Please note that you have to be logged in to your ICLR account in order to join Gather.Town.

Recommender systems (RS) are ubiquitous in digital space. This paper develops a deep learning-based approach to address three practical challenges in RS: complex structures of high-dimensional data, noise in relational information, and the black-box nature of machine learning algorithms. Our method—Multi-GraphGraph Attention Network (MG-GAT)—learns latent user and business representations by aggregating a diverse set of information from neighbors of each user (business) on a neighbor importance graph. MG-GAT out-performs state-of-the-art deep learning models in the recommendation task using two large-scale datasets collected from Yelp and four other standard datasets in RS. The improved performance highlights MG-GAT’s advantage in incorporating multi-modal features in a principled manner. The features importance, neighbor importance graph, and latent representations reveal business insights on predictive features and explainable characteristics of business and users. Moreover, the learned neighbor importance graph can be used in a variety of management applications, such as targeting customers, promoting new businesses, and designing information acquisition strategies. Our paper presents a quintessential big data application of deep learning models in management while providing interpretability essential for real-world decision-making.

Drug discovery is lengthy process which costs 2.6B per approved drug on average. The cost is so high because finding a small molecule that binds to a particular target is a perilous highly uncertain process that can’t be completed in a decade in many of the cases. And even when a molecule is found it might not be doing its job very well and might very likely fail in later stages of trials. Our goal is to find much better drug candidate molecules and do it very fast.

This talk will discuss recent work in topological representation learning for functional neuroimaging.

In this talk, Prof. Arsuaga will discuss recent work on TDA for Cancer Genome Analysis.

Despite their massive popularity, deep networks are difficult to interpret or analyze. Their design and training is often driven by intuition and their tuning performed via exhaustive hyper-parameter search. More principled evaluations and explorations of deep networks to understand why and how certain neural networks outperform others is critical for faster prototyping, reduced training times and better interpretability. In this talk I present a novel visualization algorithm that reveals the internal geometry of such networks: Multislice PHATE (M-PHATE), the first method designed explicitly to visualize how a neural network's hidden representations of data evolve throughout the course of training. Our approach depends on the construction of a multi-slice graph that captures both the dynamics and the community structure of the hidden units. Our visualization provides a more detailed feedback to the deep learning practitioner beyond simple global measures (validation loss and accuracy), and without the need to access validation data. We demonstrate comparing different neural networks with M-PHATE in two vignettes: continual learning and generalization.