Explaining predictions made by complex machine learning models helps users understand and accept the predicted outputs with confidence. Instance-based explanation provides such help by identifying relevant instances as evidence to support a model's prediction result. To find relevant instances, several relevance metrics have been proposed. In this study, we ask the following research question: "Do the metrics actually work in practice?" To address this question, we propose two sanity check criteria that valid metrics should pass, and two additional criteria to evaluate the practical utility of the metrics. All criteria are designed in terms of whether the metric can pick up instances of desirable properties that the users expect in practice. Through experiments, we obtained two insights. First, some popular relevance metrics do not pass sanity check criteria. Second, some metrics based on cosine similarity perform better than other metrics, which would be recommended choices in practice. We also analyze why some metrics are successful and why some are not. We expect our insights to help further researches such as developing better explanation methods or designing new evaluation criteria.

Motivated by the problem of optimization of force-field systems in physics using large-scale computer simulations, we consider exploration of a deterministic complex multivariate response surface. The objective is to find input combinations that generate output close to some desired or "target" vector. In spite of reducing the problem to exploration of the input space with respect to a one-dimensional loss function, the search is nontrivial and challenging due to infeasible input combinations, high dimensionalities of the input and output space and multiple "desirable" regions in the input space and the difficulty of emulating the objective function well with a surrogate model. We propose an approach that is based on combining machine learning techniques with smart experimental design ideas to locate multiple good regions in the input space.

This paper proposes an online learning method of Gaussian process state-space model (GP-SSM). GP-SSM is a probabilistic representation learning scheme that represents unknown state transition and/or measurement models as Gaussian processes (GPs). While the majority of prior literature on learning of GP-SSM are focused on processing a given set of time series data, data may arrive and accumulate sequentially over time in most dynamical systems. Storing all such sequential data and updating the model over entire data incur large amount of computational resources in space and time. To overcome this difficulty, we propose a practical method, termed \textit{onlineGPSSM}, that incorporates stochastic variational inference (VI) and online VI with novel formulation. The proposed method mitigates the computational complexity without catastrophic forgetting and also support adaptation to changes in a system and/or a real environments. Furthermore, we present application of onlineGPSSM into the reinforcement learning (RL) of partially observable dynamical systems by integrating onlineGPSSM with Bayesian filtering and trajectory optimization algorithms. Numerical examples are presented to demonstrate applicability of the proposed method.

This work proposes a new challenge set for multimodal classification, focusing on detecting hate speech in multimodal memes. It is constructed such that unimodal models struggle and only multimodal models can succeed: difficult examples ("benign confounders") are added to the dataset to make it hard to rely on unimodal signals. The task requires subtle reasoning, yet is straightforward to evaluate as a binary classification problem. We provide baseline performance numbers for unimodal models, as well as for multimodal models with various degrees of sophistication. We find that state-of-the-art methods perform poorly compared to humans (64.73% vs. 84.7%

Throughout scientific history, overarching theoretical frameworks have allowed researchers to grow beyond personal intuitions and culturally biased theories. They allow to verify and replicate existing findings, and to link is connected results. The notion of self-play, albeit often cited in multiagent Reinforcement Learning, has never been grounded in a formal model. We present a formalized framework, with clearly defined assumptions, which encapsulates the meaning of self-play as abstracted from various existing self-play algorithms. This framework is framed as an approximation to a theoretical solution concept for multiagent training. On a simple environment, we qualitatively measure how well a subset of the captured self-play methods approximate this solution when paired with the famous PPO algorithm. We also provide insights on interpreting quantitative metrics of performance for self-play training. Our results indicate that, throughout training, various self-play definitions exhibit cyclic policy evolutions.

Performing link prediction using knowledge graph embedding (KGE) models is a popular approach for knowledge graph completion. Such link predictions are performed by measuring the likelihood of links in the graph via a transformation function that maps nodes via edges into a vector space. Since the complex structure of the real world is reflected in multi-relational knowledge graphs, the transformation functions need to be able to represent this complexity. However, most of the existing transformation functions in embedding models have been designed in Euclidean geometry and only cover one or two simple transformations. Therefore, they are prone to underfitting and limited in their ability to embed complex graph structures. The area of projective geometry, however, fully covers inversion, reflection, translation, rotation, and homothety transformations. We propose a novel KGE model, which supports those transformations and subsumes other state-of-the-art models. The model has several favorable theoretical properties and outperforms existing approaches on widely used link prediction benchmarks.

Computational intractability has for decades motivated the development of a plethora of methodologies that mainly aimed at a quality-time trade-off. The use of Machine Learning techniques has finally emerged as one of the possible tools to obtain approximate solutions to ${\cal NP}$-hard combinatorial optimization problems. In a recent article, Dai et al. introduced a method for computing such approximate solutions for instances of the Vertex Cover problem. In this paper we consider the effectiveness of selecting a proper training strategy by considering special problem instances called "obstructions" that we believe carry some intrinsic properties of the problem itself. Capitalizing on the recent work of Dai et al. on the Vertex Cover problem, and using the same case study as well as 19 other problem instances, we show the utility of using obstructions for training neural networks. Experiments show that training with obstructions results in a huge reduction in number of iterations needed for convergence, thus gaining a substantial reduction in the time needed for training the model.

This paper targets the automated extraction of components of argumentative information and their relations from natural language text. Moreover, we address a current lack of systems to provide complete argumentative structure from arbitrary natural language text for general usage. We present an argument mining pipeline as a universally applicable approach for transforming German and English language texts to graph-based argument representations. We also introduce new methods for evaluating the results based on existing benchmark argument structures. Our results show that the generated argument graphs can be beneficial to detect new connections between different statements of an argumentative text. Our pipeline implementation is publicly available on GitHub.

With the development of Internet of Things (IoT), IoT intelligence becomes emerging technology. "Curse of Dimensionality" is the barrier of data fusion in edge devices for the success of IoT intelligence. A Linguistic Attribute Hierarchy (LAH), embedded with Linguistic Decision Trees (LDTs), can represent a new attribute deep learning. In contrast to the conventional deep learning, an LAH could overcome the shortcoming of missing interpretation by providing transparent information propagation through the rules, produced by LDTs in the LAH. Similar to the conventional deep learning, the computing complexity of optimising LAHs blocks the applications of LAHs. In this paper, we propose a heuristic approach to constructing an LAH, embedded with LDTs for decision making or classification by utilising the distance correlations between attributes and between attributes and the goal variable. The set of attributes is divided to some attribute clusters, and then they are heuristically organised to form a linguistic attribute hierarchy. The proposed approach was validated with some benchmark decision making or classification problems from the UCI machine learning repository. The experimental results show that the proposed self-organisation algorithm can construct an effective and efficient linguistic attribute hierarchy. Such a self-organised linguistic attribute hierarchy embedded with LDTs can not only efficiently tackle "curse of dimensionality" in a single LDT for data fusion with massive attributes, but also achieve better or comparable performance on decision making or classification, compared to the single LDT for the problem to be solved. The self-organisation algorithm is much efficient than the Genetic Algorithm in Wrapper for the optimisation of LAHs. This makes it feasible to embed the self-organisation algorithm in edge devices for IoT intelligence.

Due to the growing deployment of classification algorithms in various social contexts, developing methods that are fair with respect to protected attributes such as gender or race is an important problem. However, the information about protected attributes in datasets may be inaccurate due to either issues with data collection or when the protected attributes used are themselves predicted by algorithms. Such inaccuracies can prevent existing fair classification algorithms from achieving desired fairness guarantees. Motivated by this, we study fair classification problems when the protected attributes in the data may be ``noisy''. In particular, we consider a noise model where any protected type may be flipped to another with some fixed probability. We propose a ``denoised'' fair optimization formulation that can incorporate very general fairness goals via a set of constraints, mitigates the effects of such noise perturbations, and comes with provable guarantees. Empirically, we show that our framework can lead to near-perfect statistical parity with only a slight loss in accuracy for significant noise levels.