Nanoporous materials (NPMs) are suitable for solving some of the society's biggest challenges including carbon capture and conversion, storing hydrogen and methane, and sensing gases. The key challenge in discovering high-performing NPMs for a target application is that making and evaluating candidate NPMs requires performing resource-expensive wet-lab experiments. We consider the problem of discovering NPMs using existing experimental data of NPM evaluations. The overall goal is to find better NPMs than the best NPMs from the past experimental data. A simple approach is to create a surrogate model to match the objective values on the given dataset and employ it to score candidate NPMs to discover optimized NPMs. However, this surrogate model will fail because it does not have the appropriate search bias for the goal of optimization. To address this challenge, we propose a novel surrogate modeling approach that combines value matching loss with an optimization bias as regularizer. The key idea is to algorithmically realize search bias is to mimic the search behavior of monotonically increasing sequences of NPMs from the given dataset. Experiments on multiple real-world NPM discovery tasks demonstrate that our proposed surrogate model discovers significantly better NPMs than baselines including value matching surrogate model and one-step Bayesian optimization.

Various complex water management decisions are made in snow-dominant watersheds with the knowledge of Snow-Water Equivalent (SWE)---a key measure widely used to estimate the water content of a snowpack. However, forecasting SWE is challenging because SWE is influenced by various factors including topography and an array of environmental conditions, and has therefore been observed to be spatio-temporally variable. Classical approaches to SWE forecasting have not adequately utilized these spatial/temporal correlations, nor do they provide uncertainty estimates --- which can be of significant value to the decision maker. In this paper, we present ForeSWE, a new probabilistic spatio-temporal forecasting model that integrates deep learning and classical probabilistic techniques. The resulting model features a combination of an attention mechanism to integrate spatiotemporal features and interactions, alongside a Gaussian process module that provides principled quantification of prediction uncertainty. We evaluate the model on data from 512 Snow Telemetry (SNOTEL) stations in the Western US. The results show significant improvements in both forecasting accuracy and prediction interval compared to state-of-the-art approaches. The results also serve to highlight the efficacy in uncertainty estimates between different approaches. Collectively, these findings have provided a platform for deployment and feedback by the water management community.

Multimodal federated learning in real-world settings often encounters incomplete and heterogeneous data across clients. This results in misaligned local feature representations that limit the effectiveness of model aggregation. Unlike prior work that assumes either differing modality sets without missing input features or a shared modality set with missing features across clients, we consider a more general and realistic setting where each client observes a different subset of modalities and might also have missing input features within each modality. To address the resulting misalignment in learned representations, we propose a new federated learning framework featuring locally adaptive representations based on learnable client-side embedding controls that encode each client’s data-missing patterns. These embeddings serve as reconfiguration signals that align the globally aggregated representation with each client's local context, enabling more effective use of shared information. Furthermore, the embedding controls can be algorithmically aggregated across clients with similar data-missing patterns to enhance the robustness of reconfiguration signals in adapting the global representation. Empirical results on multiple federated multimodal benchmarks with diverse data-missing patterns across clients demonstrate the efficacy of the proposed method, achieving up to 36.45\% performance improvement under severe data incompleteness. The method is also supported by a theoretical analysis with an explicit performance bound that matches our empirical observations. Our source codes are provided at [https://github.com/nmduonggg/PEPSY](https://github.com/nmduonggg/PEPSY)

Federated Learning (FL) has emerged as an effective paradigm allowing multiple parties to collaboratively train a global model while protecting their private data. However, it is observed that the performance of FL approaches tends to degrade significantly when data are sparsely distributed across clients with small datasets. This is referred to as the sparse-and-scarce challenge, where data held by each client is both sparse (does not contain examples to all classes) and scarce (small dataset). Sparse-and-scarce data diminishes the generalizability of clients’ data, leading to intensive over-fitting and massive domain shifts in the local models and, ultimately, decreasing the aggregated model's performance. Interestingly, while this scenario is a specific manifestation of the well-known non-IID11This refers to the generic situation where local data distributions are not identical and independently distributed.challenge in FL, it has not been distinctly addressed. Our empirical investigation highlights that generic approaches to the non-IID challenge often prove inadequate in mitigating the sparse-and-scarce issue. To bridge this gap, we develop SAFA, a novel FL algorithm that specifically addresses the sparse-and-scarce challenge via a novel continual model iteration procedure. SAFA maximally exposes local models to the inter-client diversity of data with minimal effects of catastrophic forgetting. Our experiments show that SAFA outperforms existing FL solutions, up to 17.86%, compared to the prominent baseline. The code is accessible viahttps://github.com/HungNguyen20/SAFA.

Offline optimization is an emerging problem in many experimental engineering domains including protein, drug or aircraft design, where online experimentation to collect evaluation data is too expensive or dangerous. To avoid that, one has to optimize an unknown function given only its offline evaluation at a fixed set of inputs. A naive solution to this problem is to learn a surrogate model of the unknown function and optimize this surrogate instead. However, such a naive optimizer is prone to erroneous overestimation of the surrogate (possibly due to over-fitting on a biased sample of function evaluation) on inputs outside the offline dataset. Prior approaches addressing this challenge have primarily focused on learning robust surrogate models. However, their search strategies are derived from the surrogate model rather than the actual offline data. To fill this important gap, we introduce a new learning-to-search perspective for offline optimization by reformulating it as an offline reinforcement learning problem. Our proposed policy-guided gradient search approach explicitly learns the best policy for a given surrogate model created from the offline data. Our empirical results on multiple benchmarks demonstrate that the learned optimization policy can be combined with existing offline surrogates to significantly improve the optimization performance.

The increasingly decentralized and private nature of data in our digital society has motivated the development of personalized, collaborative intelligent systems that enable knowledge aggregation across multiple data owners while accommodating for their data privacy and system constraints. However, collaborative learning has only been investigated in simple and limited settings: isolated task scenarios where learning begins from scratch and does not build on prior expertise; learned model is represented in task-specific forms which are not generalizable to unseen, emerging scenarios; and more often, a universal model representation is assumed across collaborators, ignoring their local compute constraints or input representations. This restricts its practicality in continual learning scenarios with limited task data, which demand continuous adaptation and knowledge transfer across different information silos, tasks, and learning models, as well as the utilization of prior solution expertises. To overcome these limitations, my research has been focused on developing effective and scalable resource-aware collaborative learning frameworks across heterogeneous systems.

This paper investigates the problem of exploiting existing solution models of previous tasks to address a related target task with limited training data. Existing approaches addressing this problem often require access to the internal parameterization of the existing solution models and possibly their training data, which is not possible in many practical settings. To relax this requirement, We approach this problem from a new perspective of black-box re-purposing, which augments the target inputs and leverages their corresponding outputs generated by existing black-box APIs into a feature ensemble. We hypothesize that such feature ensemble can be learned to incorporate and encode relevant black-box knowledge into the feature representation of target data, which will compensate for their scarcity. This hypothesis is confirmed via the reported successes of our proposed black-box ensemble in solving multiple few-shot learning tasks derived from various benchmark datasets. All reported results show consistently that the set of heterogeneous black-box solutions of previous tasks can indeed be reused and combined effectively to solve a reasonably related target task without requiring access to a large training dataset. This is the first step towards enabling new possibilities to further supplement existing techniques in transfer or meta learning with black-box knowledge.

Offline optimization is an important task in numerous material engineering domains where online experimentation to collect data is too expensive and needs to be replaced by an in silico maximization of a surrogate of the black-box function. Although such a surrogate can be learned from offline data, its prediction might not be reliable outside the offline data regime, which happens when the surrogate has narrow prediction margin and is (therefore) sensitive to small perturbations of its parameterization. This raises the following questions: (1) how to regulate the sensitivity of a surrogate model; and (2) whether conditioning an offline optimizer with such less sensitive surrogate will lead to better optimization performance. To address these questions, we develop an optimizable sensitivity measurement for the surrogate model, which then inspires a sensitivity-informed regularizer that is applicable to a wide range of offline optimizers. This development is both orthogonal and synergistic to prior research on offline optimization, which is demonstrated in our extensive experiment benchmark.

Offline design optimization problem arises in numerous science and engineering applications including material and chemical design, where expensive online experimentation necessitates the use of *in silico* surrogate functions to predict and maximize the target objective over candidate designs. Although these surrogates can be learned from offline data, their predictions are often inaccurate outside the offline data regime. This challenge raises a fundamental question about the impact of imperfect surrogate model on the performance gap between its optima and the true optima, and to what extent the performance loss can be mitigated. Although prior work developed methods to improve the robustness of surrogate models and their associated optimization processes, a provably quantifiable relationship between an imperfect surrogate and the corresponding performance gap, as well as whether prior methods directly address it, remain elusive. To shed light on this important question, we present a theoretical framework to understand offline black-box optimization, by explicitly bounding the optimization quality based on how well the surrogate matches the latent gradient field that underlines the offline data. Inspired by our theoretical analysis, we propose a principled black-box gradient matching algorithm to create effective surrogate models for offline optimization, improving over prior approaches on various real-world benchmarks.

Federated Learning (FL) is a method for training machine learning models using distributed data sources. It ensures privacy by allowing clients to collaboratively learn a shared global model while storing their data locally. However, a significant challenge arises when dealing with missing modalities in clients’ datasets, where certain features or modalities are unavailable or incomplete, leading to heterogeneous data distribution. While previous studies have addressed the issue of complete-modality missing1, they fail to tackle partial-modality missing2on account of severe heterogeneity among clients at an instance level, where the pattern of missing data can vary significantly from one sample to another. To tackle this challenge, this study proposes a novel framework named FedMAC, designed to address multimodality missing under conditions of partial-modality missing in FL. Additionally, to avoid trivial aggregation of multi-modal features, we introduce contrastive-based regularization to impose additional constraints on the latent representation space. The experimental results demonstrate the effectiveness of FedMAC across various client configurations with statistical heterogeneity, outperforming baseline methods by up to 26% in severe missing scenarios, highlighting its potential as a solution for the challenge of partially missing modalities in federated systems.1Complete missing is when one or more modalities are absent in server and clients’ data.2Partial missing is when only parts of one or more modalities are absent in server and clients’ data

Fine-tuning pre-trained models is a popular approach in machine learning for solving complex tasks with moderate data. However, fine-tuning the entire pre-trained model is ineffective in federated data scenarios where local data distributions are diversely skewed. To address this, we explore integrating federated learning with a more effective prompt-tuning method, optimizing for a small set of input prefixes to reprogram the pre-trained model's behavior. Our approach transforms federated learning into a distributed set modeling task, aggregating diverse sets of prompts to globally fine-tune the pre-trained model. We benchmark various baselines based on direct adaptations of existing federated model aggregation techniques and introduce a new probabilistic prompt aggregation method that substantially outperforms these baselines. Our reported results on a variety of computer vision datasets confirm that the proposed method is most effective to combat extreme data heterogeneity in federated learning.

Transformers have increasingly become the de facto method to model sequential data with state-of-the-art performance. Due to its widespread use, being able to estimate and calibrate its modeling uncertainty is important to understand and design robust transformer models. To achieve this, previous works have used Gaussian processes (GPs) to perform uncertainty calibration for the attention units of transformers and attained notable successes. However, such approaches have to confine the transformers to the space of symmetric attention to ensure the necessary symmetric requirement of their GP’s kernel specification, which reduces the representation capacity of the model. To mitigate this restriction, we propose the Correlated Gaussian Process Transformer (CGPT), a new class of transformers whose self-attention units are modeled as cross-covariance between two correlated GPs (CGPs). This allows asymmetries in attention and can enhance the representation capacity of GP-based transformers. We also derive a sparse approximation for CGP to make it scale better. Our empirical studies show that both CGP-based and sparse CGP-based transformers achieve better performance than state-of-the-art GP-based transformers on a variety of benchmark tasks.

Recent studies on pre-trained vision/language models have demonstrated the practical benefit of a new, promising solution-building paradigm in AI where models can be pre-trained on broad data describing a generic task space and then adapted successfully to solve a wide range of downstream tasks, even when training data is severely limited (e.g., in zero- or few-shot learning scenarios). Inspired by such progress, we investigate in this paper the possibilities and challenges of adapting such a paradigm to the context of recommender systems, which is less investigated from the perspective of pre-trained model. In particular, we propose to develop a generic recommender that captures universal interaction patterns by training on generic user-item interaction data extracted from different domains, which can then be fast adapted to improve few-shot learning performance in unseen new domains (with limited data).

Randomized smoothing has recently attracted attentions in the field of adversarial robustness to provide provable robustness guarantees on smoothed neural network classifiers. However, existing works show that vanillarandomized smoothing usually does not provide good robustness performance and often requires (re)training techniques on the base classifier in order to boost the robustness of the resulting smoothed classifier. In this work, we propose two cost-effective approaches to boost the robustness of randomized smoothing while preserving its clean performance. The first approach introduces a new robust training method AdvMacer which combines adversarial training and robustness certification maximization for randomized smoothing. We show that AdvMacer can improve the robustness performance of randomized smoothing classifiers compared to SOTA baselines, while being 3x faster to train than MACER baseline. The second approach introduces a post-processing method EsbRS which greatly improves the robustness certificate based on building model ensembles. Extensive experiments verify the superior performance of our methods on various datasets. Our code is available at https://github.com/Trustworthy-ML-Lab/AdvMacer_and_EsbRS.

Item-to-Item (I2I) recommendation is an important function that suggests replacement or complement options for an item based on their functional similarities or synergies. To capture such item relationships effectively, the recommenders need to understand why subsets of items are co-viewed or co-purchased by the customers. Graph-based models, such as graph neural networks (GNNs), provide a natural framework to combine, ingest and extract valuable insights from such high-order item relationships. However, learning GNNs effectively for I2I requires ingesting a large amount of relational data, which might not always be available, especially in new, emerging market segments. To mitigate this data bottleneck, we postulate that recommendation patterns learned from existing market segments (with private data) could be adapted to build effective warm-start models for emerging ones. To achieve this, we introduce a personalized graph adaptation model based on GNNs to summarize, assemble and adapt recommendation patterns across market segments with heterogeneous customer behaviors into effective local models.

Learning an effective global model on private and decentralized datasets has become an increasingly important challenge of machine learning when applied in practice. Existing distributed learning paradigms, such as Federated Learning, enable this via model aggregation which enforces a strong form of modeling homogeneity and synchronicity across clients. This is however not suitable to many practical scenarios. For example, in distributed sensing, heterogeneous sensors reading data from different views of the same phenomenon would need to use different models for different data modalities. Local learning therefore happens in isolation but inference requires merging the local models to achieve consensus. To enable consensus among local models, we propose a feature fusion approach that extracts local representations from local models and incorporates them into a global representation that improves the prediction performance. Achieving this requires addressing two non-trivial problems. First, we need to learn an alignment between similar feature components which are arbitrarily arranged across clients to enable representation aggregation. Second, we need to learn a consensus graph that captures the high-order interactions between local feature spaces and how to combine them to achieve a better prediction. This paper presents solutions to these problems and demonstrates them in real-world applications on time series data such as power grids and traffic networks.

This paper studies the item-to-item recommendation problem in recommender systems from a new perspective of metric learning via implicit feedback. We develop and investigate a personalizable deep metric model that captures both the internal contents of items and how they were interacted with by users. There are two key challenges in learning such model. First, there is no explicit similarity annotation, which deviates from the assumption of most metric learning methods. Second, these approaches do not account for the fact that items are often represented by multiple sources of meta data and different users use different combinations of these sources to form their own notion of similarity. To address these challenges, we develop a new metric representation embedded as kernel parameters of a probabilistic model. This helps express the correlation between items that a user has interacted with, which can be used to predict user interaction with new items. Our approach hinges on the intuition that similar items induce similar interactions from the same user, thus fitting a metric-parameterized model to predict an implicit feedback signal could indirectly guide it towards finding the most suitable metric for each user. To this end, we also analyze how and when the proposed method is effective from a theoretical lens. Its empirical effectiveness is also demonstrated on several real-world datasets.

We propose a new approach to estimate causal effects from observational data. We leverage multiple data sources which share similar causal mechanisms with the scarce target observations to help infer causal effects in the target domain. The data sources may be available in sequence or some unplanned order. Causal inference can be carried out without prior knowledge of the data discrepancy between the source and target observations. We introduce three levels of knowledge transfer through modelling the outcomes, treatments, and confounders to achieve consistent positive transfer. We incorporate parametric transfer factors to adaptively control the transfer strength, thus achieving a fair and balanced knowledge transfer between the sources and the target. We also empirically show the effectiveness of the proposed method as compared with recent baselines.

We propose a Bayesian framework for estimating causal effects from federated observational data sources. Bayesian causal inference is an important approach to learning the distribution of the causal estimands and understanding the uncertainty of causal effects. Our framework estimates the posterior distributions of the causal effects to compute the higher-order statistics that capture the uncertainty. We integrate local causal effects from different data sources without centralizing them. We then estimate the treatment effects from observational data using a non-parametric reformulation of the classical potential outcomes framework. We model the potential outcomes as a random function distributed by Gaussian processes, with defining parameters that can be efficiently learned from multiple data sources. Our method avoids exchanging raw data among the sources, thus contributing towards privacy-preserving causal learning. The promise of our approach is demonstrated through a set of simulated and real-world examples.

There is a growing interest in applying deep learning (DL) to healthcare, driven by the availability of data with multiple feature channels inrich-dataenvironments (e.g., intensive care units). However, in many other practical situations, we can only access data with much fewer feature channels in apoor-dataenvironments (e.g., at home), which often results in predictive models with poor performance. How can we boost the performance of models learned from suchpoor-dataenvironment by leveraging knowledge extracted from existing models trained usingrich datain a related environment? To address this question, we develop a knowledge infusion framework namedCHEERthat can succinctly summarize suchrich modelinto transferable representations, which can be incorporated into thepoor modelto improve its performance. The infused model is analyzed theoretically and evaluated empirically on several datasets. Our empirical results showed thatCHEERoutperformed baselines by 5.60 to 46.80 percent in terms of the macro-F1 score on multiple physiological datasets.

Deploying deep reinforcement learning in safety-critical settings requires developing algorithms that obey hard constraints during exploration. This paper contributes a first approach toward enforcing formal safety constraints on end-to-end policies with visual inputs. Our approach draws on recent advances in object detection and automated reasoning for hybrid dynamical systems. The approach is evaluated on a novel benchmark that emphasizes the challenge of safely exploring in the presence of hard constraints. Our benchmark draws from several proposed problem sets for safe learning and includes problems that emphasize challenges such as reward signals that are not aligned with safety constraints. On each of these benchmark problems, our algorithm completely avoids unsafe behavior while remaining competitive at optimizing for as much reward as is safe. We characterize safety constraints in terms of a refinement relation on Markov decision processes - rather than directly constraining the reinforcement learning algorithm so that it only takes safe actions, we instead refine the environment so that only safe actions are defined in the environment's transition structure. This has pragmatic system design benefits and, more importantly, provides a clean conceptual setting in which we are able to prove important safety and efficiency properties. These allow us to transform the constrained optimization problem of acting safely in the original environment into an unconstrained optimization in a refined environment.

Production systems operating on a growing domain of analytic services often require generating warm-start solution models for emerging tasks with limited data. One potential approach to address this warm-start challenge is to adopt meta learning to generate a base model that can be adapted to solve unseen tasks with minimal fine-tuning. This however requires the training processes of previous solution models of existing tasks to be synchronized. This is not possible if these models were pre-trained separately on private data owned by different entities and cannot be synchronously re-trained. To accommodate for such scenarios, we develop a new personalized learning framework that synthesizes customized models for unseen tasks via fusion of independently pre-trained models of related tasks. We establish performance guarantee for the proposed framework and demonstrate its effectiveness on both synthetic and real datasets.

This paper presents an active distillation method for a local institution (e.g., hospital) to find the best queries within its given budget to distill an on-server black-box model’s predictive knowledge into a local surrogate with transparent parameterization. This allows local institutions to understand better the predictive reasoning of the black-box model in its own local context or to further customize the distilled knowledge with its private dataset that cannot be centralized and fed into the server model. The proposed method thus addresses several challenges of deploying machine learning (ML) in many industrial settings (e.g., healthcare analytics) with strong proprietary constraints. These include: (1) the opaqueness of the server model’s architecture which prevents local users from understanding its predictive reasoning in their local data contexts; (2) the increasing cost and risk of uploading local data on the cloud for analysis; and (3) the need to customize the server model with private onsite data. We evaluated the proposed method on both benchmark and real-world healthcare data where significant improvements over existing local distillation methods were observed. A theoretical analysis of the proposed method is also presented.

Adverse drug-drug interactions (DDIs) remain a leading cause of morbidity and mortality. Identifying potential DDIs during the drug design process is critical for patients and society. Although several computational models have been proposed for DDI prediction, there are still limitations: (1) specialized design of drug representation for DDI predictions is lacking; (2) predictions are based on limited labelled data and do not generalize well to unseen drugs or DDIs; and (3) models are characterized by a large number of parameters, thus are hard to interpret. In this work, we develop a ChemicAl SubstrucTurE Representation (CASTER) framework that predicts DDIs given chemical structures of drugs. CASTER aims to mitigate these limitations via (1) a sequential pattern mining module rooted in the DDI mechanism to efficiently characterize functional sub-structures of drugs; (2) an auto-encoding module that leverages both labelled and unlabelled chemical structure data to improve predictive accuracy and generalizability; and (3) a dictionary learning module that explains the prediction via a small set of coefficients which measure the relevance of each input sub-structures to the DDI outcome. We evaluated CASTER on two real-world DDI datasets and showed that it performed better than state-of-the-art baselines and provided interpretable predictions.

Model fusion is an emerging study in collective learning where heterogeneous experts with private data and learning architectures need to combine their black-box knowledge for better performance. Existing literature achieves this via a local knowledge distillation scheme that transfuses the predictive patterns of each pre-trained expert onto a white-box imitator model, which can be incorporated efficiently into a global model. This scheme however does not extend to multi-task scenarios where different experts were trained to solve different tasks and only part of their distilled knowledge is relevant to a new task. To address this multi-task challenge, we develop a new fusion paradigm that represents each expert as a distribution over a spectrum of predictive prototypes, which are isolated from task-specific information encoded within the prototype distribution. The task-agnostic prototypes can then be reintegrated to generate a new model that solves a new task encoded with a different prototype distribution. The fusion and adaptation performance of the proposed framework is demonstrated empirically on several real-world benchmark datasets.

This paper presents a novel Collective Online Learning of Gaussian Processes (COOL-GP) framework for enabling a massive number of GP inference agents to simultaneously perform (a) efficient online updates of their GP models using their local streaming data with varying correlation structures and (b) decentralized fusion of their resulting online GP models with different learned hyperparameter settings and inducing inputs. To realize this, we exploit the notion of a common encoding structure to encapsulate the local streaming data gathered by any GP inference agent into summary statistics based on our proposed representation, which is amenable to both an efficient online update via an importance sampling trick as well as multi-agent model fusion via decentralized message passing that can exploit sparse connectivity among agents for improving efficiency and enhance the robustness of our framework against transmission loss. We provide a rigorous theoretical analysis of the approximation loss arising from our proposed representation to achieve efficient online updates and model fusion. Empirical evaluations show that COOL-GP is highly effective in model fusion, resilient to information disparity between agents, robust to transmission loss, and can scale to thousands of agents.

Model fusion is a fundamental problem in collec-tive machine learning (ML) where independentexperts with heterogeneous learning architecturesare required to combine expertise to improve pre-dictive performance. This is particularly chal-lenging in information-sensitive domains whereexperts do not have access to each other’s internalarchitecture and local data. This paper presentsthe first collective model fusion framework formultiple experts with heterogeneous black-box ar-chitectures. The proposed method will enable thisby addressing the key issues of how black-boxexperts interact to understand the predictive be-haviors of one another; how these understandingscan be represented and shared efficiently amongthemselves; and how the shared understandingscan be combined to generate high-quality consen-sus prediction. The performance of the resultingframework is analyzed theoretically and demon-strated empirically on several datasets.

In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited. We develop a Bayesian nonparametric framework for federated learning with neural networks. Each data server is assumed to provide local neural network weights, which are modeled through our framework. We then develop an inference approach that allows us to synthesize a more expressive global network without additional supervision, data pooling and with as few as a single communication round. We then demonstrate the efficacy of our approach on federated learning problems simulated from two popular image classification datasets.

Predictive phenotyping is about accurately predicting what phenotypes will occur in the next clinical visit based on longitudinal Electronic Health Record (EHR) data. While deep learning (DL) models have recently demonstrated strong performance in predictive phenotyping, they require access to a large amount of labeled data, which are expensive to acquire. To address this label-insufficient challenge, we propose a deep dictionary learning framework (DDL) for phenotyping, which utilizes unlabeled data as a complementary source of information to generate a better, more succinct data representation. Our empirical evaluations on multiple EHR datasets demonstrated that DDL outperforms the existing predictive phenotyping methods on a wide variety of clinical tasks that require patient phenotyping. The results also show that unlabeled data can be used to generate better data representation that helps improve DDL's phenotyping performance over existing methods that only uses labeled data.

In many situations, we need to build and deploy separate models in related environments with different data qualities. For example, an environment with strong observation equipments (e.g., intensive care units) often provides high-quality multi-modal data, which are acquired from multiple sensory devices and have rich-feature representations. On the other hand, an environment with poor observation equipment (e.g., at home) only provides low-quality, uni-modal data with poor-feature representations. To deploy a competitive model in a poor-data environment without requiring direct access to multi-modal data acquired from a rich-data environment, this paper develops and presents a knowledge distillation (KD) method (RDPD) to enhance a predictive model trained on poor data using knowledge distilled from a high-complexity model trained on rich, private data. We evaluated RDPD on three real-world datasets and shown that its distilled model consistently outperformed all baselines across all datasets, especially achieving the greatest performance improvement over a model trained only on low-quality data by 24.56% on PR-AUC and 12.21% on ROC-AUC, and over that of a state-of-the-art KD model by 5.91% on PR-AUC and 4.44% on ROC-AUC.

This paper presents a novel variational inference framework for deriving a family of Bayesian sparse Gaussian process regression (SGPR) models whose approximations are variationally optimal with respect to the full-rank GPR model enriched with various corresponding correlation structures of the observation noises. Our variational Bayesian SGPR (VBSGPR) models jointly treat both the distributions of the inducing variables and hyperparameters as variational parameters, which enables the decomposability of the variational lower bound that in turn can be exploited for stochastic optimization. Such a stochastic optimization involves iteratively following the stochastic gradient of the variational lower bound to improve its estimates of the optimal variational distributions of the inducing variables and hyperparameters (and hence the predictive distribution) of our VBSGPR models and is guaranteed to achieve asymptotic convergence to them. We show that the stochastic gradient is an unbiased estimator of the exact gradient and can be computed in constant time per iteration, hence achieving scalability to big data. We empirically evaluate the performance of our proposed framework on two real-world, massive datasets.

We consider the problem of aggregating models learned from sequestered, possibly heterogeneous datasets. Exploiting tools from Bayesian nonparametrics, we develop a general meta-modeling framework that learns shared global latent structures by identifying correspondences among local model parameterizations. Our proposed framework is model-independent and is applicable to a wide range of model types. After verifying our approach on simulated data, we demonstrate its utility in aggregating Gaussian topic models, hierarchical Dirichlet process based hidden Markov models, and sparse Gaussian processes with applications spanning text summarization, motion capture analysis, and temperature forecasting.

This paper presents a novel decentralized high-dimensional Bayesian optimization (DEC-HBO) algorithm that, in contrast to existing HBO algorithms, can exploit the interdependent effects of various input components on the output of the unknown objective function f for boosting the BO performance and still preserve scalability in the number of input dimensions without requiring prior knowledge or the existence of a low (effective) dimension of the input space. To realize this, we propose a sparse yet rich factor graph representation of f to be exploited for designing an acquisition function that can be similarly represented by a sparse factor graph and hence be efficiently optimized in a decentralized manner using distributed message passing. Despite richly characterizing the interdependent effects of the input components on the output of f with a factor graph, DEC-HBO can still guarantee no-regret performance asymptotically. Empirical evaluation on synthetic and real-world experiments (e.g., sparse Gaussian process model with 1811 hyperparameters) shows that DEC-HBO outperforms the state-of-the-art HBO algorithms.

A key challenge in multi-robot and multi-agent systems is generating solutions that are robust to other self-interested or even adversarial parties who actively try to prevent the agents from achieving their goals. The practicality of existing works addressing this challenge is limited to only small-scale synchronous decision-making scenarios or a single agent planning its best response against a single adversary with fixed, procedurally characterized strategies. In contrast this paper considers a more realistic class of problems where a team of asynchronous agents with limited observation and communication capabilities need to compete against multiple strategic adversaries with changing strategies. This problem necessitates agents that can coordinate to detect changes in adversary strategies and plan the best response accordingly. Our approach first optimizes a set of stratagems that represent these best responses. These optimized stratagems are then integrated into a unified policy that can detect and respond when the adversaries change their strategies. The near-optimality of the proposed framework is established theoretically as well as demonstrated empirically in simulation and hardware.

While much research effort has been dedicated to scaling up sparse Gaussian process (GP) models based on inducing variables for big data, little attention is afforded to the other less explored class of low-rank GP approximations that exploit the sparse spectral representation of a GP kernel. This paper presents such an effort to advance the state of the art of sparse spectrum GP models to achieve competitive predictive performance for massive datasets. Our generalized framework of stochastic variational Bayesian sparse spectrum GP (sVBSSGP) models addresses their shortcomings by adopting a Bayesian treatment of the spectral frequencies to avoid overfitting, modeling these frequencies jointly in its variational distribution to enable their interaction a posteriori, and exploiting local data for boosting the predictive performance. However, such structural improvements result in a variational lower bound that is intractable to be optimized. To resolve this, we exploit a variational parameterization trick to make it amenable to stochastic optimization. Interestingly, the resulting stochastic gradient has a linearly decomposable structure that can be exploited to refine our stochastic optimization method to incur constant time per iteration while preserving its property of being an unbiased estimator of the exact gradient of the variational lower bound. Empirical evaluation on real-world datasets shows that sVBSSGP outperforms state-of-the-art stochastic implementations of sparse GP models.

This paper addresses the problem of active learning of a multi-output Gaussian process (MOGP) model representing multiple types of coexisting correlated environmental phenomena. In contrast to existing works, our active learning problem involves selecting not just the most informative sampling locations to be observed but also the types of measurements at each selected location for minimizing the predictive uncertainty (i.e., posterior joint entropy) of a target phenomenon of interest given a sampling budget. Unfortunately, such an entropy criterion scales poorly in the numbers of candidate sampling locations and selected observations when optimized. To resolve this issue, we first exploit a structure common to sparse MOGP models for deriving a novel active learning criterion. Then, we exploit a relaxed form of submodularity property of our new criterion for devising a polynomial-time approximation algorithm that guarantees a constant-factor approximation of that achieved by the optimal set of selected observations. Empirical evaluation on real-world datasets shows that our proposed approach outperforms existing algorithms for active learning of MOGP and single-output GP models.

This paper presents a novel distributed variational inference framework that unifies many parallel sparse Gaussian process regression (SGPR) models for scalable hyperparameter learning with big data. To achieve this, our framework exploits a structure of correlated noise process model that represents the observation noises as a finite realization of a high-order Gaussian Markov random process. By varying the Markov order and covariance function for the noise process model, different variational SGPR models result. This consequently allows the correlation structure of the noise process model to be characterized for which a particular variational SGPR model is optimal. We empirically evaluate the predictive performance and scalability of the distributed variational SGPR models unified by our framework on two real-world datasets.

This paper presents a novel unifying framework of anytime sparse Gaussian process regression (SGPR) models that can produce good predictive performance fast and improve their predictive performance over time. Our proposed unifying framework reverses the variational inference procedure to theoretically construct a non-trivial, concave functional that is maximized at the predictive distribution of any SGPR model of our choice. As a result, a stochastic natural gradient ascent method can be derived that involves iteratively following the stochastic natural gradient of the functional to improve its estimate of the predictive distribution of the chosen SGPR model and is guaranteed to achieve asymptotic convergence to it. Interestingly, we show that if the predictive distribution of the chosen SGPR model satisfies certain decomposability conditions, then the stochastic natural gradient is an unbiased estimator of the exact natural gradient and can be computed in constant time (i.e., independent of data size) at each iteration. We empirically evaluate the trade-off between the predictive performance vs. time efficiency of the anytime SGPR models on two real-world million-sized datasets.