
MUSCLE: Strengthening SemiSupervised Learning Via Concurrent Unsupervised Learning Using Mutual Information Maximization
Deep neural networks are powerful, massively parameterized machine learn...
read it

Compressing Deep Neural Networks via Layer Fusion
This paper proposes layer fusion  a model compression technique that di...
read it

Robust Classification under ClassDependent Domain Shift
Investigation of machine learning algorithms robust to changes between t...
read it

All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference
The recently proposed Thermodynamic Variational Objective (TVO) leverage...
read it

Sequential Unsupervised Domain Adaptation through Prototypical Distributions
We develop an algorithm for unsupervised domain adaptation (UDA) of a cl...
read it

Event Cartography: Latent Point Process Embeddings
Many important phenomena arise naturally as temporal point processes wit...
read it

Anchor Attention for Hybrid Crowd Forecasts Aggregation
Forecasting the future is a notoriously difficult task. To overcome this...
read it

Improving Generalization by Controlling LabelNoise Information in Neural Network Weights
In the presence of noisy or incorrect labels, neural networks have the u...
read it

Towards Learning Representations of Binary Executable Files for Security Tasks
Tackling binary analysis problems has traditionally implied manually def...
read it

Predictive Engagement: An Efficient Metric For Automatic Evaluation of OpenDomain Dialogue Systems
User engagement is a critical metric for evaluating the quality of open...
read it

Man is to Person as Woman is to Location: Measuring Gender Bias in Named Entity Recognition
We study the bias in several stateoftheart named entity recognition (...
read it

Deep Structured Neural Network for Event Temporal Relation Extraction
We propose a novel deep structured learning framework for event temporal...
read it

Stacking Models for Nearly Optimal Link Prediction in Complex Networks
Most realworld networks are incompletely observed. Algorithms that can ...
read it

NearlyUnsupervised Hashcode Representations for Relation Extraction
Recently, kernelized locality sensitive hashcodes have been successfully...
read it

A Survey on Bias and Fairness in Machine Learning
With the widespread use of AI systems and applications in our everyday l...
read it

Efficient Covariance Estimation from Temporal Data
Estimating the covariance structure of multivariate time series is a fun...
read it

MixHop: HigherOrder Graph Convolution Architectures via Sparsified Neighborhood Mixing
Existing popular methods for semisupervised learning with Graph Neural ...
read it

Better Automatic Evaluation of OpenDomain Dialogue Systems with Contextualized Embeddings
Despite advances in opendomain dialogue systems, automatic evaluation o...
read it

Exact RateDistortion in Autoencoders via Echo Noise
Compression is at the heart of effective representation learning. Howeve...
read it

Identifying and Analyzing Cryptocurrency Manipulations in Social Media
Interest surrounding cryptocurrencies, digital or virtual currencies tha...
read it

Maximizing Multivariate Information with ErrorCorrecting Codes
Multivariate mutual information provides a conceptual framework for char...
read it

Evading the Adversary in Invariant Representation
Representations of data that are invariant to changes in specified nuisa...
read it

A Forest Mixture Bound for BlockFree Parallel Inference
Coordinate ascent variational inference is an important algorithm for in...
read it

Dialogue Modeling Via Hash Functions: Applications to Psychotherapy
We propose a novel machinelearning framework for dialogue modeling whic...
read it

Adaptive prior probabilities via optimization of risk and entropy
An agent choosing between various actions tends to take the one with the...
read it

AutoEncoding Total Correlation Explanation
Advances in unsupervised learning enable reconstruction and generation o...
read it

Stochastic Learning of Nonstationary Kernels for Natural Language Modeling
Natural language processing often involves computations with semantic or...
read it

Efficient Representation for Natural Language Processing via Kernelized Hashcodes
Kernel similarity functions have been successfully applied in classifica...
read it

Unifying Local and Global Change Detection in Dynamic Networks
Many realworld networks are complex dynamical systems, where both local...
read it

Low Complexity Gaussian Latent Factor Models and a Blessing of Dimensionality
Learning the structure of graphical models from data is a fundamental pr...
read it

Multitask Learning and Benchmarking with Clinical Time Series Data
Health care is one of the most exciting frontiers in data mining and mac...
read it

Toward Interpretable Topic Discovery via Anchored Correlation Explanation
Many predictive tasks, such as diagnosing a patient based on their medic...
read it

Variational Information Maximization for Feature Selection
Feature selection is one of the most fundamental problems in machine lea...
read it

Sifting Common Information from Many Variables
Measuring the relationship between any pair of variables is a rich and a...
read it

The DARPA Twitter Bot Challenge
A number of organizations ranging from terrorist groups such as ISIS to ...
read it

Extracting Biomolecular Interactions Using Semantic Parsing of Biomedical Text
We advance the state of the art in biomolecular interaction extraction w...
read it

The Information Sieve
We introduce a new framework for unsupervised learning of representation...
read it

Understanding confounding effects in linguistic coordination: an informationtheoretic approach
We suggest an informationtheoretic approach for measuring stylistic coo...
read it

Scalable Link Prediction in Dynamic Networks via NonNegative Matrix Factorization
We propose a scalable temporal latent space model for link prediction in...
read it

Efficient Estimation of Mutual Information for Strongly Dependent Variables
We demonstrate that a popular class of nonparametric mutual information ...
read it

Active Inference for Binary Symmetric Hidden Markov Models
We consider active maximum a posteriori (MAP) inference problem for Hidd...
read it

Maximally Informative Hierarchical Representations of HighDimensional Data
We consider a set of probabilistic functions of some input variables as ...
read it

Discovering Structure in HighDimensional Data Through Correlation Explanation
We introduce a method to learn a hierarchy of successively more abstract...
read it

Comparative Analysis of Viterbi Training and Maximum Likelihood Estimation for HMMs
We present an asymptotic analysis of Viterbi Training (VT) and contrast ...
read it

Phase Transitions in Community Detection: A Solvable Toy Model
Recently, it was shown that there is a phase transition in the community...
read it

Latent SelfExciting Point Process Model for SpatialTemporal Networks
We propose a latent selfexciting point process model that describes geo...
read it

Coevolution of Selection and Influence in Social Networks
Many networks are complex dynamical systems, where both attributes of no...
read it

A Sequence of Relaxations Constraining Hidden Variable Models
Many widely studied graphical models with latent variables lead to nontr...
read it

On Maximum a Posteriori Estimation of Hidden Markov Processes
We present a theoretical analysis of Maximum a Posteriori (MAP) sequence...
read it

Continuous Strategy Replicator Dynamics for MultiAgent Learning
The problem of multiagent learning and adaptation has attracted a great...
read it
Aram Galstyan
is this you? claim profile
Director of the Machine Intelligence and Data Science (MINDS) group at Information Sciences Institute, University of Southern California, Research Associate Professor at the USC Computer Science department, Project Leader of CoPI for IARPA’s Mercury program and Information Sciences Institute USC, Leader of PI DARPA SMISC project,