Learn Object Representations Research Articles

EdgeSHAPer: Bond-centric Shapley value-based explanation method for graph neural networks

SummaryGraph neural networks (GNNs) recursively propagate signals along the edges of an input graph, integrate node feature information with graph structure, and learn object representations. Like other deep neural network models, GNNs have notorious black box character. For GNNs, only few approaches are available to rationalize model decisions. We introduce EdgeSHAPer, a generally applicable method for explaining GNN-based models. The approach is devised to assess edge importance for predictions. Therefore, EdgeSHAPer makes use of the Shapley value concept from game theory. For proof-of-concept, EdgeSHAPer is applied to compound activity prediction, a central task in drug discovery. EdgeSHAPer’s edge centricity is relevant for molecular graphs where edges represent chemical bonds. Combined with feature mapping, EdgeSHAPer produces intuitive explanations for compound activity predictions. Compared to a popular node-centric and another edge-centric GNN explanation method, EdgeSHAPer reveals higher resolution in differentiating features determining predictions and identifies minimal pertinent positive feature sets.

Discovering prerequisite relations from educational documents through word embeddings

Inferring prerequisite relations among educational documents, in terms of prior knowledge required to understand and complete assignments about certain topics, is a crucial task for instructional designers and teachers. Massive open online courses, electronic textbooks, public encyclopedias and repositories of learning objects and other forms of informative content create a huge availability of educational material, which can be exploited in online platforms for distance education, both for recommending specific resources and personalized learning paths. But public taxonomies of prerequisites, or learning object metadata useful to trace down prerequisites are not generally available.A description of a new approach for prerequisite discovering in educational documents is given. It is based on word embeddings, that is, statistical language models for the representation of text-based learning objects in low-dimensional latent spaces. It takes advantage of the latent representations to identify prerequisites in a binary classification setting. The accuracy of the approach is validated by means of an experimental benchmark covering multiple datasets of educational material.

Rotating Machine Systems Fault Diagnosis Using Semisupervised Conditional Random Field-Based Graph Attention Network

Data-driven intelligent diagnosis methods require sufficient labeled data during training, which are usually limited in practice. A semisupervised conditional random field-based graph attention network (CRF-GAT) algorithm is proposed in this article for fault diagnosis and condition monitoring. The proposed method combines the advantages of CRF and GAT, and therefore, it achieves semisupervised fault diagnosis by modeling the label dependency and learning object representations. The scheme is optimized with the variational expectation–maximization (EM) algorithm. Specially, the clustering with adaptive neighbor (CAN) method is introduced for constructing the graph. The proposed method is applied in induction motor (IM) and permanent magnet synchronous motor (PMSM), which achieves the identification of the motor status, fault severity, and working condition. The results show that the CRF-GAT can realize an accuracy of above 97% with even below 10% of labeled samples for training, which demonstrates that it is an effective method in semisupervised fault diagnosis.

Object Synthesis by Learning Part Geometry with Surface and Volumetric Representations

We propose a conditional generative model, named Part Geometry Network (PG-Net), which synthesizes realistic objects and can be used as a robust feature descriptor for object reconstruction and classification. Surface and volumetric representations of objects have complementary properties of three-dimensional objects. Combining these modalities is more informative than using one modality alone. Therefore, PG-Net utilizes complementary properties of surface and volumetric representations by estimating curvature, surface area, and occupancy in voxel grids of objects with a single decoder as a multi-task learning. Objects are combinations of multiple parts, and therefore part geometry (PG) is essential to synthesize each part of the objects. PG-Net employs a part identifier to learn the part geometry. Additionally, we augmented a dataset by interpolating individual functional parts such as wings of an airplane, which helps learning part geometry and finding local/global minima of PG-Net. To demonstrate the capability of learning object representations of PG-Net, we performed object reconstruction and classification tasks on two standard large-scale datasets. PG-Net outperformed the state-of-the-art methods in object synthesis, classification, and reconstruction in a large margin.

Deep Ensemble Object Tracking Based on Temporal and Spatial Networks

In recent years, correlation filtering and deep learning have achieved good performance in object tracking. Correlation filtering is an efficient and real-time method because its formula provides a fast solution in the Fourier domain, but it does not benefit from end-to-end training. Although deep learning is an effective method for learning object representations, training deep networks online with one or a few examples is challenging. To address these problems, we propose a deep ensemble object tracking algorithm that fuses temporal and spatial information to improve algorithm precision and robustness. The framework of our algorithm includes four aspects: feature extraction, a baseline network, a branch network and adaptive ensemble learning. Feature extraction extracts the general object representation. The baseline network integrates feature extraction and a correlation filtering algorithm into a convolutional neural network for end-to-end training. The branch network is composed of a temporal network and a spatial network. The temporal and spatial networks capture the object temporal and spatial information and further refine the object position. Our algorithm only needs an initial frame to train all networks. Adaptive ensemble learning compensates for the object information deficiency and improves tracking accuracy. Many experiments on tracking benchmark datasets demonstrate that our algorithm performs favourably compared with state-of-the-art tracking algorithms.

MAKING OBJECT LEARNING AND RECOGNITION AN ACTIVE PROCESS

The exploration and learning of new objects is an essential capability of a cognitive robot. In this paper we focus on making use of the robot's manipulation abilities to learn complete object representations suitable for 3D object recognition. Taking control of the object allows the robot to focus on relevant parts of the images, thus bypassing potential pitfalls of purely bottom-up attention and segmentation. The main contribution of the paper consists in integrated visuomotor processes that allow the robot to learn object representations by manipulation without having any prior knowledge about the objects. Our experimental results show that the acquired data is of sufficient quality to train a classifier that can recognize 3D objects independently of the viewpoint.

Information Retrieval in Virtual Universities

Information retrieval in the context of virtual universities deals with the representation, organization, and access to learning objects. The representation and organization of learning objects should provide the learner with an easy access to the learning objects. In this article, we give an overview of the ONES system, and analyze the relevance of two information retrieval models for virtual universities. We argue that keywords based search (i.e., the Boolean model), though well suited for Web searches, is overly coarse for virtual universities. Instead, the vector model, on which our implemented search engine is also based on, seems to be more appropriate as it provides similarity measure (i.e., the learning object having the best match is presented first). We also compare the performance of four algorithms for computing the similarities (matching).

Information Retrieval in Virtual Universities

Information retrieval in the context of virtual universities deals with the representation, organization and access to learning objects. The representation and organization of learning objects should provide the learner with an easy access to the learning objects. In this paper, we give an overview of the ONES system and analyze the relevance of two information retrieval models for virtual universities. We argue that keywords-based search (i.e., the Boolean model), though well suited for Web searches, is overly coarse for virtual universities. Instead, the vector model, on which our implemented search engine also is based, seems to be more appropriate, as it provides similarity measure (i.e., the learning object having the best match is presented first). We also compare the performance of four algorithms for computing the similarities (matching).

An ontological representation of learning objects and learning designs as codified knowledge

PurposeThe aim of this paper is discussing about the similarities between the life cycle of knowledge management and the processes in which learning objects are created, evaluated and used.Design/methodology/approachThe paper describes LO and learning designs and depicts their integration into the knowledge life cycle (KLC) of the KMCI, showing the main ontological definitions required to represent the proposed integration, putting them into relation with previous research in the topic.FindingsThe main points in that the “learning object” concept can be connected to existing KLC models in order to provide a more comprehensive framework for reuse‐oriented e‐learning and knowledge management.Originality/valueThe paper describes how to integrate learning‐oriented artefacts as part of the organizational context, in particular, as part of the knowledge life cycle (KLC). It also depicts the integration of a reuse‐oriented e‐learning framework into the KLC of the KMCI in the form of ontological definitions.