In offline model-based optimisation (MBO) we are interested in using machine learning to design candidates that maximise some measure of desirability through an expensive but real-world scoring process. Offline MBO tries to approximate this expensive scoring function and use that to evaluate generated designs, however evaluation is non-exact because one approximation is being evaluated with another. Instead, we ask ourselves: if we did have the real world scoring function at hand, what cheap-to-compute validation metrics would correlate best with this? Since the real-world scoring function is available for simulated MBO datasets, insights obtained from this can be transferred over to real-world offline MBO tasks where the real-world scoring function is expensive to compute. To address this, we propose a conceptual evaluation framework that is amenable to measuring extrapolation, and apply this to conditional denoising diffusion models. Empirically, we find that two validation metrics -- agreement and Frechet distance -- correlate quite well with the ground truth. When there is high variability in conditional generation, feedback is required in the form of an approximated version of the real-world scoring function. Furthermore, we find that generating high-scoring samples may require heavily weighting the generative model in favour of sample quality, potentially at the cost of sample diversity.
相關內容
The link prediction task aims to predict missing entities or relations in the knowledge graph and is essential for the downstream application. Existing well-known models deal with this task by mainly focusing on representing knowledge graph triplets in the distance space or semantic space. However, they can not fully capture the information of head and tail entities, nor even make good use of hierarchical level information. Thus, in this paper, we propose a novel knowledge graph embedding model for the link prediction task, namely, HIE, which models each triplet (\textit{h}, \textit{r}, \textit{t}) into distance measurement space and semantic measurement space, simultaneously. Moreover, HIE is introduced into hierarchical-aware space to leverage rich hierarchical information of entities and relations for better representation learning. Specifically, we apply distance transformation operation on the head entity in distance space to obtain the tail entity instead of translation-based or rotation-based approaches. Experimental results of HIE on four real-world datasets show that HIE outperforms several existing state-of-the-art knowledge graph embedding methods on the link prediction task and deals with complex relations accurately.
In this work, we examine recently developed methods for Bayesian inference of optimal dynamic treatment regimes (DTRs). DTRs are a set of treatment decision rules aimed at tailoring patient care to patient-specific characteristics, thereby falling within the realm of precision medicine. In this field, researchers seek to tailor therapy with the intention of improving health outcomes; therefore, they are most interested in identifying optimal DTRs. Recent work has developed Bayesian methods for identifying optimal DTRs in a family indexed by $\psi$ via Bayesian dynamic marginal structural models (MSMs) (Rodriguez Duque et al., 2022a); we review the proposed estimation procedure and illustrate its use via the new BayesDTR R package. Although methods in (Rodriguez Duque et al., 2022a) can estimate optimal DTRs well, they may lead to biased estimators when the model for the expected outcome if everyone in a population were to follow a given treatment strategy, known as a value function, is misspecified or when a grid search for the optimum is employed. We describe recent work that uses a Gaussian process ($GP$) prior on the value function as a means to robustly identify optimal DTRs (Rodriguez Duque et al., 2022b). We demonstrate how a $GP$ approach may be implemented with the BayesDTR package and contrast it with other value-search approaches to identifying optimal DTRs. We use data from an HIV therapeutic trial in order to illustrate a standard analysis with these methods, using both the original observed trial data and an additional simulated component to showcase a longitudinal (two-stage DTR) analysis.
In this work we study systems consisting of a group of moving particles. In such systems, often some important parameters are unknown and have to be estimated from observed data. Such parameter estimation problems can often be solved via a Bayesian inference framework. However in many practical problems, only data at the aggregate level is available and as a result the likelihood function is not available, which poses challenge for Bayesian methods. In particular, we consider the situation where the distributions of the particles are observed. We propose a Wasserstein distance based sequential Monte Carlo sampler to solve the problem: the Wasserstein distance is used to measure the similarity between the observed and the simulated particle distributions and the sequential Monte Carlo samplers is used to deal with the sequentially available observations. Two real-world examples are provided to demonstrate the performance of the proposed method.
Since Rendle and Krichene argued that commonly used sampling-based evaluation metrics are "inconsistent" with respect to the global metrics (even in expectation), there have been a few studies on the sampling-based recommender system evaluation. Existing methods try either mapping the sampling-based metrics to their global counterparts or more generally, learning the empirical rank distribution to estimate the top-$K$ metrics. However, despite existing efforts, there is still a lack of rigorous theoretical understanding of the proposed metric estimators, and the basic item sampling also suffers from the "blind spot" issue, i.e., estimation accuracy to recover the top-$K$ metrics when $K$ is small can still be rather substantial. In this paper, we provide an in-depth investigation into these problems and make two innovative contributions. First, we propose a new item-sampling estimator that explicitly optimizes the error with respect to the ground truth, and theoretically highlight its subtle difference against prior work. Second, we propose a new adaptive sampling method which aims to deal with the "blind spot" problem and also demonstrate the expectation-maximization (EM) algorithm can be generalized for such a setting. Our experimental results confirm our statistical analysis and the superiority of the proposed works. This study helps lay the theoretical foundation for adopting item sampling metrics for recommendation evaluation, and provides strong evidence towards making item sampling a powerful and reliable tool for recommendation evaluation.
With the advent of large datasets, offline reinforcement learning (RL) is a promising framework for learning good decision-making policies without the need to interact with the real environment. However, offline RL requires the dataset to be reward-annotated, which presents practical challenges when reward engineering is difficult or when obtaining reward annotations is labor-intensive. In this paper, we introduce Optimal Transport Reward labeling (OTR), an algorithm that assigns rewards to offline trajectories, with a few high-quality demonstrations. OTR's key idea is to use optimal transport to compute an optimal alignment between an unlabeled trajectory in the dataset and an expert demonstration to obtain a similarity measure that can be interpreted as a reward, which can then be used by an offline RL algorithm to learn the policy. OTR is easy to implement and computationally efficient. On D4RL benchmarks, we show that OTR with a single demonstration can consistently match the performance of offline RL with ground-truth rewards.
Informative cluster size (ICS) arises in situations with clustered data where a latent relationship exists between the number of participants in a cluster and the outcome measures. Although this phenomenon has been sporadically reported in statistical literature for nearly two decades now, further exploration is needed in certain statistical methodologies to avoid potentially misleading inferences. For inference about population quantities without covariates, inverse cluster size reweightings are often employed to adjust for ICS. Further, to study the effect of covariates on disease progression described by a multistate model, the pseudo-value regression technique has gained popularity in time-to-event data analysis. We seek to answer the question: "How to apply pseudo-value regression to clustered time-to-event data when cluster size is informative?" ICS adjustment by the reweighting method can be performed in two steps; estimation of marginal functions of the multistate model and fitting the estimating equations based on pseudo-value responses, leading to four possible strategies. We present theoretical arguments and thorough simulation experiments to ascertain the correct strategy for adjusting for ICS. A further extension of our methodology is implemented to include informativeness induced by the intra-cluster group size. We demonstrate the methods in two real-world applications: (i) to determine predictors of tooth survival in a periodontal study, and (ii) to identify indicators of ambulatory recovery in spinal cord injury patients who participated in locomotor-training rehabilitation.
In large-scale systems there are fundamental challenges when centralised techniques are used for task allocation. The number of interactions is limited by resource constraints such as on computation, storage, and network communication. We can increase scalability by implementing the system as a distributed task-allocation system, sharing tasks across many agents. However, this also increases the resource cost of communications and synchronisation, and is difficult to scale. In this paper we present four algorithms to solve these problems. The combination of these algorithms enable each agent to improve their task allocation strategy through reinforcement learning, while changing how much they explore the system in response to how optimal they believe their current strategy is, given their past experience. We focus on distributed agent systems where the agents' behaviours are constrained by resource usage limits, limiting agents to local rather than system-wide knowledge. We evaluate these algorithms in a simulated environment where agents are given a task composed of multiple subtasks that must be allocated to other agents with differing capabilities, to then carry out those tasks. We also simulate real-life system effects such as networking instability. Our solution is shown to solve the task allocation problem to 6.7% of the theoretical optimal within the system configurations considered. It provides 5x better performance recovery over no-knowledge retention approaches when system connectivity is impacted, and is tested against systems up to 100 agents with less than a 9% impact on the algorithms' performance.
Data in Knowledge Graphs often represents part of the current state of the real world. Thus, to stay up-to-date the graph data needs to be updated frequently. To utilize information from Knowledge Graphs, many state-of-the-art machine learning approaches use embedding techniques. These techniques typically compute an embedding, i.e., vector representations of the nodes as input for the main machine learning algorithm. If a graph update occurs later on -- specifically when nodes are added or removed -- the training has to be done all over again. This is undesirable, because of the time it takes and also because downstream models which were trained with these embeddings have to be retrained if they change significantly. In this paper, we investigate embedding updates that do not require full retraining and evaluate them in combination with various embedding models on real dynamic Knowledge Graphs covering multiple use cases. We study approaches that place newly appearing nodes optimally according to local information, but notice that this does not work well. However, we find that if we continue the training of the old embedding, interleaved with epochs during which we only optimize for the added and removed parts, we obtain good results in terms of typical metrics used in link prediction. This performance is obtained much faster than with a complete retraining and hence makes it possible to maintain embeddings for dynamic Knowledge Graphs.
Clustering is one of the most fundamental and wide-spread techniques in exploratory data analysis. Yet, the basic approach to clustering has not really changed: a practitioner hand-picks a task-specific clustering loss to optimize and fit the given data to reveal the underlying cluster structure. Some types of losses---such as k-means, or its non-linear version: kernelized k-means (centroid based), and DBSCAN (density based)---are popular choices due to their good empirical performance on a range of applications. Although every so often the clustering output using these standard losses fails to reveal the underlying structure, and the practitioner has to custom-design their own variation. In this work we take an intrinsically different approach to clustering: rather than fitting a dataset to a specific clustering loss, we train a recurrent model that learns how to cluster. The model uses as training pairs examples of datasets (as input) and its corresponding cluster identities (as output). By providing multiple types of training datasets as inputs, our model has the ability to generalize well on unseen datasets (new clustering tasks). Our experiments reveal that by training on simple synthetically generated datasets or on existing real datasets, we can achieve better clustering performance on unseen real-world datasets when compared with standard benchmark clustering techniques. Our meta clustering model works well even for small datasets where the usual deep learning models tend to perform worse.
Sentiment analysis is a widely studied NLP task where the goal is to determine opinions, emotions, and evaluations of users towards a product, an entity or a service that they are reviewing. One of the biggest challenges for sentiment analysis is that it is highly language dependent. Word embeddings, sentiment lexicons, and even annotated data are language specific. Further, optimizing models for each language is very time consuming and labor intensive especially for recurrent neural network models. From a resource perspective, it is very challenging to collect data for different languages. In this paper, we look for an answer to the following research question: can a sentiment analysis model trained on a language be reused for sentiment analysis in other languages, Russian, Spanish, Turkish, and Dutch, where the data is more limited? Our goal is to build a single model in the language with the largest dataset available for the task, and reuse it for languages that have limited resources. For this purpose, we train a sentiment analysis model using recurrent neural networks with reviews in English. We then translate reviews in other languages and reuse this model to evaluate the sentiments. Experimental results show that our robust approach of single model trained on English reviews statistically significantly outperforms the baselines in several different languages.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191