2023

Recently there has been a surge of interest in designing graph embedding methods. Few, if any, can scale to a large-sized graph with millions of nodes due to both computational complexity and memory requirements. In this talk, I will present an approach to redress this limitation by introducing the MultI-Level Embedding (MILE) framework – a generic methodology allowing con-temporary graph embedding methods to scale to large graphs. MILE repeatedly coarsens the graph into smaller ones using a hybrid matching technique to maintain the backbone structure of the graph. It then applies existing embedding methods on the coarsest graph and refines the embeddings to the original graph through a graph convolution neural network that it learns. Time permitting, I will then describe one of several natural extensions to MILE – in a distributed setting (DistMILE) to further improve the scalability of graph embedding or mechanisms – to learn fair graph representations (FairMILE).
The proposed MILE framework and variants (DistMILE, FairMILE), are agnostic to the underlying graph embedding techniques and can be applied to many existing graph embedding methods without modifying them and is agnostic to their implementation language. Experimental results on five large-scale datasets demonstrate that MILE significantly boosts the speed (order of magnitude) of graph embedding while generating embeddings of better quality, for the task of node classification. MILE can comfortably scale to a graph with 9 million nodes and 40 million edges, on which existing methods run out of memory or take too long to compute on a modern workstation. Our experiments demonstrate that DistMILE learns representations of similar quality with respect to other baselines while reducing the time of learning embeddings even further (up to 40 x speedup over MILE). FairMILE similarly learns fair representations of the data while reducing the time of learning embeddings.
Joint work with Jionqian Liang (Google Brain), S. Gurukar (OSU) and Yuntian He (OSU)

In the first part we cover five current specific problems that motivate the needs of responsible AI: (1) discrimination (e.g., facial recognition, justice, sharing economy, language models); (2) phrenology (e.g., biometric based predictions); (3) unfair digital commerce (e.g., exposure and popularity bias); (4) stupid models (e.g., minimal adversarial AI) and (5) indiscriminate use of computing resources (e.g., large language models). These examples do have a personal bias but set the context for the second part where we address four challenges: (1) too many principles (e.g., principles vs. techniques), (2) cultural differences; (3) regulation and (4) our cognitive biases. We finish discussing what we can do to address these challenges in the near future to be able to develop responsible AI.

In this talk I’ll present an overview of the challenges and opportunities for applying data mining and machine learning for tasks in personalized health, including the role of semantics. In particular, I’ll focus on the task of healthy recipe recommendation via the use of knowledge graphs, as well as generating summaries from personal health data, highlighting our work within the RPI-IBM Health Empowerment by Analytics, Learning, and Semantics (HEALS) project.