Author name cluster

Bert Huang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

16 papers

2 author rows

JMLR Journal 2021 Journal Article

A General Framework for Adversarial Label Learning

Chidubem Arachie
Bert Huang

We consider the task of training classifiers without fully labeled data. We propose a weakly supervised method---adversarial label learning---that trains classifiers to perform well when noisy and possibly correlated labels are provided. Our framework allows users to provide different weak labels and multiple constraints on these labels. Our model then attempts to learn parameters for the data by solving a zero-sum game for the binary problems and a non-zero sum game optimization for multi-class problems. The game is between an adversary that chooses labels for the data and a model that minimizes the error made by the adversarial labels. The weak supervision constrains what labels the adversary can choose. The method therefore minimizes an upper bound of the classifier's error rate using projected primal-dual subgradient descent. Minimizing this bound protects against bias and dependencies in the weak supervision. We first show the performance of our framework on binary classification tasks then we extend our algorithm to show its performance on multiclass datasets. Our experiments show that our method can train without labels and outperforms other approaches for weakly supervised learning. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2021. ( edit, beta )

PDF Details

UAI Conference 2021 Conference Paper

Constrained labeling for weakly supervised learning

Chidubem Arachie
Bert Huang

Curation of large fully supervised datasets has become one of the major roadblocks for machine learning. Weak supervision provides an alternative to supervised learning by training with cheap, noisy, and possibly correlated labeling functions from varying sources. The key challenge in weakly supervised learning is combining the different weak supervision signals while navigating misleading correlations in their errors. In this paper, we propose a simple data-free approach for combining weak supervision signals by defining a constrained space for the possible labels of the weak signals and training with a random labeling within this constrained space. Our method is efficient and stable, converging after a few iterations of gradient descent. We prove theoretical conditions under which the worst-case error of the randomized label decreases with the rank of the linear constraints. We show experimentally that our method outperforms other weak supervision methods on various text- and image-classification tasks.

Details

AAAI Conference 2020 Conference Paper

Structured Output Learning with Conditional Generative Flows

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. For many models, computing the likelihood is intractable. These models are therefore hard to train, requiring the use of surrogate objectives or variational inference to approximate likelihood. In this paper, we propose conditional Glow (c-Glow), a conditional generative ﬂow for structured output learning. C- Glow beneﬁts from the ability of ﬂow-based models to compute p(y|x) exactly and efﬁciently. Learning with c-Glow does not require a surrogate objective or performing inference during training. Once trained, we can directly and efﬁciently generate conditional samples. We develop a samplebased prediction method, which can use this advantage to do efﬁcient and effective inference. In our experiments, we test c-Glow on ﬁve different tasks. C-Glow outperforms the stateof-the-art baselines in some tasks and predicts comparable outputs in the other tasks. The results show that c-Glow is versatile and is applicable to many different structured prediction problems.

PDF Details

NeurIPS Conference 2020 Conference Paper

Woodbury Transformations for Deep Generative Flows

You Lu
Bert Huang

Normalizing flows are deep generative models that allow efficient likelihood calculation and sampling. The core requirement for this advantage is that they are constructed using functions that can be efficiently inverted and for which the determinant of the function's Jacobian can be efficiently computed. Researchers have introduced various such flow operations, but few of these allow rich interactions among variables without incurring significant computational costs. 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. In contrast with other operations used in state-of-the-art normalizing flows, Woodbury transformations enable (1) high-dimensional interactions, (2) efficient sampling, and (3) efficient likelihood evaluation. Other similar operations, such as 1x1 convolutions, emerging convolutions, or periodic convolutions allow at most two of these three advantages. In our experiments on multiple image datasets, we find that Woodbury transformations allow learning of higher-likelihood models than other flow architectures while still enjoying their efficiency advantages.

PDF Details

AAAI Conference 2019 Conference Paper

Adversarial Label Learning

Chidubem Arachie
Bert Huang

We consider the task of training classifiers without labels. We propose a weakly supervised method—adversarial label learning—that trains classifiers to perform well against an adversary that chooses labels for training data. The weak supervision constrains what labels the adversary can choose. The method therefore minimizes an upper bound of the classifier’s error rate using projected primal-dual subgradient descent. Minimizing this bound protects against bias and dependencies in the weak supervision. Experiments on real datasets show that our method can train without labels and outperforms other approaches for weakly supervised learning.

PDF Details

AAAI Conference 2019 Conference Paper

Block Belief Propagation for Parameter Learning in Markov Random Fields

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. The iteration complexity for those methods therefore scales with the size of the graphical models. In this paper, we propose block belief propagation learning (BBPL), which uses block-coordinate updates of approximate marginals to compute approximate gradients, removing the need to compute inference on the entire graphical model. Thus, the iteration complexity of BBPL does not scale with the size of the graphs. We prove that the method converges to the same solution as that obtained by using full inference per iteration, despite these approximations, and we empirically demonstrate its scalability improvements over standard training methods.

PDF Details

UAI Conference 2018 Conference Paper

Sparse-Matrix Belief Propagation

Reid Bixler
Bert Huang

We propose sparse-matrix belief propagation, which executes loopy belief propagation in pairwise Markov random fields by replacing indexing over graph neighborhoods with sparsematrix operations. This abstraction allows for seamless integration with optimized sparse linear algebra libraries, including those that perform matrix and tensor operations on modern hardware such as graphical processing units (GPUs). The sparse-matrix abstraction allows the implementation of belief propagation in a high-level language (e. g. , Python) that is also able to leverage the power of GPU parallelization. We demonstrate sparse-matrix belief propagation by implementing it in a modern deep learning framework (PyTorch), measuring the resulting massive improvement in running time, and facilitating future integration into deep learning models.

Details

NeurIPS Conference 2017 Conference Paper

Beyond Parity: Fairness Objectives for Collaborative Filtering

Sirui Yao
Bert Huang

We study fairness in collaborative-filtering recommender systems, which are sensitive to discrimination that exists in historical data. Biased data can lead collaborative-filtering methods to make unfair predictions for users from minority groups. We identify the insufficiency of existing fairness metrics and propose four new metrics that address different forms of unfairness. These fairness metrics can be optimized by adding fairness terms to the learning objective. Experiments on synthetic and real data show that our new metrics can better measure fairness than the baseline, and that the fairness objectives effectively help reduce unfairness.

PDF Details

JMLR Journal 2017 Journal Article

Hinge-Loss Markov Random Fields and Probabilistic Soft Logic

Stephen H. Bach
Matthias Broecheler
Bert Huang
Lise Getoor

A fundamental challenge in developing high-impact machine learning technologies is balancing the need to model rich, structured domains with the ability to scale to big data. Many important problem areas are both richly structured and large scale, from social and biological networks, to knowledge graphs and the Web, to images, video, and natural language. 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. The first, hinge-loss Markov random fields (HL-MRFs), is a new kind of probabilistic graphical model that generalizes different approaches to convex inference. We unite three approaches from the randomized algorithms, probabilistic graphical models, and fuzzy logic communities, showing that all three lead to the same inference objective. We then define HL- MRFs by generalizing this unified objective. The second new formalism, probabilistic soft logic (PSL), is a probabilistic programming language that makes HL-MRFs easy to define using a syntax based on first-order logic. We introduce an algorithm for inferring most-probable variable assignments (MAP inference) that is much more scalable than general-purpose convex optimization methods, because it uses message passing to take advantage of sparse dependency structures. We then show how to learn the parameters of HL-MRFs. The learned HL-MRFs are as accurate as analogous discrete models, but much more scalable. Together, these algorithms enable HL-MRFs and PSL to model rich, structured data at scales not previously possible. [abs] [ pdf ][ bib ] &copy JMLR 2017. ( edit, beta )

PDF Details

JMLR Journal 2016 Journal Article

Stability and Generalization in Structured Prediction

Ben London
Bert Huang
Lise Getoor

Structured prediction models have been found to learn effectively from a few large examples--- sometimes even just one. Despite empirical evidence, canonical learning theory cannot guarantee generalization in this setting because the error bounds decrease as a function of the number of examples. We therefore propose new PAC-Bayesian generalization bounds for structured prediction that decrease as a function of both the number of examples and the size of each example. Our analysis hinges on the stability of joint inference and the smoothness of the data distribution. We apply our bounds to several common learning scenarios, including max-margin and soft-max training of Markov random fields. Under certain conditions, the resulting error bounds can be far more optimistic than previous results and can even guarantee generalization from a single large example. [abs] [ pdf ][ bib ] &copy JMLR 2016. ( edit, beta )

PDF Details

ICML Conference 2015 Conference Paper

Paired-Dual Learning for Fast Training of Latent Variable Hinge-Loss MRFs

Stephen H. Bach
Bert Huang
Jordan L. Boyd-Graber
Lise Getoor

Latent variables allow probabilistic graphical models to capture nuance and structure in important domains such as network science, natural language processing, and computer vision. Naive approaches to learning such complex models can be prohibitively expensive—because they require repeated inferences to update beliefs about latent variables—so lifting this restriction for useful classes of models is an important problem. Hinge-loss Markov random fields (HL-MRFs) are graphical models that allow highly scalable inference and learning in structured domains, in part by representing structured problems with continuous variables. However, this representation leads to challenges when learning with latent variables. We introduce paired-dual learning, a framework that greatly speeds up training by using tractable entropy surrogates and avoiding repeated inferences. Paired-dual learning optimizes an objective with a pair of dual inference problems. This allows fast, joint optimization of parameters and dual variables. We evaluate on social-group detection, trust prediction in social networks, and image reconstruction, finding that paired-dual learning trains models as accurate as those trained by traditional methods in much less time, often before traditional methods make even a single parameter update.

Details

ICML Conference 2015 Conference Paper

The Benefits of Learning with Strongly Convex Approximate Inference

Ben London 0001
Bert Huang
Lise Getoor

We explore the benefits of strongly convex free energies in variational inference, providing both theoretical motivation and a new meta-algorithm. Using the duality between strong convexity and stability, we prove a high-probability bound on the error of learned marginals that is inversely proportional to the modulus of convexity of the free energy, thereby motivating free energies whose moduli are constant with respect to the size of the graph. We identify sufficient conditions for Ω(1)-strong convexity in two popular variational techniques: tree-reweighted and counting number entropies. Our insights for the latter suggest a novel counting number optimization framework, which guarantees strong convexity for any given modulus. Our experiments demonstrate that learning with a strongly convex free energy, using our optimization framework to guarantee a given modulus, results in substantially more accurate marginal probabilities, thereby validating our theoretical claims and the effectiveness of our framework.

Details

AAAI Conference 2014 Conference Paper

Learning Latent Engagement Patterns of Students in Online Courses

Arti Ramesh
Dan Goldwasser
Bert Huang
Hal Daume III
Lise Getoor

Maintaining and cultivating student engagement is critical for learning. Understanding factors affecting student engagement will help in designing better courses and improving student retention. The large number of participants in massive open online courses (MOOCs) and data collected from their interaction with the MOOC open up avenues for studying student engagement at scale. In this work, we develop a framework for modeling and understanding student engagement in online courses based on student behavioral cues. Our first contribution is the abstraction of student engagement types using latent representations. We use that abstraction in a probabilistic model to connect student behavior with course completion. We demonstrate that the latent formulation for engagement helps in predicting student survival across three MOOCs. Next, in order to initiate better instructor interventions, we need to be able to predict student survival early in the course. We demonstrate that we can predict student survival early in the course reliably using the latent model. Finally, we perform a closer quantitative analysis of user interaction with the MOOC and identify student activities that are good indicators for survival at different points in the course.

PDF Details

ICML Conference 2013 Conference Paper

Collective Stability in Structured Prediction: Generalization from One Example

Ben London 0001
Bert Huang
Ben Taskar
Lise Getoor

Structured predictors enable joint inference over multiple interdependent output variables. These models are often trained on a small number of examples with large internal structure. Existing distribution-free generalization bounds do not guarantee generalization in this setting, though this contradicts a large body of empirical evidence from computer vision, natural language processing, social networks and other fields. In this paper, we identify a set of natural conditions – weak dependence, hypothesis complexity and a new measure, collective stability – that are sufficient for generalization from even a single example, without imposing an explicit generative model of the data. We then demonstrate that the complexity and stability conditions are satisfied by a broad class of models, including marginal inference in templated graphical models. We thus obtain uniform convergence rates that can decrease significantly faster than previous bounds, particularly when each structured example is sufficiently large and the number of training examples is constant, even one.

Details

UAI Conference 2013 Conference Paper

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

Stephen H. Bach
Bert Huang
Ben London 0001
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. Instead of working in a combinatorial space, we use hinge-loss Markov random fields (HL-MRFs), an expressive class of graphical models with log-concave density functions over continuous variables, which can represent confidences in discrete predictions. This paper demonstrates that HL- MRFs are general tools for fast and accurate structured prediction. We introduce the first inference algorithm that is both scalable and applicable to the full class of HL-MRFs, and show how to train HL-MRFs with several learning algorithms. Our experiments show that HL-MRFs match or surpass the predictive performance of state-of-the-art methods, including discrete models, in four application domains.

Details

NeurIPS Conference 2011 Conference Paper

Learning a Distance Metric from a Network

Blake Shaw
Bert Huang
Tony Jebara

Many real-world networks are described by both connectivity information and features for every node. 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. Like the graph embedding algorithm structure preserving embedding, SPML learns a metric which is structure preserving, meaning a connectivity algorithm such as k-nearest neighbors will yield the correct connectivity when applied using the distances from the learned metric. We show a variety of synthetic and real-world experiments where SPML predicts link patterns from node features more accurately than standard techniques. We further demonstrate a method for optimizing SPML based on stochastic gradient descent which removes the running-time dependency on the size of the network and allows the method to easily scale to networks of thousands of nodes and millions of edges.

PDF Details