Working with a non-stationary stream of data requires for the analysis system to evolve its model (the parameters as well as the structure) over time. In particular, concept drifts can occur, which makes it necessary to forget knowledge that has become obsolete. However, the forgetting is subjected to the stability-plasticity dilemma, that is, increasing forgetting improve reactivity of adapting to the new data while reducing the robustness of the system. Based on a set of inference rules, Evolving Fuzzy Systems-EFS-have proven to be effective in solving the data stream learning problem. However tackling the stability-plasticity dilemma is still an open question. This paper proposes a coherent method to integrate forgetting in Evolving Fuzzy System, based on the recently introduced notion of concept drift anticipation. The forgetting is applied with two methods: an exponential forgetting of the premise part and a deferred directional forgetting of the conclusion part of EFS to preserve the coherence between both parts. The originality of the approach consists in applying the forgetting only in the anticipation module and in keeping the EFS (called principal system) learned without any forgetting. Then, when a drift is detected in the stream, a selection mechanism is proposed to replace the obsolete parameters of the principal system with more suitable parameters of the anticipation module. An evaluation of the proposed methods is carried out on benchmark online datasets, with a comparison with state-of-the-art online classifiers (Learn++.NSE, PENsemble, pclass) as well as with the original system using different forgetting strategies.

In this paper, a novel training paradigm inspired by quantum computation is proposed for deep reinforcement learning (DRL) with experience replay. In contrast to traditional experience replay mechanism in DRL, the proposed deep reinforcement learning with quantum-inspired experience replay (DRL-QER) adaptively chooses experiences from the replay buffer according to the complexity and the replayed times of each experience (also called transition), to achieve a balance between exploration and exploitation. In DRL-QER, transitions are first formulated in quantum representations, and then the preparation operation and the depreciation operation are performed on the transitions. In this progress, the preparation operation reflects the relationship between the temporal difference errors (TD-errors) and the importance of the experiences, while the depreciation operation is taken into account to ensure the diversity of the transitions. The experimental results on Atari 2600 games show that DRL-QER outperforms state-of-the-art algorithms such as DRL-PER and DCRL on most of these games with improved training efficiency, and is also applicable to such memory-based DRL approaches as double network and dueling network.

In this work, we propose a novel Knowledge Graph Embedding (KGE) strategy, called M\"{o}biusE, in which the entities and relations are embedded to the surface of a M\"{o}bius ring. The proposition of such a strategy is inspired by the classic TorusE, in which the addition of two arbitrary elements is subject to a modulus operation. In this sense, TorusE naturally guarantees the critical boundedness of embedding vectors in KGE. However, the nonlinear property of addition operation on Torus ring is uniquely derived by the modulus operation, which in some extent restricts the expressiveness of TorusE. As a further generalization of TorusE, M\"{o}biusE also uses modulus operation to preserve the closeness of addition operation on it, but the coordinates on M\"{o}bius ring interacts with each other in the following way: {\em \color{red} any vector on the surface of a M\"{o}bius ring moves along its parametric trace will goes to the right opposite direction after a cycle}. Hence, M\"{o}biusE assumes much more nonlinear representativeness than that of TorusE, and in turn it generates much more precise embedding results. In our experiments, M\"{o}biusE outperforms TorusE and other classic embedding strategies in several key indicators.

Automatically constructing taxonomy finds many applications in e-commerce and web search. One critical challenge is as data and business scope grow in real applications, new concepts are emerging and needed to be added to the existing taxonomy. Previous approaches focus on the taxonomy expansion, i.e. finding an appropriate hypernym concept from the taxonomy for a new query concept. In this paper, we formulate a new task, "taxonomy completion", by discovering both the hypernym and hyponym concepts for a query. We propose Triplet Matching Network (TMN), to find the appropriate pairs for a given query concept. TMN consists of one primal scorer and multiple auxiliary scorers. These auxiliary scorers capture various fine-grained signals (e.g., query to hypernym or query to hyponym semantics), and the primal scorer makes a holistic prediction on triplet based on the internal feature representations of all auxiliary scorers. Also, an innovative channel-wise gating mechanism that retains task-specific information in concept representations is introduced to further boost model performance. Experiments on four real-world large-scale datasets show that TMN achieves the best performance on both taxonomy completion task and the previous taxonomy expansion task, outperforming existing methods.

Query optimizer is at the heart of the database systems. Cost-based optimizer studied in this paper is adopted in almost all current database systems. A cost-based optimizer introduces a plan enumeration algorithm to find a (sub)plan, and then uses a cost model to obtain the cost of that plan, and selects the plan with the lowest cost. In the cost model, cardinality, the number of tuples through an operator, plays a crucial role. Due to the inaccuracy in cardinality estimation, errors in cost model, and the huge plan space, the optimizer cannot find the optimal execution plan for a complex query in a reasonable time. In this paper, we first deeply study the causes behind the limitations above. Next, we review the techniques used to improve the quality of the three key components in the cost-based optimizer, cardinality estimation, cost model, and plan enumeration. We also provide our insights on the future directions for each of the above aspects.

Entity alignment (EA) is the task of identifying the entities that refer to the same real-world object but are located in different knowledge graphs (KGs). For entities to be aligned, existing EA solutions treat them separately and generate alignment results as ranked lists of entities on the other side. Nevertheless, this decision-making paradigm fails to take into account the interdependence among entities. Although some recent efforts mitigate this issue by imposing the 1-to-1 constraint on the alignment process, they still cannot adequately model the underlying interdependence and the results tend to be sub-optimal. To fill in this gap, in this work, we delve into the dynamics of the decision-making process, and offer a reinforcement learning (RL) based model to align entities collectively. Under the RL framework, we devise the coherence and exclusiveness constraints to characterize the interdependence and restrict collective alignment. Additionally, to generate more precise inputs to the RL framework, we employ representative features to capture different aspects of the similarity between entities in heterogeneous KGs, which are integrated by an adaptive feature fusion strategy. Our proposal is evaluated on both cross-lingual and mono-lingual EA benchmarks and compared against state-of-the-art solutions. The empirical results verify its effectiveness and superiority.

Optimal transport distances have become a classic tool to compare probability distributions and have found many applications in machine learning. Yet, despite recent algorithmic developments, their complexity prevents their direct use on large scale datasets. To overcome this challenge, a common workaround is to compute these distances on minibatches i.e. to average the outcome of several smaller optimal transport problems. We propose in this paper an extended analysis of this practice, which effects were previously studied in restricted cases. We first consider a large variety of Optimal Transport kernels. We notably argue that the minibatch strategy comes with appealing properties such as unbiased estimators, gradients and a concentration bound around the expectation, but also with limits: the minibatch OT is not a distance. To recover some of the lost distance axioms, we introduce a debiased minibatch OT function and study its statistical and optimisation properties. Along with this theoretical analysis, we also conduct empirical experiments on gradient flows, generative adversarial networks (GANs) or color transfer that highlight the practical interest of this strategy.

In many practical applications, such as fraud detection, credit risk modeling or medical decision making, classification models for assigning instances to a predefined set of classes are required to be both precise as well as interpretable. Linear modeling methods such as logistic regression are often adopted, since they offer an acceptable balance between precision and interpretability. Linear methods, however, are not well equipped to handle categorical predictors with high-cardinality or to exploit non-linear relations in the data. As a solution, data preprocessing methods such as weight-of-evidence are typically used for transforming the predictors. The binning procedure that underlies the weight-of-evidence approach, however, has been little researched and typically relies on ad-hoc or expert driven procedures. The objective in this paper, therefore, is to propose a formalized, data-driven and powerful method. To this end, we explore the discretization of continuous variables through the binning of spline functions, which allows for capturing non-linear effects in the predictor variables and yields highly interpretable predictors taking only a small number of discrete values. Moreover, we extend upon the weight-of-evidence approach and propose to estimate the proportions using shrinkage estimators. Together, this offers an improved ability to exploit both non-linear and categorical predictors for achieving increased classification precision, while maintaining interpretability of the resulting model and decreasing the risk of overfitting. We present the results of a series of experiments in a fraud detection setting, which illustrate the effectiveness of the presented approach. We facilitate reproduction of the presented results and adoption of the proposed approaches by providing both the dataset and the code for implementing the experiments and the presented approach.

Existing weighting methods for treatment effect estimation are often built upon the idea of propensity scores or covariate balance. They usually impose strong assumptions on treatment assignment or outcome model to obtain unbiased estimation, such as linearity or specific functional forms, which easily leads to the major drawback of model mis-specification. In this paper, we aim to alleviate these issues by developing a distribution learning-based weighting method. We first learn the true underlying distribution of covariates conditioned on treatment assignment, then leverage the ratio of covariates' density in the treatment group to that of the control group as the weight for estimating treatment effects. Specifically, we propose to approximate the distribution of covariates in both treatment and control groups through invertible transformations via change of variables. To demonstrate the superiority, robustness, and generalizability of our method, we conduct extensive experiments using synthetic and real data. From the experiment results, we find that our method for estimating average treatment effect on treated (ATT) with observational data outperforms several cutting-edge weighting-only benchmarking methods, and it maintains its advantage under a doubly-robust estimation framework that combines weighting with some advanced outcome modeling methods.

Astounding results from transformer models on natural language tasks have intrigued the vision community to study their application to computer vision problems. This has led to exciting progress on a number of tasks while requiring minimal inductive biases in the model design. This survey aims to provide a comprehensive overview of the transformer models in the computer vision discipline and assumes little to no prior background in the field. We start with an introduction to fundamental concepts behind the success of transformer models i.e., self-supervision and self-attention. Transformer architectures leverage self-attention mechanisms to encode long-range dependencies in the input domain which makes them highly expressive. Since they assume minimal prior knowledge about the structure of the problem, self-supervision using pretext tasks is applied to pre-train transformer models on large-scale (unlabelled) datasets. The learned representations are then fine-tuned on the downstream tasks, typically leading to excellent performance due to the generalization and expressivity of encoded features. We cover extensive applications of transformers in vision including popular recognition tasks (e.g., image classification, object detection, action recognition, and segmentation), generative modeling, multi-modal tasks (e.g., visual-question answering and visual reasoning), video processing (e.g., activity recognition, video forecasting), low-level vision (e.g., image super-resolution and colorization) and 3D analysis (e.g., point cloud classification and segmentation). We compare the respective advantages and limitations of popular techniques both in terms of architectural design and their experimental value. Finally, we provide an analysis on open research directions and possible future works.