• Publications
  • Influence
Multitask learning and benchmarking with clinical time series data
TLDR
This work proposes four clinical prediction benchmarks using data derived from the publicly available Medical Information Mart for Intensive Care (MIMIC-III) database, covering a range of clinical problems including modeling risk of mortality, forecasting length of stay, detecting physiologic decline, and phenotype classification.
A Survey on Bias and Fairness in Machine Learning
TLDR
This survey investigated different real-world applications that have shown biases in various ways, and created a taxonomy for fairness definitions that machine learning researchers have defined to avoid the existing bias in AI systems.
MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
TLDR
This work proposes a new model, MixHop, that can learn a general class of neighborhood mixing relationships by repeatedly mixing feature representations of neighbors at various distances, and proposes sparsity regularization that allows to visualize how the network prioritizes neighborhood information across different graph datasets.
Scalable Temporal Latent Space Inference for Link Prediction in Dynamic Social Networks
We propose a temporal latent space model for link prediction in dynamic social networks, where the goal is to predict links over time based on a sequence of previous graph snapshots. The model
Mathematical Model of Foraging in a Group of Robots: Effect of Interference
TLDR
A mathematical model of foraging in a homogeneous multi-robot system, with the goal of understanding quantitatively the effects of interference, is presented and an optimal group size is found that maximizes group performance.
Analysis of Dynamic Task Allocation in Multi-Robot Systems
TLDR
A mathematical model of a general dynamic task allocation mechanism that allows robots to choose between two types of tasks and the effect that the number of observations and the choice of the decision function have on the performance of the system is presented.
Invariant Representations without Adversarial Training
TLDR
It is shown that adversarial training is unnecessary and sometimes counter-productive; this work casts invariant representation learning as a single information-theoretic objective that can be directly optimized.
The DARPA Twitter Bot Challenge
TLDR
There is a need to identify and eliminate "influence bots" - realistic, automated identities that illicitly shape discussions on sites like Twitter and Facebook - before they get too influential.
Better Automatic Evaluation of Open-Domain Dialogue Systems with Contextualized Embeddings
TLDR
Using contextualized word embeddings to compute more accurate relatedness scores and thus better evaluation metrics is explored, and experiments show that the evaluation metrics outperform RUBER, which is trained on staticembeddings.
Information transfer in social media
TLDR
A measure of causal relationships between nodes based on the information--theoretic notion of transfer entropy, or information transfer, which allows us to differentiate between weak influence over large groups and strong influence over small groups.
...
...