Visual relationship detection aims to describe the interactions between pairs of objects. Different from individual object learning tasks, the number of possible relationships are much larger, which makes it hard to explore only based on the visual appearance of objects. In addition, due to the limited human effort, the annotations for visual relationships are usually incomplete which increases the difficulty of model training and evaluation. In this paper, we propose a novel framework, called Deep Structural Ranking, for visual relationship detection. To complement the representation ability of visual appearance, we integrate multiple cues for predicting the relationships contained in an input image. Moreover, we design a new ranking objective function by enforcing the annotated relationships to have higher relevance scores. Unlike previous works, our proposed method can both facilitate the co-occurrence of relationships and mitigate the incompleteness problem. Experimental results show that our proposed method outperforms the state-of-the-art on the two widely used datasets. We also demonstrate its superiority in detecting zero-shot relationships.

We present analysis of existing memory models, examining how models represent knowledge, structure memory, learn, make decisions, and predict reaction times. On the basis of this analysis, we propose a theoretical framework that characterizes memory modelling in terms of six key decisions: (1) choice of knowledge representation scheme, (2) choice of data structure, (3) choice of associative architecture, (4) choice of learning rule, (5) choice of time variant process, and (6) choice of response decision criteria. This framework is both descriptive and proscriptive: we intend to both describe the state of the literature and outline what we believe is the most fruitful space of possibilities for the development of future memory models.

Moreover, 2 keynote and 2 tutorial papers were invited. Most regular papers were presented in one of these tracks: Smart Contracts, Blockchain, and Rules, Constraint Handling Rules, Event Driven Architectures and Active Database Systems, Legal Rules and Reasoning, Rule-and Ontology-Based Data Access and Transformation, Rule Induction, and Learning. Following up on previous years, RuleML also hosted the 6th RuleML Doctoral Consortium and the 10th International Rule Challenge, which this year was dedicated to applications of rule-based reasoning, such as Rules in Retail, Rules in Tourism, Rules in Transportation, Rules in Geography, Rules in Location-Based Search, Rules in Insurance Regulation, Rules in Medicine, and Rules in Ecosystem Research. The 10th International Rule Challenge Awards went to Ingmar Dasseville, Laurent Janssens, Gerda Janssens, Jan Vanthienen, and Marc Denecker, for their paper Combining DMN and the Knowledge Base Paradigm for Flexible Decision Enactment, and Jacob Feldman for his paper What-If Analyzer for DMN-based Decision Models. As in previous years, RuleML 2016 was also a place for presentations and face-to-face meetings about rule technology standardizations, which this year Mark Your Calendars!

Matrix completion as a common problem in many application domains has received increasing attention in the machine learning community. Previous matrix completion methods have mostly focused on exploiting the matrix low-rank property to recover missing entries. Recently, it has been noticed that side information that describes the matrix items can help to improve the matrix completion performance. In this paper, we propose a novel matrix completion approach that exploits side information within a principled co-embedding framework. This framework integrates a low-rank matrix factorization model and a label embedding based prediction model together to derive a convex co-embedding formulation with nuclear norm regularization. We develop a fast proximal gradient descent algorithm to solve this co-embedding problem. The effectiveness of the proposed approach is demonstrated on two types of real world application problems.

An important problem with online communities in general, and online rating systems in particular, is uncooperative behavior: lack of user participation, dishonest contributions. This may be due to an incentive structure akin to a Prisoners' Dilemma (PD). We show that introducing an explicit social network to PD games fosters cooperative behavior, and use this insight to design a new aggregation technique for online rating systems. Using a dataset of ratings from Yelp, we show that our aggregation technique outperforms Yelp's proprietary filter, as well as baseline techniques from recommender systems.

This paper focuses on case acquisition strategies in the context of Case-based Learning from Observation (CBLfO). In Learning from Observation (LfO), a system learns behaviors by observing an expert rather than being explicitly programmed. Specifically, we focus on the problem of learning behaviors from experts that reason using internal state information, that is, information that can not be directly observed. The unobservability of this state information means that the behaviors can not be represented by a simple perception-to-action mapping. We propose a new case acquisition strategy called "Similarity-based Chunking", and compare it with existing strategies to address this problem. Additionally, since standard classification accuracy in predicting the expert's actions is known to be a poor measure for evaluating LfO systems, we propose a new evaluation procedure based on two complementary metrics: behavior performance and similarity with the expert.

Traces of user behaviour can be a valuable source of knowledge that can be used during case-based reasoning. This paper presents an approach for analyzing and cleaning user traces. The analysis looks to identify three properties in traces: reasoning with an internal state, non-deterministic behaviour and error. The existence of any of these properties may influence how a system should reason or store knowledge in cases. Initially, each trace is examined to see areas that might contain one of the three properties. Multiple versions of the trace are then generated in order to determine which specific property is present. The analysis is applied to traces generated by observing both a computer and human controller for an obstacle avoidance robot. The results demonstrate that the analysis is able to successfully identify which properties are present and clean many of the errors that exist in the traces.

Robots are becoming increasingly common in home, industrial and medical environments. Their end users may know what they want the robots to do but lack the required technical skills to program them. We present a case-based reasoning approach for training a control module that controls a multi-purpose robotic platform. The control module learns by observing an expert performing a task and does not require any human intervention to program or modify the control module. To avoid requiring the control module to be modified when the robot it controls is repurposed, smart sensors and effectors register with the control module allowing it to dynamically modify the case structure it uses and how those cases are compared. This allows the hardware configuration to be modified, or completely changed, without having to change the control module. We present a case study demonstrating how a robot can be trained using learning by observation and later repurposed with new sensors and then retrained.

Over the past 11 years, this FLAIRS special track program has provided a focal point for the North American case-based reasoning (CBR) community, though it has drawn good international participation as well. Five papers were accepted this year. Ontañón presents seven different case acquisition techniques for CBR systems that use learning from demonstration and performs a comparative evaluation in the context of real-time strategy games. Ontañón and Plaza describe a preliminary formal model of knowledge transfer in case-based inference based on the idea of partial unification. Jalali and Leake present a new approach for ordering questions in conversational CBR systems that takes into account not just their discriminativeness but also the user's ability to answer.

Recent work has demonstrated that several trust and reputation models can be exploited by malicious agents with cyclical behaviour. In each cycle, the malicious agent with cyclical behaviour first regains a high trust value after a number of cooperations and then abuses its gained trust by engaging in a bad transaction. Using a game theoretic formulation, Salehi-Abari and White have proposed the AER model that is resistant to exploitation by cyclical behaviour. Their simulation results imply that FIRE, Regret, and a model due to Yu and Singh, can always be exploited with an appropriate value for the period of cyclical behaviour. Furthermore, their results demonstrate that this is not so for the proposed adaptive scheme. This paper provides a mathematical analysis of the properties of five trust models when faced with cyclical behaviour of malicious agents. Three main results are proven. First, malicious agents can always select a cycle period that allows them to exploit the four models of FIRE, Regret, Probabilistic models, and Yu and Singh indefinitely. Second, malicious agents cannot select a single, finite cycle period that allows them to exploit the AER model forever. Finally, the number of cooperations required to achieve a given trust value increases monotonically with each cycle. In addition to the mathematical analysis, this paper empirically shows how malicious agents can use the theorems proven in this paper to mount efficient attacks on trust models.