Yoonho Lee

I’m a CS Ph.D. student at Stanford, advised by Chelsea Finn and part of the IRIS Lab. My research is supported by the KFAS Doctoral Fellowship. Previously, as alternative military service for the South Korean army, I worked as a research scientist at Kakao and AITRICS, working with Juho Lee. Before that, I completed my master’s (CS, advised by Seungjin Choi) and undergraduate (math) degrees at POSTECH.

My research interest is in developing neural network models that can learn and make reliable decisions even in changing environments. To accomplish this, I believe that we should move beyond the independent and identically distributed (i.i.d.) paradigm and address the nonstationary nature of real-world data in our learning and evaluation procedures.

selected publications

ICML

DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
Eric Mitchell, Yoonho Lee, Alexander Khazatsky, Christopher D Manning, Chelsea Finn
ICML 2023 (oral) [abstract] [paper] [website] [code] [demo]
TLDR: We develop a method that can detect if a passage is generated by a particular language model. Our method is based on the hypothesis that a passage is likely model-generated if it is near a local maximum in the model’s predictive probability space.

The fluency and factual knowledge of large language models (LLMs) heightens the need for corresponding systems to detect whether a piece of text is machine-written. For example, students may use LLMs to complete written assignments, leaving instructors unable to accurately assess student learning. In this paper, we first demonstrate that text sampled from an LLM tends to occupy negative curvature regions of the model’s log probability function. Leveraging this observation, we then define a new curvature-based criterion for judging if a passage is generated from a given LLM. This approach, which we call DetectGPT, does not require training a separate classifier, collecting a dataset of real or generated passages, or explicitly watermarking generated text. It uses only log probabilities computed by the model of interest and random perturbations of the passage from another generic pre-trained language model (e.g, T5). We find DetectGPT is more discriminative than existing zero-shot methods for model sample detection, notably improving detection of fake news articles generated by 20B parameter GPT-NeoX from 0.81 AUROC for the strongest zero-shot baseline to 0.95 AUROC for DetectGPT.
Conservative Prediction via Transductive Confidence Minimization
Caroline Choi*, Fahim Tajwar*, Yoonho Lee*, Huaxiu Yao, Ananya Kumar, Chelsea Finn
ICLR 2023 workshops: TrustML, ME-FoMo [abstract] [paper]
TLDR: Conservative prediction by reducing confidence on an unlabeled uncertainty set.

Errors of machine learning models can be prohibitively costly, especially in safety-critical settings such as healthcare. However, machine learning may be applicable to such scenarios if the learned model can abstain and defer to a human on difficult examples instead of making errors. In safety-critical settings, we prefer conservative models that defer to humans at the cost of some overall accuracy. Unfortunately, selective classification and out-of-distribution detection are notably difficult as it is hard to anticipate all possible examples. To mitigate this challenge, we focus on the transductive setting, where unlabeled examples from the test distribution are available during training. We propose transductive confidence minimization (TCM), which minimizes prediction confidence on unlabeled test examples while simultaneously optimizing the training objective. We theoretically show that TCM learns a lower bound on the true confidence, and that this property can be leveraged to provably detect examples that are sufficiently different from training examples, regardless of what distribution they came from. In our experiments, TCM consistently shows high performance, achieving the highest OOD detection performance compared to 6 other methods on 9 out of 10 ID->OOD pairs and consistently outperforming methods for selective classification in settings where we test on data from a previously unseen distribution.
Project and Probe: Sample-Efficient Domain Adaptation by Interpolating Orthogonal Features
Annie S. Chen*, Yoonho Lee*, Amrith Setlur, Sergey Levine, Chelsea Finn
ICLR 2023 workshops: TrustML (oral), ME-FoMo [abstract] [paper]
TLDR: A lightweight and sample-efficient approach that learns diverse linear features and adapts to a target distribution by interpolating among them with a small target dataset.

Conventional approaches to robustness try to learn a model based on causal features. However, identifying maximally robust or causal features may be difficult in some scenarios, and in others, non-causal "shortcut" features may actually be more predictive. We propose a lightweight, sample-efficient approach that learns a diverse set of features and adapts to a target distribution by interpolating these features with a small target dataset. Our approach, Project and Probe (Pro2), first learns a linear projection that maps a pre-trained embedding onto orthogonal directions while being predictive of labels in the source dataset. The goal of this step is to learn a variety of predictive features, so that at least some of them remain useful after distribution shift. Pro2 then learns a linear classifier on top of these projected features using a small target dataset. We theoretically show that Pro2 learns a projection matrix that is optimal for classification in an information-theoretic sense, resulting in better generalization due to a favorable bias-variance tradeoff. Our experiments on four datasets, with multiple distribution shift settings for each, show that Pro2 improves performance by 5-15% when given limited target data compared to prior methods such as standard linear probing.
ICLR

Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
Yoonho Lee*, Annie S. Chen*, Fahim Tajwar, Ananya Kumar, Huaxiu Yao, Percy Liang, Chelsea Finn
ICLR 2023
NeurIPS 2022 Workshops: DistShift, ICBINB [abstract] [paper]
TLDR: The best layer to fine-tune reflects the nature of the distribution shift.

A common approach to transfer learning under distribution shift is to fine-tune the last few layers of a pre-trained model, preserving learned features while also adapting to the new task. This paper shows that in such settings, selectively fine-tuning a subset of layers (which we term surgical fine-tuning) matches or outperforms commonly used fine-tuning approaches. Moreover, the type of distribution shift influences which subset is more effective to tune: for example, for image corruptions, fine-tuning only the first few layers works best. We validate our findings systematically across seven real-world data tasks spanning three types of distribution shifts. Theoretically, we prove that for two-layer neural networks in an idealized setting, first-layer tuning can outperform fine-tuning all layers. Intuitively, fine-tuning more parameters on a small target dataset can cause information learned during pre-training to be forgotten, and the relevant information depends on the type of shift.
ICLR

Diversify and Disambiguate: Out-of-Distribution Robustness via Disagreement
Yoonho Lee, Huaxiu Yao, Chelsea Finn
ICLR 2023
ICML workshops: PODS, SCIS [abstract] [paper] [website] [code]
TLDR: Given underspecified data, (1) find a diverse set of solutions and (2) choose the best one.

Many datasets are underspecified: there exist multiple equally viable solutions to a given task. Underspecification can be problematic for methods that learn a single hypothesis because different functions that achieve low training loss can focus on different predictive features and thus produce widely varying predictions on out-of-distribution data. We propose DivDis, a simple two-stage framework that first learns a diverse collection of hypotheses for a task by leveraging unlabeled data from the test distribution. We then disambiguate by selecting one of the discovered hypotheses using minimal additional supervision, in the form of additional labels or inspection of function visualization. We demonstrate the ability of DivDis to find hypotheses that use robust features in image classification and natural language processing problems with underspecification.
ICML

Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
Juho Lee, Yoonho Lee, Jungtaek Kim, Adam Kosiorek, Seungjin Choi, Yee Whye Teh
ICML 2019 [abstract] [paper] [code]
TLDR: Self-attention for sets using inducing points. O(N) feedforward complexity.

Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances. Since solutions to such problems do not depend on the order of elements of the set, models used to address them should be permutation invariant. We present an attention-based neural network module, the Set Transformer, specifically designed to model interactions among elements in the input set. The model consists of an encoder and a decoder, both of which rely on attention mechanisms. In an effort to reduce computational complexity, we introduce an attention scheme inspired by inducing point methods from sparse Gaussian process literature. It reduces the computation time of self-attention from quadratic to linear in the number of elements in the set. We show that our model is theoretically attractive and we evaluate it on a range of tasks, demonstrating the state-of-the-art performance compared to recent methods for set-structured data.
ICML

Gradient-based Meta-learning with Learned Layerwise Metric and Subspace
Yoonho Lee, Seungjin Choi
ICML 2018 [abstract] [paper] [video] [code]
TLDR: Improving MAML by fixing some weights during task adaptation.

Gradient-based meta-learning methods leverage gradient descent to learn the commonalities among various tasks. While previous such methods have been successful in meta-learning tasks, they resort to simple gradient descent during meta-testing. Our primary contribution is the MT-net, which enables the meta-learner to learn on each layer’s activation space a subspace that the task-specific learner performs gradient descent on. Additionally, a task-specific learner of an MT-net performs gradient descent with respect to a meta-learned distance metric, which warps the activation space to be more sensitive to task identity. We demonstrate that the dimension of this learned subspace reflects the complexity of the task-specific learner’s adaptation task, and also that our model is less sensitive to the choice of initial learning rates than previous gradient-based meta-learning methods. Our method achieves state-of-the-art or comparable performance on few-shot classification and regression tasks.