Search Results for author: Bert Huang

Found 25 papers, 5 papers with code

Weakly Supervised Label Learning Flows

1 code implementation19 Feb 2023 You Lu, Chidubem Arachie, Bert Huang

In this paper, we develop label learning flows (LLF), a general framework for weakly supervised learning problems.

Weakly-supervised Learning

Data Consistency for Weakly Supervised Learning

no code implementations8 Feb 2022 Chidubem Arachie, Bert Huang

Instead, we use weak signals and the data features to solve a constrained optimization that enforces data consistency among the labels we generate.

Image Classification Weakly-supervised Learning

Constrained Labeling for Weakly Supervised Learning

1 code implementation15 Sep 2020 Chidubem Arachie, Bert Huang

Curation of large fully supervised datasets has become one of the major roadblocks for machine learning.

Image Classification Weakly-supervised Learning

Woodbury Transformations for Deep Generative Flows

1 code implementation NeurIPS 2020 You Lu, Bert Huang

In this paper, we introduce Woodbury transformations, which achieve efficient invertibility via the Woodbury matrix identity and efficient determinant calculation via Sylvester's determinant identity.

Normalising Flows

Bounded Expectation of Label Assignment: Dataset Annotation by Supervised Splitting with Bias-Reduction Techniques

no code implementations17 Jun 2019 Alyssa Herbst, Bert Huang

We introduce a scheme for inferring labels of unlabeled data at a fraction of the cost of labeling the entire dataset.

Active Learning Clustering

Labeled Graph Generative Adversarial Networks

no code implementations7 Jun 2019 Shuangfei Fan, Bert Huang

To further evaluate the quality of the generated graphs, we use them on a downstream task of graph classification, and the results show that LGGAN can faithfully capture the important aspects of the graph structure.

Graph Classification Image Generation

Stochastic Generalized Adversarial Label Learning

no code implementations3 Jun 2019 Chidubem Arachie, Bert Huang

In this paper, we propose stochastic generalized adversarial label learning (Stoch-GALL), a framework for training machine learning models that perform well when noisy and possibly correlated labels are provided.

BIG-bench Machine Learning General Classification +1

Structured Output Learning with Conditional Generative Flows

2 code implementations30 May 2019 You Lu, Bert Huang

Traditional structured prediction models try to learn the conditional likelihood, i. e., p(y|x), to capture the relationship between the structured output y and the input features x.

Structured Prediction Variational Inference

Deep Generative Models for Generating Labeled Graphs

no code implementations ICLR Workshop DeepGenStruct 2019 Shuangfei Fan, Bert Huang

As a new way to train generative models, generative adversarial networks (GANs) have achieved considerable success in image generation, and this framework has also recently been applied to data with graph structures.

Image Generation

Block Belief Propagation for Parameter Learning in Markov Random Fields

no code implementations9 Nov 2018 You Lu, Zhiyuan Liu, Bert Huang

Traditional learning methods for training Markov random fields require doing inference over all variables to compute the likelihood gradient.

Adversarial Label Learning

no code implementations22 May 2018 Chidubem Arachie, Bert Huang

We propose a weakly supervised method---adversarial label learning---that trains classifiers to perform well against an adversary that chooses labels for training data.

Weakly-supervised Learning

New Fairness Metrics for Recommendation that Embrace Differences

no code implementations29 Jun 2017 Sirui Yao, Bert Huang

We study fairness in collaborative-filtering recommender systems, which are sensitive to discrimination that exists in historical data.

Collaborative Filtering Fairness +1

Best-Choice Edge Grafting for Efficient Structure Learning of Markov Random Fields

no code implementations25 May 2017 Walid Chaabene, Bert Huang

In this paper, we address key computational bottlenecks that current incremental techniques still suffer by introducing best-choice edge grafting, an incremental, structured method that activates edges as groups of features in a streaming setting.

Beyond Parity: Fairness Objectives for Collaborative Filtering

1 code implementation NeurIPS 2017 Sirui Yao, Bert Huang

We study fairness in collaborative-filtering recommender systems, which are sensitive to discrimination that exists in historical data.

Collaborative Filtering Fairness +1

Recurrent Collective Classification

no code implementations19 Mar 2017 Shuangfei Fan, Bert Huang

We propose a new method for training iterative collective classifiers for labeling nodes in network data.

Classification General Classification

Cyberbullying Identification Using Participant-Vocabulary Consistency

no code implementations26 Jun 2016 Elaheh Raisi, Bert Huang

In this study, we propose a model that simultaneously discovers instigators and victims of bullying as well as new bullying vocabulary by starting with a corpus of social interactions and a seed dictionary of bullying indicators.

Hinge-Loss Markov Random Fields and Probabilistic Soft Logic

no code implementations17 May 2015 Stephen H. Bach, Matthias Broecheler, Bert Huang, Lise Getoor

In this paper, we introduce two new formalisms for modeling structured data, and show that they can both capture rich structure and scale to big data.

Knowledge Graphs Probabilistic Programming

Hinge-loss Markov Random Fields: Convex Inference for Structured Prediction

no code implementations26 Sep 2013 Stephen Bach, Bert Huang, Ben London, Lise Getoor

Graphical models for structured domains are powerful tools, but the computational complexities of combinatorial prediction spaces can force restrictions on models, or require approximate inference in order to be tractable.

Structured Prediction

A Hypergraph-Partitioned Vertex Programming Approach for Large-scale Consensus Optimization

no code implementations30 Aug 2013 Hui Miao, Xiangyang Liu, Bert Huang, Lise Getoor

In modern data science problems, techniques for extracting value from big data require performing large-scale optimization over heterogenous, irregularly structured data.

hypergraph partitioning

Multi-relational Learning Using Weighted Tensor Decomposition with Modular Loss

no code implementations7 Mar 2013 Ben London, Theodoros Rekatsinas, Bert Huang, Lise Getoor

For the typical cases of real-valued functions and binary relations, we propose several loss functions and derive the associated parameter gradients.

Relational Reasoning Tensor Decomposition

Graph-based Generalization Bounds for Learning Binary Relations

no code implementations21 Feb 2013 Ben London, Bert Huang, Lise Getoor

We investigate the generalizability of learned binary relations: functions that map pairs of instances to a logical indicator.

Entity Resolution Generalization Bounds +1

Learning a Distance Metric from a Network

no code implementations NeurIPS 2011 Blake Shaw, Bert Huang, Tony Jebara

To better model and understand these networks, we present structure preserving metric learning (SPML), an algorithm for learning a Mahalanobis distance metric from a network such that the learned distances are tied to the inherent connectivity structure of the network.

Graph Embedding Metric Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.