There are many applications where positive instances are rare but important to identify. For example, in NLP, positive sentences for a given relation are rare in a large corpus. Positive data are more informative for learning in these applications, but before one labels a certain amount of data, it is unknown where to find the rare positives. Since random sampling can lead to significant waste in labeling effort, previous ”active search” methods use a single bandit model to learn about the data distribution (exploration) while sampling from the regions potentially containing more positives (exploitation). Many bandit models are possible and a sub-optimal model reduces labeling efficiency, but the optimal model is unknown before any data are labeled. We propose Meta-AS (Meta Active Search) that uses a meta-bandit to evaluate a set of base bandits and aims to label positive examples efficiently, comparing to the optimal base bandit with hindsight. The meta-bandit estimates the mean and variance of the performance of the base bandits, and selects a base bandit to propose what data to label next for exploration or exploitation. The feedback in the labels updates both the base bandits and the meta-bandit for the next round. Meta-AS can accommodate a diverse set of base bandits to explore assumptions about the dataset, without over-committing to a single model before labeling starts. Experiments on five datasets for relation extraction demonstrate that Meta-AS labels positives more efficiently than the base bandits and other bandit selection strategies.
more »
« less
Active-learning and materials design: the example of high glass transition temperature polymers
Machine-learning (ML) approaches have proven to be of great utility in modern materials innovation pipelines. Generally, ML models are trained on predetermined past data and then used to make predictions for new test cases. Active-learning, however, is a paradigm in which ML models can direct the learning process itself through providing dynamic suggestions/queries for the “next-best experiment.” In this work, the authors demonstrate how an active-learning framework can aid in the discovery of polymers possessing high glass transition temperatures ( T g ). Starting from an initial small dataset of polymer T g measurements, the authors use Gaussian process regression in conjunction with an active-learning framework to iteratively add T g measurements of candidate polymers to the training dataset. The active-learning framework employs one of three decision making strategies (exploitation, exploration, or balanced exploitation/exploration) for selection of the “next-best experiment.” The active-learning workflow terminates once 10 polymers possessing a T g greater than a certain threshold temperature are selected. The authors statistically benchmark the performance of the aforementioned three strategies (against a random selection approach) with respect to the discovery of high- T g polymers for this particular demonstrative materials design challenge.
more »
« less
- Award ID(s):
- 1743418
- NSF-PAR ID:
- 10098412
- Date Published:
- Journal Name:
- MRS Communications
- ISSN:
- 2159-6859
- Page Range / eLocation ID:
- 1 to 7
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
High-throughput molecular simulations and machine learning (ML) have been implemented to adequately screen a large number of metal−organic frameworks (MOFs) for applications involving adsorption. Grand canonical Monte Carlo (GCMC) simulations have proven effective in calculating the adsorption capacity at given pressures and temperatures, but they can require expensive computational resources. While they can be resource-efficient, ML models can require large datasets, creating a need for algorithms that can efficiently characterize adsorption; active learning (AL) can play a very important role in this regard. In this work, we make use of Gaussian process regression (GPR) to model pure component adsorption of nitrogen at 77 K from 10−5 to 1 bar, methane at 298 K from 10 −5 to 100 bar, carbon dioxide at 298 K from 10−5 to 100 bar, and hydrogen at 77 K from 10−5 to 100 bar on PCN-61, MgMOF-74, DUT-32, DUT-49, MOF-177, NU-800, UiO-66, ZIF-8, IRMOF-1, IRMOF-10, and IRMOF-16. The GPR model requires an initial training of the model with an initial dataset, the prior one, and, in this study of evaluating AL, we make use of three different prior selection schemes. Each prior scheme is updated with a sampling point resulting from the GP model uncertainties. This protocol continues until a maximum GPR relative error of 2% is attained. We make a recommendation on the best prior selection scheme for the total 44 adsorbate−adsorbent pairs primarily making use of the mean absolute error and the total amount of points required for convergence of the model. To further evaluate the AL framework, we apply the BET consistency criteria on the simulated and GP nitrogen isotherms and compare the resulting surface areas.more » « less
-
more » « less
Abstract Polymers play an integral role in various applications, from everyday use to advanced technologies. In the era of machine learning (ML), polymer informatics has become a vital field for efficiently designing and developing polymeric materials. However, the focus of polymer informatics has predominantly centered on single-component polymers, leaving the vast chemical space of polymer blends relatively unexplored. This study employs a high-throughput molecular dynamics (MD) simulation combined with active learning (AL) to uncover polymer blends with enhanced thermal conductivity (TC) compared to the constituent single-component polymers. Initially, the TC of about 600 amorphous single-component polymers and 200 amorphous polymer blends with varying blending ratios are determined through MD simulations. The optimal representation method for polymer blends is identified, which involves a weighted sum approach that extends existing polymer representation from single-component polymers to polymer blends. An AL framework, combining MD simulation and ML, is employed to explore the TC of approximately 550,000 unlabeled polymer blends. The AL framework proves highly effective in accelerating the discovery of high-performance polymer blends for thermal transport. Additionally, we delve into the relationship between TC, radius of gyration (
R g), and hydrogen bonding, highlighting the roles of inter- and intra-chain interactions in thermal transport in amorphous polymer blends. A significant positive association between TC andR gimprovement and an indirect contribution from H-bond interaction to TC enhancement are revealed through a log-linear model and an odds ratio calculation, emphasizing the impact of increasingR gand H-bond interactions on enhancing polymer blend TC. -
more » « less
In the recent decades, with rapid development in computing power and algorithms, machine learning (ML) has exhibited its enormous potential in new polymer discovery. Herein, the history of ML is described and the basic process of ML accelerated polymer discovery is summarized. Next, the four steps in this process are reviewed, that is, dataset selection, fingerprinting, ML framework, and new polymer generation. Finally, a couple of main challenges for ML accelerated polymer discovery is presented and the outlooks in this field are prospected. It is expected that this review can service as a useful tool for the people who just step into this field and deepen the understanding for the people who are already in this field.
-
When and Whom to Collaborate with in a Changing Environment: A Collaborative Dynamic Bandit Solutionnull (Ed.)Collaborative bandit learning, i.e., bandit algorithms that utilize collaborative filtering techniques to improve sample efficiency in online interactive recommendation, has attracted much research attention as it enjoys the best of both worlds. However, all existing collaborative bandit learning solutions impose a stationary assumption about the environment, i.e., both user preferences and the dependency among users are assumed static over time. Unfortunately, this assumption hardly holds in practice due to users' ever-changing interests and dependency relations, which inevitably costs a recommender system sub-optimal performance in practice. In this work, we develop a collaborative dynamic bandit solution to handle a changing environment for recommendation. We explicitly model the underlying changes in both user preferences and their dependency relation as a stochastic process. Individual user's preference is modeled by a mixture of globally shared contextual bandit models with a Dirichlet process prior. Collaboration among users is thus achieved via Bayesian inference over the global bandit models. To balance exploitation and exploration during the interactions, Thompson sampling is used for both model selection and arm selection. Our solution is proved to maintain a standard $\tilde O(\sqrt{T})$ Bayesian regret in this challenging environment. Extensive empirical evaluations on both synthetic and real-world datasets further confirmed the necessity of modeling a changing environment and our algorithm's practical advantages against several state-of-the-art online learning solutions.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1557/mrc.2019.78
