Author name cluster

Kevin Yang

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.

6 papers

2 author rows

ICLR Conference 2024 Conference Paper

RLCD: Reinforcement Learning from Contrastive Distillation for LM Alignment

Kevin Yang
Dan Klein 0001
Asli Celikyilmaz
Nanyun Peng 0001
Yuandong Tian

We propose Reinforcement Learning from Contrastive Distillation (RLCD), a method for aligning language models to follow principles expressed in natural language (e.g., to be more harmless) without using human feedback. RLCD creates preference pairs from two contrasting model outputs, one using a positive prompt designed to encourage following the given principles, and one using a negative prompt designed to encourage violating them. Using two different prompts causes model outputs to be more differentiated on average, resulting in cleaner preference labels in the absence of human annotations. We then use the preference pairs to train a preference model, which is in turn used to improve a base unaligned language model via reinforcement learning. Empirically, RLCD outperforms RLAIF (Bai et al., 2022b) and context distillation (Huang et al., 2022) baselines across three diverse alignment tasks—harmlessness, helpfulness, and story outline generation—and when using both 7B and 30B model scales for simulating preference data

Details

NeurIPS Conference 2022 Conference Paper

Exploring evolution-aware & -free protein language models as protein function predictors

Mingyang Hu
Fajie Yuan
Kevin Yang
Fusong Ju
Jin Su
Hui Wang
Fei Yang
Qiuyang Ding

Large-scale Protein Language Models (PLMs) have improved performance in protein prediction tasks, ranging from 3D structure prediction to various function predictions. In particular, AlphaFold, a ground-breaking AI system, could potentially reshape structural biology. However, the utility of the PLM module in AlphaFold, Evoformer, has not been explored beyond structure prediction. In this paper, we investigate the representation ability of three popular PLMs: ESM-1b (single sequence), MSA-Transformer (multiple sequence alignment), and Evoformer (structural), with a special focus on Evoformer. Specifically, we aim to answer the following key questions: (1) Does the Evoformer trained as part of AlphaFold produce representations amenable to predicting protein function? (2) If yes, can Evoformer replace ESM-1b and MSA-Transformer? (3) How much do these PLMs rely on evolution-related protein data? In this regard, are they complementary to each other? We compare these models by empirical study along with new insights and conclusions. All code and datasets for reproducibility are available at https: //github. com/elttaes/Revisiting-PLMs.

PDF Details

ICLR Conference 2022 Conference Paper

Multi-objective Optimization by Learning Space Partition

Yiyang Zhao
Linnan Wang
Kevin Yang
Tianjun Zhang
Tian Guo 0001
Yuandong Tian

In contrast to single-objective optimization (SOO), multi-objective optimization (MOO) requires an optimizer to find the Pareto frontier, a subset of feasible solutions that are not dominated by other feasible solutions. In this paper, we propose LaMOO, a novel multi-objective optimizer that learns a model from observed samples to partition the search space and then focus on promising regions that are likely to contain a subset of the Pareto frontier. The partitioning is based on the dominance number, which measures "how close'' a data point is to the Pareto frontier among existing samples. To account for possible partition errors due to limited samples and model mismatch, we leverage Monte Carlo Tree Search (MCTS) to exploit promising regions while exploring suboptimal regions that may turn out to contain good solutions later. Theoretically, we prove the efficacy of learning space partitioning via LaMOO under certain assumptions. Empirically, on the HyperVolume (HV) benchmark, a popular MOO metric, LaMOO substantially outperforms strong baselines on multiple real-world MOO tasks, by up to 225% in sample efficiency for neural architecture search on Nasbench201, and up to 10% for molecular design.

Details

NeurIPS Conference 2021 Conference Paper

FLIP: Benchmark tasks in fitness landscape inference for proteins

Christian Dallago
Jody Mou
Kadina Johnston
Bruce Wittmann
Nicholas Bhattacharya
Samuel Goldman
Ali Madani
Kevin Yang

Machine learning could enable an unprecedented level of control in protein engineering for therapeutic and industrial applications. Critical to its use in designing proteins with desired properties, machine learning models must capture the protein sequence-function relationship, often termed fitness landscape. Existing benchmarks like CASP or CAFA assess structure and function predictions of proteins, respectively, yet they do not target metrics relevant for protein engineering. In this work, we introduce Fitness Landscape Inference for Proteins (FLIP), a benchmark for function prediction to encourage rapid scoring of representation learning for protein engineering. Our curated splits, baselines, and metrics probe model generalization in settings relevant for protein engineering, e. g. low-resource and extrapolative. Currently, FLIP encompasses experimental data across adeno-associated virus stability for gene therapy, protein domain B1 stability and immunoglobulin binding, and thermostability from multiple protein families. In order to enable ease of use and future expansion to new splits, all data are presented in a standard format. FLIP scripts and data are freely accessible at https: //benchmark. protein. properties.

PDF Details

NeurIPS Conference 2021 Conference Paper

Learning Space Partitions for Path Planning

Kevin Yang
Tianjun Zhang
Chris Cummins
Brandon Cui
Benoit Steiner
Linnan Wang
Joseph E. Gonzalez
Dan Klein

Path planning, the problem of efficiently discovering high-reward trajectories, often requires optimizing a high-dimensional and multimodal reward function. Popular approaches like CEM and CMA-ES greedily focus on promising regions of the search space and may get trapped in local maxima. DOO and VOOT balance exploration and exploitation, but use space partitioning strategies independent of the reward function to be optimized. Recently, LaMCTS empirically learns to partition the search space in a reward-sensitive manner for black-box optimization. In this paper, we develop a novel formal regret analysis for when and why such an adaptive region partitioning scheme works. We also propose a new path planning method LaP3 which improves the function value estimation within each sub-region, and uses a latent representation of the search space. Empirically, LaP3 outperforms existing path planning methods in 2D navigation tasks, especially in the presence of difficult-to-escape local optima, and shows benefits when plugged into the planning components of model-based RL such as PETS. These gains transfer to highly multimodal real-world tasks, where we outperform strong baselines in compiler phase ordering by up to 39% on average across 9 tasks, and in molecular design by up to 0. 4 on properties on a 0-1 scale. Code is available at https: //github. com/yangkevin2/neurips2021-lap3.

PDF Details

ICML Conference 2020 Conference Paper

Improving Molecular Design by Stochastic Iterative Target Augmentation

Kevin Yang
Wengong Jin
Kyle Swanson
Regina Barzilay
Tommi S. Jaakkola

Generative models in molecular design tend to be richly parameterized, data-hungry neural models, as they must create complex structured objects as outputs. Estimating such models from data may be challenging due to the lack of sufficient training data. In this paper, we propose a surprisingly effective self-training approach for iteratively creating additional molecular targets. We first pre-train the generative model together with a simple property predictor. The property predictor is then used as a likelihood model for filtering candidate structures from the generative model. Additional targets are iteratively produced and used in the course of stochastic EM iterations to maximize the log-likelihood that the candidate structures are accepted. A simple rejection (re-weighting) sampler suffices to draw posterior samples since the generative model is already reasonable after pre-training. We demonstrate significant gains over strong baselines for both unconditional and conditional molecular design. In particular, our approach outperforms the previous state-of-the-art in conditional molecular design by over 10% in absolute gain. Finally, we show that our approach is useful in other domains as well, such as program synthesis.

Details