scholarly journals Recent Advances in Heterogeneous Relation Learning for Recommendation

2021 ◽  
Author(s):  
Chao Huang
Keyword(s):  
Web Applications ◽  
Information Overload ◽  
Contextual Information ◽  
Relational Learning ◽  
Critical Role ◽  
Learning Approaches ◽  
Relational Properties ◽  
Graph Neural Networks ◽  
Relation Learning ◽  
Learning Frameworks

Recommender systems have played a critical role in many web applications to meet user's personalized interests and alleviate the information overload. In this survey, we review the development of recommendation frameworks with the focus on heterogeneous relational learning, which consists of different types of dependencies among users and items. The objective of this task is to map heterogeneous relational data into latent representation space, such that the structural and relational properties from both user and item domain can be well preserved. To address this problem, recent research developments can fall into three major categories: social recommendation, knowledge graph-enhanced recommender system, and multi-behavior recommendation. We discuss the learning approaches in each category, such as matrix factorization, attention mechanism and graph neural networks, for effectively distilling heterogeneous contextual information. Finally, we present exploratory outlook to highlight several promising directions and opportunities in heterogeneous relational learning frameworks for recommendation.

scholarly journals Knowledge and Geo-Object Based Graph Convolutional Network for Remote Sensing Semantic Segmentation

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3848
Author(s):  
Wei Cui ◽  
Meng Yao ◽  
Yuanjie Hao ◽  
Ziwei Wang ◽  
Xin He ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Prior Knowledge ◽  
Contextual Information ◽  
Information Aggregation ◽  
Semantic Segmentation ◽  
Spatial Correlations ◽  
Convolutional Network ◽  
Object Based ◽  
Graph Neural Networks ◽  
Salt And Pepper

Pixel-based semantic segmentation models fail to effectively express geographic objects and their topological relationships. Therefore, in semantic segmentation of remote sensing images, these models fail to avoid salt-and-pepper effects and cannot achieve high accuracy either. To solve these problems, object-based models such as graph neural networks (GNNs) are considered. However, traditional GNNs directly use similarity or spatial correlations between nodes to aggregate nodes’ information, which rely too much on the contextual information of the sample. The contextual information of the sample is often distorted, which results in a reduction in the node classification accuracy. To solve this problem, a knowledge and geo-object-based graph convolutional network (KGGCN) is proposed. The KGGCN uses superpixel blocks as nodes of the graph network and combines prior knowledge with spatial correlations during information aggregation. By incorporating the prior knowledge obtained from all samples of the study area, the receptive field of the node is extended from its sample context to the study area. Thus, the distortion of the sample context is overcome effectively. Experiments demonstrate that our model is improved by 3.7% compared with the baseline model named Cluster GCN and 4.1% compared with U-Net.

Attention and Focus in Dance

2021 ◽  
Author(s):  
Clare Guss-West
Keyword(s):  
High Performance ◽  
Teaching Practice ◽  
Information Overload ◽  
Critical Role ◽  
Attentional Focus ◽  
Mental Work ◽  
Increased Risk ◽  
Professional Dancers ◽  
And Performance ◽  
Professional Dancer

The Western approach to dance is largely focused on control and mastery of technique, both of which are certainly necessary skills for improving performance. But mindful attention, despite its critical role in high performance, has gotten short shrift—until now. Attention and Focus in Dance, a how-to book rooted in the 20 years of attentional focus findings of researcher Gabriele Wulf, will help dancers unlock their power and stamina reserves, enabling efficient movement, heightening their sensory perception and releasing their dance potential. Author Clare Guss-West—a professional dancer, choreographer, teacher and holistic practitioner—presents a systematic, science-based approach to the mental work of dance. Her approach helps dancers hone the skills of attention, focus and self-cueing to replenish energy and enhance their physical and artistic performance. A Unique, Research-Based Approach Here is what Attention and Focus in Dance offers readers: • A unique approach, connecting the foundations of Eastern movement with Western movement forms • Research-based teaching practices in diverse contexts, including professional dance companies, private studios, and programmes for dancers with special needs or movement challenges • Testimonies and tips from international professional dancers and dance educators who use the book's approach in their training and teaching • A dance-centric focus that can be easily integrated into existing training and teaching practice, in rehearsal, or in rehabilitation contexts to provide immediate and long-term benefits Guss-West explores attentional focus techniques for dancers, teachers and dance health care practitioners, making practical connections between research, movement theory and day-to-day dance practice. “Many dancers are using excessive energy deployment and significant counterproductive effort, and that can lead to a global movement dysfunction, lack of stamina and an increased risk of injury,” says Guss-West. “Attentional focus training is the most relevant study that sport science and Eastern-movement practice can bring to dance.” Book Organisation The text is organised into two parts. Part I guides dancers in looking at the attentional challenges and information overload that many professional dancers suffer from. It outlines the need for a systematic attention and focus strategy, and it explains how scientific research on attentional focus relates to dance practice. This part also examines the ways in which Eastern-movement principles intersect with and complement scientific findings, and it examines how the Eastern and scientific concepts can breathe new life into basic dance elements such as posture, turnout and port de bras. Attention and focus techniques are included for replenishing energy and protecting against energy depletion and exhaustion. Part II presents attention and focus strategies for teaching, self-coaching and cueing. It addresses attentional focus cues for beginners and for more advanced dancers and professionals, and it places attentional focus in the broader context of holistic teaching strategies. Maximising Dance Potential “Whether cueing others or yourself, cueing for high performance is an art,” Guss-West says. “Readers will discover how to format cues and feedback to facilitate effective neuromuscular response and enhance dancer recall of information and accessibility while dancing.” Attention and Focus in Dance offers an abundance of research-backed concepts and inspirational ideas that can help dancers in their learning and performance. This book aids readers in filtering information and directing their focus for optimal physical effect. Ultimately, it guides dancers and teachers in being the best version of themselves and maximising their potential in dance.

scholarly journals Context-based Word Acquisition for Situated Dialogue in a Virtual World

2010 ◽  
Vol 37 ◽  
pp. 247-277 ◽  
Author(s):  
S. Qu ◽  
J. Y. Chai
Keyword(s):  
Virtual World ◽  
Language Production ◽  
Domain Knowledge ◽  
Contextual Information ◽  
Eye Gaze ◽  
Learning Approaches ◽  
New Words ◽  
Word Acquisition ◽  
Language Behavior ◽  
Situated Dialogue

To tackle the vocabulary problem in conversational systems, previous work has applied unsupervised learning approaches on co-occurring speech and eye gaze during interaction to automatically acquire new words. Although these approaches have shown promise, several issues related to human language behavior and human-machine conversation have not been addressed. First, psycholinguistic studies have shown certain temporal regularities between human eye movement and language production. While these regularities can potentially guide the acquisition process, they have not been incorporated in the previous unsupervised approaches. Second, conversational systems generally have an existing knowledge base about the domain and vocabulary. While the existing knowledge can potentially help bootstrap and constrain the acquired new words, it has not been incorporated in the previous models. Third, eye gaze could serve different functions in human-machine conversation. Some gaze streams may not be closely coupled with speech stream, and thus are potentially detrimental to word acquisition. Automated recognition of closely-coupled speech-gaze streams based on conversation context is important. To address these issues, we developed new approaches that incorporate user language behavior, domain knowledge, and conversation context in word acquisition. We evaluated these approaches in the context of situated dialogue in a virtual world. Our experimental results have shown that incorporating the above three types of contextual information significantly improves word acquisition performance.

Ensuring Students Engage with Ethical and Professional Practice Concepts

2009 ◽  
pp. 327-350
Author(s):  
J. Barrie Thompson
Keyword(s):  
Professional Practice ◽  
Teaching And Learning ◽  
Ethical Issues ◽  
Code Of Ethics ◽  
Contextual Information ◽  
Learning Approaches ◽  
International Model ◽  
Software Engineers ◽  
The Uk ◽  
The University

The teaching and learning of aspects related to ethics and professional practice present significant challenges to both staff and students as these topics are much more abstract than say software design and testing. The core of this chapter is an in-depth examination of how ethics and professional practice can be addressed in a very practical manner. To set the scene and provide contextual information the chapter commences with information on an international model of professionalism, a code of ethics for Software Engineers, and different teaching and learning approaches that can be employed when addressing ethical issues. The major part of the chapter is then devoted to detailing a particular teaching and leaning approach, which has been developed at the University of Sunderland in the UK. Finally conclusions, views on the present situation and future developments, and details of outstanding challenges are presented.

A Personalized Recommendation Model Based on Contextual Information

2015 ◽  
Vol 713-715 ◽  
pp. 1530-1533
Author(s):  
Yuan Zi He
Keyword(s):  
Recommender System ◽  
Information Overload ◽  
Contextual Information ◽  
User Model ◽  
Personalized Recommendation ◽  
Contextual Data ◽  
Model Based ◽  
Structure Text ◽  
Novel Model

Personalized recommendation offers a new way to solve the problem of information overload. In order to effectively build user model and improve the effect of personalized recommendation, this paper proposes a novel model for mining contextual information of non-structure text, and insects the contextual information into user model, which enriches user model. The experiment results shown that the model can greatly improve the recommendation performance when the model is applied to contextual data of the recommender system in hotel.

scholarly journals Integrating TA concepts into team meetings through micro-learning approaches

2020 ◽  
Vol 9 ◽  
pp. 161-185
Author(s):  
Amanda Lacy
Keyword(s):  
Information Overload ◽  
Learning Opportunities ◽  
Learning Needs ◽  
Learning Approaches ◽  
Transactional Analysis ◽  
Knowledge Application ◽  
Shared Attention ◽  
Team Meetings ◽  
Competing Priorities ◽  
Micro Learning

Micro-learning within team meetings offers immediacy of knowledge application and integration into practice. As a pedagogical method micro-learning has grown within workplace settings through being able to deliver small amounts of knowledge often, that is relevant, upskilling and applicable directly into practice. With more meetings happening in the workplace than ever before leveraging learning opportunities has never been more important. Learning opportunities have regularly been missed during team meetings due to competing priorities, information overload, lack of shared attention, divergent mental models and failure to identify learning needs. This article covers one aspect of a PhD research project focused on learning in team meetings. Discussion are two transactional analysis concepts delivered as micro-learning topics within team meetings and applied into practice. The approach, findings and further considerations are presented.

scholarly journals Multidimensional encoding of movement and contextual variables by rat globus pallidus neurons during a novel environment exposure task

2021 ◽  
Author(s):  
Noam D Peer ◽  
Hagar G Yamin ◽  
Dana Cohen
Keyword(s):  
Globus Pallidus ◽  
Contextual Information ◽  
Critical Role ◽  
Central Nucleus ◽  
Indirect Pathway ◽  
Cognitive Domains ◽  
Novel Environment ◽  
Animal Survival ◽  
Environment Exposure ◽  
Locomotion Speed

The basal ganglia (BG) play a critical role in a variety of functions that are essential for animal survival. Information from different cortical areas propagates through the BG in anatomically segregated circuits along the parallel direct and indirect pathways. We examined how the globus pallidus (GP), a central nucleus within the indirect pathway, encodes input from the motor and cognitive domains. We chronically recorded and analyzed neuronal activity in the GP of rats engaged in a novel environment exposure task. GP neurons displayed multidimensional responses to movement and contextual information. A model predicting single unit activity required many task-related variables, thus confirming the multidimensionality of GP neurons. In addition, populations of GP neurons, but not single units, reliably encoded the animals' locomotion speed and the environmental novelty. We posit that the GP independently processes information from different domains, effectively compresses it and collectively conveys it to successive nuclei.

scholarly journals A taxonomy of weight learning methods for statistical relational learning

2021 ◽  
Author(s):  
Sriram Srinivasan ◽  
Charles Dickens ◽  
Eriq Augustine ◽  
Golnoosh Farnadi ◽  
Lise Getoor
Keyword(s):  
Probabilistic Models ◽  
Performance Metrics ◽  
Relational Learning ◽  
Empirical Evaluation ◽  
Statistical Relational Learning ◽  
Weight Space ◽  
Learning Approaches ◽  
Extensive Evaluation ◽  
Real World Datasets ◽  
Weight Learning

AbstractStatistical relational learning (SRL) frameworks are effective at defining probabilistic models over complex relational data. They often use weighted first-order logical rules where the weights of the rules govern probabilistic interactions and are usually learned from data. Existing weight learning approaches typically attempt to learn a set of weights that maximizes some function of data likelihood; however, this does not always translate to optimal performance on a desired domain metric, such as accuracy or F1 score. In this paper, we introduce a taxonomy of search-based weight learning approaches for SRL frameworks that directly optimize weights on a chosen domain performance metric. To effectively apply these search-based approaches, we introduce a novel projection, referred to as scaled space (SS), that is an accurate representation of the true weight space. We show that SS removes redundancies in the weight space and captures the semantic distance between the possible weight configurations. In order to improve the efficiency of search, we also introduce an approximation of SS which simplifies the process of sampling weight configurations. We demonstrate these approaches on two state-of-the-art SRL frameworks: Markov logic networks and probabilistic soft logic. We perform empirical evaluation on five real-world datasets and evaluate them each on two different metrics. We also compare them against four other weight learning approaches. Our experimental results show that our proposed search-based approaches outperform likelihood-based approaches and yield up to a 10% improvement across a variety of performance metrics. Further, we perform an extensive evaluation to measure the robustness of our approach to different initializations and hyperparameters. The results indicate that our approach is both accurate and robust.

scholarly journals Relations between Cognitive Biases and Some Concepts of Information Behavior

2020 ◽  
Vol 4 (2) ◽  
pp. 109-118
Author(s):  
Sara Behimehr ◽  
Hamid R. Jamali
Keyword(s):  
Cognitive Biases ◽  
Information Overload ◽  
Ambiguity Aversion ◽  
Critical Role ◽  
Information Behavior ◽  
Postgraduate Students ◽  
Availability Bias ◽  
Library Anxiety ◽  
Classic Grounded Theory ◽  
The One

AbstractInformation behavior, as a part of human behavior, has many aspects, including a cognitive aspect. Cognitive biases, one of the important issues in psychology and cognitive science, can play a critical role in people’s behaviors and their information behavior. This article discusses the potential relationships between some concepts of human information behavior and cognitive biases. The qualitative research included semistructured face-to-face interviews with 25 postgraduate students who were at the writing-up stage of their research. The participants were selected using a purposeful sampling process. Interviews were analyzed using the coding technique of classic grounded theory. The research framework was the Eisenberg and Berkowitz information behavior model. The relationships that are discussed in this article include those between the principle of least effort on the one hand and availability bias and ambiguity aversion on the other; value-sensitive design and reactance; willingness to return and availability bias; library anxiety and ambiguity aversion, status quo bias, and stereotypical bias; information avoidance and selective perception, confirmation bias, stereotypical bias, and conservatism bias; information overload and information bias; and finally, filtering and attentional bias.

scholarly journals A METHODOLOGY FOR DATABASE AND DOCUMENT SELECTION

2011 ◽  
pp. 153-161
Author(s):  
Raj Gaurang Tiwari ◽  
Mohd. Husain ◽  
Anil Agrawal
Keyword(s):  
Information Retrieval ◽  
Search Engine ◽  
Web Applications ◽  
Information Overload ◽  
Critical Issue ◽  
Web Information Retrieval ◽  
Text Data ◽  
Web Based ◽  
Needed Information ◽  
Net Framework

As web users are facing the problems of information overload and drowning due to the significant and rapid growth in the amount of information and the number of users so there is need to provide Web users the more exactly needed information which is becoming a critical issue in web-based information retrieval and Web applications. In this work, we aspire to improve the performance of Web information retrieval and Web presentation through developing and employing Web data mining paradigms. Every search engine has a corresponding database that defines the set of documents that can be searched by the search engine. Generally, an index for all documents in the database is created and stored in the search engine. Text data in the Internet can be partitioned into several databases naturally. Proficient retrieval of preferred data can be attained if we can exactly predict the usefulness of each database, because with such information, we only need to retrieve potentially useful documents from useful databases. For a given query ‘q’ the usefulness of a text database is defined to be the no. of documents in the database that are sufficiently relevant to the query ‘q’. In this paper, we propose new approaches for database selection and documents selection. We also implement these algorithms using .net framework. Our experimental results indicate that these methods can yield substantial improvements over existing techniques.

Sign in / Sign up

Export Citation Format

Share Document