We present a general framework for association learning, where entities are embedded in a common latent space to express relatedness by geometry -- an approach that underlies the state of the art for link prediction, relation learning, multi-label tagging, relevance retrieval and ranking. Although current approaches rely on local training applied to non-convex formulations, we demonstrate how general convex formulations can be achieved for entity embedding, both for standard multi-linear and prototype-distance models. We investigate an efficient optimization strategy that allows scaling. An experimental evaluation reveals the advantages of global training in different case studies.

We investigate weakly-supervised image parsing, i.e., assigning class labels to image regions by using image-level labels only. Existing studies pay main attention to the formulation of the weakly-supervised learning problem, i.e., how to propagate class labels from images to regions given an affinity graph of regions. Notably, however, the affinity graph of regions, which is generally constructed in relatively simpler settings in existing methods, is of crucial importance to the parsing performance due to the fact that the weakly-supervised parsing problem cannot be solved within a single image, and that the affinity graph enables label propagation among multiple images. In order to embed more semantics into the affinity graph, we propose novel criteria by exploiting the weak supervision information carefully, and develop two graphs: L1 semantic graph and k-NN semantic graph. Experimental results demonstrate that the proposed semantic graphs not only capture more semantic relevance, but also perform significantly better than conventional graphs in image parsing.

A major challenge in artificial intelligence is building intelligent, interactive learning environments that can support students in human-like ways. Analogical reasoning can be a catalyst for conceptual learning, yet very few systems support analogical reasoning as an instructional activity. In my thesis, I plan to demonstrate that an analogy tutor can assist conceptual learning by guiding students through instructional comparisons.

This paper resolves previous problems in the Multi-Strategy architecture for online learning of robotic behaviours. The hybrid method includes a symbolic qualitative planner that constructs an approximate solution to a control problem. The approximate solution provides constraints for a numerical optimisation algorithm, which is used to refine the qualitative plan into an operational policy. Introducing quantitative constraints into the planner gives previously unachievable domain independent reasoning. The method is demonstrated on a multi-tracked robot intended for urban search and rescue.

Multi-label learning concerns learning multiple, overlapping, and correlated classes. In this paper, we adapt a recent structured prediction framework called HC-Search for multi-label prediction problems. One of the main advantages of this framework is that its training is sensitive to the loss function, unlike the other multi-label approaches that either assume a specific loss function or require a manual adaptation to each loss function. We empirically evaluate our instantiation of the HC-Search framework along with many existing multi-label learning algorithms on a variety of benchmarks by employing diverse task loss functions. Our results demonstrate that the performance of existing algorithms tends to be very similar in most cases, and that the HC-Search approach is comparable and often better than all the other algorithms across different loss functions.

This thesis seeks to address word reasoning problems from a semantic standpoint, proposing a uniform approach for generating solutions while also providing human-understandable explanations. Current state of the art solvers of semantic problems rely on traditional machine learning methods. Therefore their results are not easily reusable by algorithms or interpretable by humans. We propose leveraging web-scale knowledge graphs to determine a semantic frame of interpretation. Semantic knowledge graphs are graphs in which nodes represent concepts and the edges represent the relations between them. Our approach has the following advantages: (1) it reduces the space in which the problem is to be solved; (2) sparse and noisy data can be used without relying only on the relations deducible from the data itself; (3) the output of the inference algorithm is supported by an interpretable justification. We demonstrate our approach in two domains: (1) Topic Modeling: We form topics using connectivity in semantic graphs. We use the same topic models for two very different recommendation systems, one designed for high noise interactive applications and the other for large amounts of web data. (2) Analogy Solving: For humans, analogies are a fundamental reasoning pattern, which relies on abstraction and comparative analysis. In order for an analogy to be understood, precise relations have to be identified and mapped. We introduce graph algorithms to assess the analogy strength in contexts derived from the analogy words. We demonstrate our approach by solving standardized test analogy question.

While stable matching problems are widely studied, little work has investigated schemes for effectively eliciting agent preferences using either preference (e.g., comparison) queries for interviews (to form such comparisons); and no work has addressed how to combine both. We develop a new model for representing and assessing agent preferences that accommodates both forms of information and (heuristically) minimizes the number of queries and interviews required to determine a stable matching. Our Refine-then-Interview (RtI) scheme uses coarse preference queries to refine knowledge of agent preferences and relies on interviews only to assess comparisons of relatively “close” options. Empirical results show that RtI compares favorably to a recent pure interview minimization algorithm, and that the number of interviews it requires is generally independent of the size of the market.

Peer Designed Agents (PDAs), computer agents developed by non-experts, is an emerging technology, widely advocated in recent literature for the purpose of replacing people in simulations and investigating human behavior. Its main premise is that strategies programmed into these agents reliably reflect, to some extent, the behavior used by their programmers in real life. In this paper we show that PDA development has an important side effect that has not been addressed to date -- the process that merely attempts to capture one's strategy is also likely to affect the developer's strategy. The phenomenon is demonstrated experimentally, using several performance measures. This result has many implications concerning the appropriate design of PDA-based simulations, and the validity of using PDAs for studying individual decision making. Furthermore, we obtain that PDA development actually improved the developer's strategy according to all performance measures. Therefore, PDA development can be suggested as a means for improving people's problem solving skills.

Maintaining and cultivating student engagement is critical for learning. Understanding factors affecting student engagement will help in designing better courses and improving student retention. The large number of participants in massive open online courses (MOOCs) and data collected from their interaction with the MOOC open up avenues for studying student engagement at scale. In this work, we develop a framework for modeling and understanding student engagement in online courses based on student behavioral cues. Our first contribution is the abstraction of student engagement types using latent representations and using that in a probabilistic model to connect student behavior with course completion. We demonstrate that the latent formulation for engagement helps in predicting student survival across three MOOCs. Next, in order to initiate better instructor interventions, we need to be able to predict student survival early in the course. We demonstrate that we can predict student survival early in the course reliably using the latent model. Finally, we perform a closer quantitative analysis of user interaction with the MOOC and identify student activities that are good indicators for survival at different points in the course.

We report on a project aiming at developing a system that solves a wide range of math problems written in natural language. In the system, formal analysis of natural language semantics is coupled with automated reasoning technologies including computer algebra, using logic as their common language. We have developed a prototype system that accepts as its input a linguistically annotated problem text. Using the prototype system as a reference point, we analyzed real university entrance examination problems from the viewpoint of end-to-end automated reasoning. Further, evaluation on entrance exam mock tests revealed that an optimistic estimate of the system’s performance already matches human averages on a few test sets.