no code implementations • 11 Dec 2024 • Yoonho Lee, Jonathan Williams, Henrik Marklund, Archit Sharma, Eric Mitchell, Anikait Singh, Chelsea Finn
Large pretrained models often struggle with underspecified tasks -- situations where the training data does not fully define the desired behavior.
1 code implementation • 29 Sep 2024 • Johnathan Xie, Annie S. Chen, Yoonho Lee, Eric Mitchell, Chelsea Finn
The effectiveness of large language models (LLMs) is not only measured by their ability to generate accurate outputs but also by their calibration-how well their confidence scores reflect the probability of their outputs being correct.
2 code implementations • 30 Aug 2024 • Yuejiang Liu, Jubayer Ibn Hamid, Annie Xie, Yoonho Lee, Maximilian Du, Chelsea Finn
In this paper, we first dissect how action chunking impacts the divergence between a learner and a demonstrator.
1 code implementation • 19 Jun 2024 • Sangwoo Seo, Sungwon Kim, Jihyeong Jung, Yoonho Lee, Chanyoung Park
In this work, we propose a novel built-in explanation framework for temporal graphs, called Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck (TGIB).
1 code implementation • 22 Feb 2024 • Johnathan Xie, Yoonho Lee, Annie S. Chen, Chelsea Finn
Self-supervised learning excels in learning representations from large amounts of unlabeled data, demonstrating success across multiple data modalities.
Ranked #2 on
Molecular Property Prediction
on Lipophilicity
1 code implementation • 6 Feb 2024 • Yoonho Lee, Michelle S. Lam, Helena Vasconcelos, Michael S. Bernstein, Chelsea Finn
Clarify is the first end-to-end system for user model correction.
no code implementations • 18 Jan 2024 • Caroline Choi, Yoonho Lee, Annie Chen, Allan Zhou, aditi raghunathan, Chelsea Finn
Given a task, AutoFT searches for a fine-tuning procedure that enhances out-of-distribution (OOD) generalization.
no code implementations • 19 Jun 2023 • Annie S. Chen, Yoonho Lee, Amrith Setlur, Sergey Levine, Chelsea Finn
Effective machine learning models learn both robust features that directly determine the outcome of interest (e. g., an object with wheels is more likely to be a car), and shortcut features (e. g., an object on a road is more likely to be a car).
1 code implementation • 8 Jun 2023 • Caroline Choi, Fahim Tajwar, Yoonho Lee, Huaxiu Yao, Ananya Kumar, Chelsea Finn
We theoretically analyze the choice of auxiliary dataset for confidence minimization, revealing two actionable insights: (1) if the auxiliary set contains unknown examples similar to those seen at test time, confidence minimization leads to provable detection of unknown test examples, and (2) if the first condition is satisfied, it is unnecessary to filter out known examples for out-of-distribution (OOD) detection.
no code implementations • 10 Feb 2023 • Annie S. Chen, Yoonho Lee, Amrith Setlur, Sergey Levine, Chelsea Finn
Transfer learning with a small amount of target data is an effective and common approach to adapting a pre-trained model to distribution shifts.
4 code implementations • 26 Jan 2023 • Eric Mitchell, Yoonho Lee, Alexander Khazatsky, Christopher D. Manning, Chelsea Finn
In this paper, we identify a property of the structure of an LLM's probability function that is useful for such detection.
1 code implementation • 25 Nov 2022 • Huaxiu Yao, Caroline Choi, Bochuan Cao, Yoonho Lee, Pang Wei Koh, Chelsea Finn
Temporal shifts -- distribution shifts arising from the passage of time -- often occur gradually and have the additional structure of timestamp metadata.
1 code implementation • 20 Oct 2022 • Yoonho Lee, Annie S. Chen, Fahim Tajwar, Ananya Kumar, Huaxiu Yao, Percy Liang, Chelsea Finn
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.
1 code implementation • 12 Oct 2022 • Balhae Kim, JungWon Choi, Seanie Lee, Yoonho Lee, Jung-Woo Ha, Juho Lee
Finally, we propose a novel Bayesian pseudocoreset algorithm based on minimizing forward KL divergence.
1 code implementation • 7 Feb 2022 • Yoonho Lee, Huaxiu Yao, Chelsea Finn
Many datasets are underspecified: there exist multiple equally viable solutions to a given task.
no code implementations • NeurIPS 2021 • Giung Nam, Jongmin Yoon, Yoonho Lee, Juho Lee
We propose a simple approach for reducing this gap, i. e., making the distilled performance close to the full ensemble.
no code implementations • 5 Jul 2021 • Minkyo Seo, Yoonho Lee, Suha Kwak
This paper studies probability distributions of penultimate activations of classification networks.
2 code implementations • 29 Oct 2020 • Yueqi Wang, Yoonho Lee, Pallab Basu, Juho Lee, Yee Whye Teh, Liam Paninski, Ari Pakman
While graph neural networks (GNNs) have been successful in encoding graph structures, existing GNN-based methods for community detection are limited by requiring knowledge of the number of communities in advance, in addition to lacking a proper probabilistic formulation to handle uncertainty.
1 code implementation • NeurIPS 2020 • Yoonho Lee, Juho Lee, Sung Ju Hwang, Eunho Yang, Seungjin Choi
While various complexity measures for deep neural networks exist, specifying an appropriate measure capable of predicting and explaining generalization in deep networks has proven challenging.
1 code implementation • NeurIPS 2020 • Juho Lee, Yoonho Lee, Jungtaek Kim, Eunho Yang, Sung Ju Hwang, Yee Whye Teh
While this "data-driven" way of learning stochastic processes has proven to handle various types of data, NPs still rely on an assumption that uncertainty in stochastic processes is modeled by a single latent variable, which potentially limits the flexibility.
no code implementations • ICLR 2020 • Juho Lee, Yoonho Lee, Yee Whye Teh
We propose a deep amortized clustering (DAC), a neural architecture which learns to cluster datasets efficiently using a few forward passes.
no code implementations • 25 Sep 2019 • Yoonho Lee, Wonjae Kim, Seungjin Choi
This paper analyzes how generalization works in meta-learning.
1 code implementation • NeurIPS 2019 • Wonjae Kim, Yoonho Lee
Without relevant human priors, neural networks may learn uninterpretable features.
no code implementations • 28 May 2019 • Yoonho Lee, Wonjae Kim, Wonpyo Park, Seungjin Choi
In this paper we present a model that produces Discrete InfoMax Codes (DIMCO); we learn a probabilistic encoder that yields k-way d-dimensional codes associated with input data.
9 code implementations • 1 Oct 2018 • Juho Lee, Yoonho Lee, Jungtaek Kim, Adam R. Kosiorek, Seungjin Choi, Yee Whye Teh
Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances.
1 code implementation • ICML 2018 • Yoonho Lee, Seungjin Choi
Our primary contribution is the {\em 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.