes is available. This limited information setup for the FSL problem deserves much attention due to its implication of privacy-preserving inaccessibility to the source-domain data but it has rarely been addressed before. Because of limited training data, we propose a non-parametric approach to this FSL problem by assuming that all the class prototypes are structurally arranged on a manifold. Accordingly, we estimate the novel-class prototype locations by projecting the few-shot samples onto the average of the subspaces on which the surrounding classes lie. During classification, we again exploit the structural arrangement of the categories by inducing a Markov chain on the graph constructed with the class prototypes. This manifold distance obtained using the Markov chain is expected to produce better results compared to a traditional nearest- neighbor-based Euclidean distance. To evaluate our proposed framework, we have tested it on two image datasets – the large-scale ImageNet and the small-scale but fine-grained CUB-200. We have also studied parameter sensitivity to better understand our framework.
more »
« less
- Award ID(s):
- 1813935
- NSF-PAR ID:
- 10288174
- Editor(s):
- Bebis, G. et
- Date Published:
- Journal Name:
- International Symposium on Visual Computing (ISVC), San Diego, CA, Oct. 5-7, 2020. In: Bebis G. et al. (eds) Advances in Visual Computing. ISVC 2020. Lecture Notes in Computer Science, vol 12510. Springer, Cham
- Volume:
- 12510
- Page Range / eLocation ID:
- 3-14
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Elofsson, Arne (Ed.)Abstract Motivation Cryoelectron tomography (cryo-ET) visualizes structure and spatial organization of macromolecules and their interactions with other subcellular components inside single cells in the close-to-native state at submolecular resolution. Such information is critical for the accurate understanding of cellular processes. However, subtomogram classification remains one of the major challenges for the systematic recognition and recovery of the macromolecule structures in cryo-ET because of imaging limits and data quantity. Recently, deep learning has significantly improved the throughput and accuracy of large-scale subtomogram classification. However, often it is difficult to get enough high-quality annotated subtomogram data for supervised training due to the enormous expense of labeling. To tackle this problem, it is beneficial to utilize another already annotated dataset to assist the training process. However, due to the discrepancy of image intensity distribution between source domain and target domain, the model trained on subtomograms in source domain may perform poorly in predicting subtomogram classes in the target domain. Results In this article, we adapt a few shot domain adaptation method for deep learning-based cross-domain subtomogram classification. The essential idea of our method consists of two parts: (i) take full advantage of the distribution of plentiful unlabeled target domain data, and (ii) exploit the correlation between the whole source domain dataset and few labeled target domain data. Experiments conducted on simulated and real datasets show that our method achieves significant improvement on cross domain subtomogram classification compared with baseline methods. Availability and implementation Software is available online https://github.com/xulabs/aitom. Supplementary information Supplementary data are available at Bioinformatics online.more » « less
-
more » « less
The problem of few-shot graph classification targets at assigning class labels for graph samples, where only limited labeled graphs are provided for each class. To solve the problem brought by label scarcity, recent studies have proposed to adopt the prevalent few-shot learning framework to achieve fast adaptations to graph classes with limited labeled graphs. In particular, these studies typically propose to accumulate meta-knowledge across a large number of meta-training tasks, and then generalize such meta-knowledge to meta-test tasks sampled from a disjoint class set. Nevertheless, existing studies generally ignore the crucial task correlations among meta-training tasks and treat them independently. In fact, such task correlations can help promote the model generalization to meta-test tasks and result in better classification performance. On the other hand, it remains challenging to capture and utilize task correlations due to the complex components and interactions in meta-training tasks. To deal with this, we propose a novel few-shot graph classification framework FAITH to capture task correlations via learning a hierarchical task structure at different granularities. We further propose a task-specific classifier to incorporate the learned task correlations into the few-shot graph classification process. Moreover, we derive FAITH+, a variant of FAITH that can improve the sampling process for the hierarchical task structure. The extensive experiments on four prevalent graph datasets further demonstrate the superiority of FAITH and FAITH+ over other state-of-the-art baselines.
-
We study the problem of few-shot Fine-grained Entity Typing (FET), where only a few annotated entity mentions with contexts are given for each entity type. Recently, prompt-based tuning has demonstrated superior performance to standard fine-tuning in few-shot scenarios by formulating the entity type classification task as a “fill-in-the-blank” problem. This allows effective utilization of the strong language modeling capability of Pre-trained Language Models (PLMs). Despite the success of current prompt-based tuning approaches, two major challenges remain: (1) the verbalizer in prompts is either manually designed or constructed from external knowledge bases, without considering the target corpus and label hierarchy information, and (2) current approaches mainly utilize the representation power of PLMs, but have not explored their generation power acquired through extensive general-domain pre-training. In this work, we propose a novel framework for fewshot FET consisting of two modules: (1) an entity type label interpretation module automatically learns to relate type labels to the vocabulary by jointly leveraging few-shot instances and the label hierarchy, and (2) a type-based contextualized instance generator produces new instances based on given instances to enlarge the training set for better generalization. On three benchmark datasets, our model outperforms existing methods by significant margins.more » « less
-
Few-shot node classification aims at classifying nodes with limited labeled nodes as references. Recent few-shot node classification methods typically learn from classes with abundant labeled nodes (i.e., meta-training classes) and then generalize to classes with limited labeled nodes (i.e., meta-test classes). Nevertheless, on real-world graphs, it is usually difficult to obtain abundant labeled nodes for many classes. In practice, each meta-training class can only consist of several labeled nodes, known as the extremely weak supervision problem. In few-shot node classification, with extremely limited labeled nodes for meta-training, the generalization gap between meta-training and meta-test will become larger and thus lead to suboptimal performance. To tackle this issue, we study a novel problem of few-shot node classification with extremely weak supervision and propose a principled framework X-FNC under the prevalent meta-learning framework. Specifically, our goal is to accumulate meta-knowledge across different meta-training tasks with extremely weak supervision and generalize such knowledge to meta-test tasks. To address the challenges resulting from extremely scarce labeled nodes, we propose two essential modules to obtain pseudo-labeled nodes as extra references and effectively learn from extremely limited supervision information. We further conduct extensive experiments on four node classification datasets with extremely weak supervision to validate the superiority of our framework compared to the state-of-the-art baselines.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/https://doi.org/10.1007/978-3-030-64559-5_1
