Author name cluster

Changho Suh

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.

13 papers

2 author rows

AAAI Conference 2023 Conference Paper

A Fair Generative Model Using LeCam Divergence

Soobin Um
Changho Suh

We explore a fairness-related challenge that arises in generative models. The challenge is that biased training data with imbalanced demographics may yield a high asymmetry in size of generated samples across distinct groups. We focus on practically-relevant scenarios wherein demographic labels are not available and therefore the design of a fair generative model is non-straightforward. In this paper, we propose an optimization framework that regulates the unfairness under such practical settings via one statistical measure, LeCam (LC)-divergence. Specifically to quantify the degree of unfairness, we employ a balanced-yet-small reference dataset and then measure its distance with generated samples using the LC-divergence, which is shown to be particularly instrumental to a small size of the reference dataset. We take a variational optimization approach to implement the LC-based measure. Experiments on benchmark real datasets demonstrate that the proposed framework can significantly improve the fairness performance while maintaining realistic sample quality for a wide range of the reference set size all the way down to 1% relative to training set.

PDF Details DOI

ICML Conference 2023 Conference Paper

Improving Fair Training under Correlation Shifts

Yuji Roh
Kangwook Lee 0001
Steven Euijong Whang
Changho Suh

Model fairness is an essential element for Trustworthy AI. While many techniques for model fairness have been proposed, most of them assume that the training and deployment data distributions are identical, which is often not true in practice. In particular, when the bias between labels and sensitive groups changes, the fairness of the trained model is directly influenced and can worsen. We make two contributions for solving this problem. First, we analytically show that existing in-processing fair algorithms have fundamental limits in accuracy and group fairness. We utilize the notion of correlation shifts between labels and groups, which can explicitly capture the change of the above bias. Second, we propose a novel pre-processing step that samples the input data to reduce correlation shifts and thus enables the in-processing approaches to overcome their limitations. We formulate an optimization problem for adjusting the data ratio among labels and sensitive groups to reflect the shifted correlation. A key benefit of our approach lies in decoupling the roles of pre- and in-processing approaches: correlation adjustment via pre-processing and unfairness mitigation on the processed data via in-processing. Experiments show that our framework effectively improves existing in-processing fair algorithms w. r. t. accuracy and fairness, both on synthetic and real datasets.

Details

ICLR Conference 2021 Conference Paper

FairBatch: Batch Selection for Model Fairness

Yuji Roh
Kangwook Lee 0001
Steven Euijong Whang
Changho Suh

Training a fair machine learning model is essential to prevent demographic disparity. Existing techniques for improving model fairness require broad changes in either data preprocessing or model training, rendering themselves difficult-to-adopt for potentially already complex machine learning systems. We address this problem via the lens of bilevel optimization. While keeping the standard training algorithm as an inner optimizer, we incorporate an outer optimizer so as to equip the inner problem with an additional functionality: Adaptively selecting minibatch sizes for the purpose of improving model fairness. Our batch selection algorithm, which we call FairBatch, implements this optimization and supports prominent fairness measures: equal opportunity, equalized odds, and demographic parity. FairBatch comes with a significant implementation benefit -- it does not require any modification to data preprocessing or model training. For instance, a single-line change of PyTorch code for replacing batch selection part of model training suffices to employ FairBatch. Our experiments conducted both on synthetic and benchmark real data demonstrate that FairBatch can provide such functionalities while achieving comparable (or even greater) performances against the state of the arts. Furthermore, FairBatch can readily improve fairness of any pre-trained model simply via fine-tuning. It is also compatible with existing batch selection techniques intended for different purposes, such as faster convergence, thus gracefully achieving multiple purposes.

Details

NeurIPS Conference 2021 Conference Paper

Sample Selection for Fair and Robust Training

Yuji Roh
Kangwook Lee
Steven Whang
Changho Suh

Fairness and robustness are critical elements of Trustworthy AI that need to be addressed together. Fairness is about learning an unbiased model while robustness is about learning from corrupted data, and it is known that addressing only one of them may have an adverse affect on the other. In this work, we propose a sample selection-based algorithm for fair and robust training. To this end, we formulate a combinatorial optimization problem for the unbiased selection of samples in the presence of data corruption. Observing that solving this optimization problem is strongly NP-hard, we propose a greedy algorithm that is efficient and effective in practice. Experiments show that our method obtains fairness and robustness that are better than or comparable to the state-of-the-art technique, both on synthetic and benchmark real datasets. Moreover, unlike other fair and robust training baselines, our algorithm can be used by only modifying the sampling step in batch selection without changing the training algorithm or leveraging additional clean data.

PDF Details

NeurIPS Conference 2020 Conference Paper

A Fair Classifier Using Kernel Density Estimation

Jaewoong Cho
Gyeongjo Hwang
Changho Suh

As machine learning becomes prevalent in a widening array of sensitive applications such as job hiring and criminal justice, one critical aspect that machine learning classifiers should respect is to ensure fairness: guaranteeing the irrelevancy of a prediction output to sensitive attributes such as gender and race. In this work, we develop a kernel density estimation trick to quantify fairness measures that capture the degree of the irrelevancy. A key feature of our approach is that quantified fairness measures can be expressed as differentiable functions w. r. t. classifier model parameters. This then allows us to enjoy prominent gradient descent to readily solve an interested optimization problem that fully respects fairness constraints. We focus on a binary classification setting and two well-known definitions of group fairness: Demographic Parity (DP) and Equalized Odds (EO). Our experiments both on synthetic and benchmark real datasets demonstrate that our algorithm outperforms prior fair classifiers in accuracy-fairness tradeoff performance both w. r. t. DP and EO.

PDF Details

ICML Conference 2020 Conference Paper

FR-Train: A Mutual Information-Based Approach to Fair and Robust Training

Yuji Roh
Kangwook Lee 0001
Steven Euijong Whang
Changho Suh

Trustworthy AI is a critical issue in machine learning where, in addition to training a model that is accurate, one must consider both fair and robust training in the presence of data bias and poisoning. However, the existing model fairness techniques mistakenly view poisoned data as an additional bias to be fixed, resulting in severe performance degradation. To address this problem, we propose FR-Train, which holistically performs fair and robust model training. We provide a mutual information-based interpretation of an existing adversarial training-based fairness-only method, and apply this idea to architect an additional discriminator that can identify poisoned data using a clean validation set and reduce its influence. In our experiments, FR-Train shows almost no decrease in fairness and accuracy in the presence of data poisoning by both mitigating the bias and defending against poisoning. We also demonstrate how to construct clean validation sets using crowdsourcing, and release new benchmark datasets.

Details

NeurIPS Conference 2020 Conference Paper

Matrix Completion with Hierarchical Graph Side Information

Adel Elmahdy
Junhyung Ahn
Changho Suh
Soheil Mohajer

We consider a matrix completion problem that exploits social or item similarity graphs as side information. We develop a universal, parameter-free, and computationally efficient algorithm that starts with hierarchical graph clustering and then iteratively refines estimates both on graph clustering and matrix ratings. Under a hierarchical stochastic block model that well respects practically-relevant social graphs and a low-rank rating matrix model (to be detailed), we demonstrate that our algorithm achieves the information-theoretic limit on the number of observed matrix entries (i. e. , optimal sample complexity) that is derived by maximum likelihood estimation together with a lower-bound impossibility result. One consequence of this result is that exploiting the hierarchical structure of social graphs yields a substantial gain in sample complexity relative to the one that simply identifies different groups without resorting to the relational structure across them. We conduct extensive experiments both on synthetic and real-world datasets to corroborate our theoretical results as well as to demonstrate significant performance improvements over other matrix completion algorithms that leverage graph side information.

PDF Details

AAAI Conference 2019 Conference Paper

Crash to Not Crash: Learn to Identify Dangerous Vehicles Using a Simulator

Hoon Kim
Kangwook Lee
Gyeongjo Hwang
Changho Suh

Developing a computer vision-based algorithm for identifying dangerous vehicles requires a large amount of labeled accident data, which is difficult to collect in the real world. To tackle this challenge, we first develop a synthetic data generator built on top of a driving simulator. We then observe that the synthetic labels that are generated based on simulation results are very noisy, resulting in poor classification performance. In order to improve the quality of synthetic labels, we propose a new label adaptation technique that first extracts internal states of vehicles from the underlying driving simulator, and then refines labels by predicting future paths of vehicles based on a well-studied motion model. Via real-data experiments, we show that our dangerous vehicle classifier can reduce the missed detection rate by at least 18. 5% compared with those trained with real data when time-to-collision is between 1. 6 s and 1. 8 s.

PDF Details

NeurIPS Conference 2018 Conference Paper

Binary Rating Estimation with Graph Side Information

Kwangjun Ahn
Kangwook Lee
Hyunseung Cha
Changho Suh

Rich experimental evidences show that one can better estimate users' unknown ratings with the aid of graph side information such as social graphs. However, the gain is not theoretically quantified. In this work, we study the binary rating estimation problem to understand the fundamental value of graph side information. Considering a simple correlation model between a rating matrix and a graph, we characterize the sharp threshold on the number of observed entries required to recover the rating matrix (called the optimal sample complexity) as a function of the quality of graph side information (to be detailed). To the best of our knowledge, we are the first to reveal how much the graph side information reduces sample complexity. Further, we propose a computationally efficient algorithm that achieves the limit. Our experimental results demonstrate that the algorithm performs well even with real-world graphs.

PDF Details

ICML Conference 2017 Conference Paper

Active Learning for Top-K Rank Aggregation from Noisy Comparisons

Soheil Mohajer
Changho Suh
Adel M. Elmahdy

We explore an active top-$K$ ranking problem based on pairwise comparisons that are collected possibly in a sequential manner as per our design choice. We consider two settings: (1) top-$K$ sorting in which the goal is to recover the top-$K$ items in order out of $n$ items; (2) top-$K$ partitioning where only the set of top-$K$ items is desired. Under a fairly general model which subsumes as special cases various models (e. g. , Strong Stochastic Transitivity model, BTL model and uniform noise model), we characterize upper bounds on the sample size required for top-$K$ sorting as well as for top-$K$ partitioning. As a consequence, we demonstrate that active ranking can offer significant multiplicative gains in sample complexity over passive ranking. Depending on the underlying stochastic noise model, such gain varies from around $\frac{\log n}{\log \log n}$ to $\frac{ n^2 \log n }{\log \log n}$. We also present an algorithm that is applicable to both settings.

Details

NeurIPS Conference 2017 Conference Paper

Optimal Sample Complexity of M-wise Data for Top-K Ranking

Minje Jang
Sunghyun Kim
Changho Suh
Sewoong Oh

We explore the top-K rank aggregation problem in which one aims to recover a consistent ordering that focuses on top-K ranked items based on partially revealed preference information. We examine an M-wise comparison model that builds on the Plackett-Luce (PL) model where for each sample, M items are ranked according to their perceived utilities modeled as noisy observations of their underlying true utilities. As our result, we characterize the minimax optimality on the sample size for top-K ranking. The optimal sample size turns out to be inversely proportional to M. We devise an algorithm that effectively converts M-wise samples into pairwise ones and employs a spectral method using the refined data. In demonstrating its optimality, we develop a novel technique for deriving tight $\ell_\infty$ estimation error bounds, which is key to accurately analyzing the performance of top-K ranking algorithms, but has been challenging. Recent work relied on an additional maximum-likelihood estimation (MLE) stage merged with a spectral method to attain good estimates in $\ell_\infty$ error to achieve the limit for the pairwise model. In contrast, although it is valid in slightly restricted regimes, our result demonstrates a spectral method alone to be sufficient for the general M-wise model. We run numerical experiments using synthetic data and confirm that the optimal sample size decreases at the rate of 1/M. Moreover, running our algorithm on real-world data, we find that its applicability extends to settings that may not fit the PL model.

PDF Details

ICML Conference 2016 Conference Paper

Community Recovery in Graphs with Locality

Yuxin Chen 0002
Govinda M. Kamath
Changho Suh
David Tse

Motivated by applications in domains such as social networks and computational biology, we study the problem of community recovery in graphs with locality. In this problem, pairwise noisy measurements of whether two nodes are in the same community or different communities come mainly or exclusively from nearby nodes rather than uniformly sampled between all node pairs, as in most existing models. We present two algorithms that run nearly linearly in the number of measurements and which achieve the information limits for exact recovery.

Details

ICML Conference 2015 Conference Paper

Spectral MLE: Top-K Rank Aggregation from Pairwise Comparisons

Yuxin Chen 0002
Changho Suh

This paper explores the preference-based top-K rank aggregation problem. Suppose that a collection of items is repeatedly compared in pairs, and one wishes to recover a consistent ordering that emphasizes the top-K ranked items, based on partially revealed preferences. We focus on the Bradley-Terry-Luce (BTL) model that postulates a set of latent preference scores underlying all items, where the odds of paired comparisons depend only on the relative scores of the items involved. We characterize the minimax limits on identifiability of top-K ranked items, in the presence of random and non-adaptive sampling. Our results highlight a separation measure that quantifies the gap of preference scores between the K-th and (K+1)-th ranked items. The minimum sample complexity required for reliable top-K ranking scales inversely with the separation measure irrespective of other preference distribution metrics. To approach this minimax limit, we propose a nearly linear-time ranking scheme, called Spectral MLE, that returns the indices of the top-K items in accordance to a careful score estimate. In a nutshell, Spectral MLE starts with an initial score estimate with minimal squared loss (obtained via a spectral method), and then successively refines each component with the assistance of coordinate-wise MLEs. Encouragingly, Spectral MLE allows perfect top-K item identification under minimal sample complexity. The practical applicability of Spectral MLE is further corroborated by numerical experiments.

Details