M. S. Ramaiah Institute of Technology

About: M. S. Ramaiah Institute of Technology is a based out in . It is known for research contribution in the topics: Feature extraction & Photoluminescence. The organization has 2853 authors who have published 2434 publications receiving 23507 citations.

Representation Learning on Graphs

Abstract: The primary challenge of applying machine learning in graph theory is finding a way to represent, or encode, graph structure so that it can be easily exploited by machine learning models. Traditionally, machine learning approaches relied on user-defined heuristics to extract features encoding structural information about a graph. However, recent years have seen a surge in approaches that automatically learn to encode graph structure into low-dimensional embeddings, using techniques based on deep learning and nonlinear dimensionality reduction. In this chapter, we will look at a review of key advancements in this area of representation learning on graphs, including matrix factorization-based methods, random-walk based algorithms, and graph convolutional networks. We will also look at methods to embed individual nodes as well as approaches to embed entire (sub)graphs.

Deference in Indians' decision making: introjected goals or injunctive norms?

Abstract: We examine the claim that Indians are more likely than Americans to act deferentially in the presence of authority figures and explore 2 possible psychological mechanisms for this cultural difference: introjected goals and injunctive norms Studies 1 and 2 showed that after reflecting upon an authority's expectations, Indians were more likely than Americans to make clothing and course choices consistent with the authority's expectations, but there was no such cultural difference for peers' expectations Study 3 showed that merely activating the concept of authority figures, without highlighting specific expectations, was sufficient to influence Indians' choices but not their evaluations Examining a more basic distinction underlying introjected goals versus injunctive norms, Study 4 showed that authority primes influenced Indians' sense of what they should do but not what they want to do Study 5 showed that, inconsistent with the internalized goal mechanism, the effect of explicit authority primes did not increase after brief delays However, Indian participants who were less likely to accommodate to the salient authority experienced more guilt across delay conditions, which supported the injunctive norms mechanism The findings suggest that manipulating injunctive norms can be an effective means for inducing or eliminating deferential behaviors in Indian settings