The 2016 Computational Analogy Workshop at ICCBR

Report on the 24th International Conference on Case-Based Reasoning Research and Development (ICCBR-2016)

Computational analogy and case-based reasoning (CBR) are closely related research areas. Both employ prior cases to reason in complex situations with incomplete information. Analogy research often focuses on modeling human cognitive processes, the structural alignment between a base/source and target, and adaptation/abstraction of the analogical source content. While CBR research also deals with alignment and adaptation, the field tends to focus more on retrieval, case-base maintenance, and pragmatic solutions to real-world problems. However, despite their obvious overlap in research goals and approaches, cross communication and collaboration between these areas has been progressively diminishing. CBR and computational analogy researchers stand to benefit greatly from increased exposure to each other's work and greater cross-pollination of ideas. The objective of this workshop is to promote such communication by bringing together researchers from the two areas, to foster new collaborative endeavors, to stimulate new ideas and avoid reinventing old ones.

Pablo Gervás's talk, How Creative Can Reuse Be? pointed up CBR as a favored The main conference program comprised 31 contributions between presentations and posters from 144 authors on technical and applied CBR papers. The origins of the Conference on Case-Based Reasoning The accepted papers were of very high quality, and date from the first European workshop on provided many new insights across a wide range of CBR (EWCBR) held in Kaiserslautern, Germany, in CBR issues. Topics in recent CBR research included in 1993. Since then many European and international the presentations and discussions at ICCBR 2016 conferences on CBR have been held in different parts included novel approaches to similarity and retrieval; of the world. The European conference on CBR advances in adaptation strategies; case generation; representation and knowledge discovery; CBR as a (ECCBR) and the International Conference on CBR cognitive approach to big data; AI with large-scale (ICCBR) were held in alternating years.

Object ranking or "learning to rank" is an important problem in the realm of preference learning. On the basis of training data in the form of a set of rankings of objects represented as feature vectors, the goal is to learn a ranking function that predicts a linear order of any new set of objects. In this paper, we propose a new approach to object ranking based on principles of analogical reasoning. More specifically, our inference pattern is formalized in terms of so-called analogical proportions and can be summarized as follows: Given objects $A,B,C,D$, if object $A$ is known to be preferred to $B$, and $C$ relates to $D$ as $A$ relates to $B$, then $C$ is (supposedly) preferred to $D$. Our method applies this pattern as a main building block and combines it with ideas and techniques from instance-based learning and rank aggregation. Based on first experimental results for data sets from various domains (sports, education, tourism, etc.), we conclude that our approach is highly competitive. It appears to be specifically interesting in situations in which the objects are coming from different subdomains, and which hence require a kind of knowledge transfer.

The estimation of optimal treatment regimes is of considerable interest to precision medicine. In this work, we propose a causal $k$-nearest neighbor method to estimate the optimal treatment regime. The method roots in the framework of causal inference, and estimates the causal treatment effects within the nearest neighborhood. Although the method is simple, it possesses nice theoretical properties. We show that the causal $k$-nearest neighbor regime is universally consistent. That is, the causal $k$-nearest neighbor regime will eventually learn the optimal treatment regime as the sample size increases. We also establish its convergence rate. However, the causal $k$-nearest neighbor regime may suffer from the curse of dimensionality, i.e. performance deteriorates as dimensionality increases. To alleviate this problem, we develop an adaptive causal $k$-nearest neighbor method to perform metric selection and variable selection simultaneously. The performance of the proposed methods is illustrated in simulation studies and in an analysis of a chronic depression clinical trial.

We propose a direct estimation method for R\'{e}nyi and f-divergence measures based on a new graph theoretical interpretation. Suppose that we are given two sample sets $X$ and $Y$, respectively with $N$ and $M$ samples, where $\eta:=M/N$ is a constant value. Considering the $k$-nearest neighbor ($k$-NN) graph of $Y$ in the joint data set $(X,Y)$, we show that the average powered ratio of the number of $X$ points to the number of $Y$ points among all $k$-NN points is proportional to R\'{e}nyi divergence of $X$ and $Y$ densities. A similar method can also be used to estimate f-divergence measures. We derive bias and variance rates, and show that for the class of $\gamma$-H\"{o}lder smooth functions, the estimator achieves the MSE rate of $O(N^{-2\gamma/(\gamma+d)})$. Furthermore, by using a weighted ensemble estimation technique, for density functions with continuous and bounded derivatives of up to the order $d$, and some extra conditions at the support set boundary, we derive an ensemble estimator that achieves the parametric MSE rate of $O(1/N)$. Our estimators are more computationally tractable than other competing estimators, which makes them appealing in many practical applications.

The bone fragments found in the Natalee Holloway case could match the DNA of any one of the four missing people who disappeared in or near Aruba. Holloway went missing during her vacation in Aruba, a Dutch Carribean island off Venezuela, on May 30, 2005. The investigation into Holloway's disappearance new human remains, which her parents hoped belonged to their daughter, but a subsequent forensic analysis proved they were not a match. Holloway's father and his private detective had uncovered human bone fragments in Aruba as part of the investigation that was chronicled on Oxygen's "The Disappearance of Natalee Holloway." One of the four bone samples recovered in Aruba was that of human, and Dr. Jason Kolowski, a forensic scientist, said the human bone fragments belong to a single individual.

Montefiore Institute - Department of Electrical Engineering and Computer Science University of Li ege, L.Wehenkel@ulg.ac.be Abstract--We devise the Unit Commitment Nearest Neighbor (UCNN) algorithm to be used as a proxy for quickly approximating outcomes of short-term decisions, to make tractable hierarchical long-term assessment and planning for large power systems. Experimental results on an updated versions of IEEE-RTS79 and IEEE-RTS96 show high accuracy measured on operational cost, achieved in run-times that are lower in several orders of magnitude than the traditional approach. Unit commitment (UC) is solved daily by Transmission System Operators (TSO) worldwide as part of the market clearing process, to ensure safe operation. Typically, the resulting mathematical problem is either a deterministic or stochastic Mixed Integer-Linear Program (MILP). It is solved accurately for the following day, taking into account all available information on generation and demand, along with exogenous factors such as renewable generation forecast. As intermittent generation capacity is increasing regularly in recent years, more stochasticity is involved in power system operation, affecting the way planning is done not only in the day-ahead time horizon, but in all different time horizons [1], [2], [3]. The complex dependence between the different time-horizons and the high uncertainty in long time-horizons makes long-term planning challenging.

For some reason, Regression and Classification problems end up taking most of the attention in machine learning world. People don't realize the wide variety of machine learning problems which can exist. Previously, I shared my learnings on Genetic algorithms with the community. Continuing on with my search, I intend to cover a topic which has much less widespread but a nagging problem in the data science community – which is multi-label classification. In this article, I will give you an intuitive explanation of what multi-label classification entails, along with illustration of how to solve the problem.