[ { "id": "JT1", "title": "On measuring inconsistency in graph databases with regular path constraints", "authors": "Francesco Parisi, Francesco Parisi", "abstract": "Real-world data are often inconsistent. Although a substantial amount of research has been done on measuring inconsistency, this research concentrated on knowledge bases formalized in propositional logic. Recently, inconsistency measures have been introduced for relational databases. However, nowadays, real-world information is always more frequently represented by graph-based structures which offer a more intuitive conceptualization than relational ones. In this paper, we explore inconsistency measures for graph databases with regular path constraints, a class of integrity constraints based on a well-known navigational language for graph data. In this context, we define several inconsistency measures dealing with specific elements contributing to inconsistency in graph databases. We also define some rationality postulates that are desirable properties for an inconsistency measure for graph databases. We analyze the compliance of each measure with each postulate and find various degrees of satisfaction; in fact, one of the measures satisfies all the postulates. Finally, we investigate the data and combined complexity of the calculation of all the measures as well as the complexity of deciding whether a measure is lower than, equal to, or greater than a given threshold. It turns out that for a majority of the measures these problems are tractable, while for the other different levels of intractability are exhibited.", "location": "Guangzhou", "day": "August 30th", "hour": "09:40", "session": "Constraint Satisfaction and Optimization" }, { "id": "JT2", "title": "Human-AI coevolution", "authors": "Dino Pedreschi, Luca Pappalardo, Emanuele Ferragina, Ricardo Baeza-Yates, Albert-László Barabási, Frank Dignum, Virginia Dignum, Tina Eliassi-Rad, Fosca Giannotti, János Kertész, Alistair Knott, Yannis Ioannidis, Paul Lukowicz, Andrea Passarella, Alex Sandy Pentland, John Shawe-Taylor, Alessandro Vespignani", "abstract": "Human-AI coevolution, defined as a process in which humans and AI algorithms continuously influence each other, increasingly characterises our society, but is understudied in artificial intelligence and complexity science literature. Recommender systems and assistants play a prominent role in human-AI coevolution, as they permeate many facets of daily life and influence human choices through online platforms. The interaction between users and AI results in a potentially endless feedback loop, wherein users' choices generate data to train AI models, which, in turn, shape subsequent user preferences. This human-AI feedback loop has peculiar characteristics compared to traditional human-machine interaction and gives rise to complex and often “unintended” systemic outcomes. This paper introduces human-AI coevolution as the cornerstone for a new field of study at the intersection between AI and complexity science focused on the theoretical, empirical, and mathematical investigation of the human-AI feedback loop. In doing so, we: (i) outline the pros and cons of existing methodologies and highlight shortcomings and potential ways for capturing feedback loop mechanisms; (ii) propose a reflection at the intersection between complexity science, AI and society; (iii) provide real-world examples for different human-AI ecosystems; and (iv) illustrate challenges to the creation of such a field of study, conceptualising them at increasing levels of abstraction, i.e., scientific, legal and socio-political.", "location": "Montreal", "day": "August 21st", "hour": "10:00", "session": "Humans and AI", "poster_positions": "From board n97 to board n101" }, { "id": "JT3", "title": "The Human in Interactive Machine Learning: Analysis and Perspectives for Ambient Intelligence", "authors": "Kevin Delcourt, Sylvie Trouilhet, Jean-Paul Arcangeli, Françoise Adreit", "abstract": "As the vision of Ambient Intelligence (AmI) becomes more feasible, the challenge of designing effective and usable human-machine interaction in this context becomes increasingly important. Interactive Machine Learning (IML) offers a set of techniques and tools to involve end-users in the machine learning process, making it possible to build more trustworthy and adaptable ambient systems. In this paper, our focus is on exploring approaches to effectively integrate and assist human users within ML-based AmI systems. Through a survey of key IML-related contributions, we identify principles for designing effective human-AI interaction in AmI applications. We apply them to the case of Opportunistic Composition, which is an approach to achieve AmI, to enhance collaboration between humans and Artificial Intelligence. Our study highlights the need for user-centered and context-aware design, and provides insights into the challenges and opportunities of integrating IML techniques into AmI systems.", "location": "Montreal", "day": "August 21st", "hour": "11:30", "session": "Humans and AI: Interpretable Models", "poster_positions": "From board n102 to board n106" }, { "id": "JT4", "title": "A Semantic Framework for Neurosymbolic Computation", "authors": "Simon Odense, Artur Garcez", "abstract": "The field of neurosymbolic AI aims to benefit from the combination of neural networks and symbolic systems. A cornerstone of the field is the translation or encoding of symbolic knowledge into neural networks. Although many neurosymbolic methods and approaches have been proposed, and with a large increase in recent years, no common definition of encoding exists that can enable a precise, theoretical comparison of neurosymbolic methods. This paper addresses this problem by introducing a semantic framework for neurosymbolic AI. We start by providing a formal definition of semantic encoding, specifying the components and conditions under which a knowledge-base can be encoded correctly by a neural network. We then show that many neurosymbolic approaches are accounted for by this definition. We provide a number of examples and correspondence proofs applying the proposed framework to the neural encoding of various forms of knowledge representation. Many, at first sight disparate, neurosymbolic methods, are shown to fall within the proposed formalization. This is expected to provide guidance to future neurosymbolic encodings by placing them in the broader context of semantic encodings of entire families of existing neurosymbolic systems. The paper hopes to help initiate a discussion around the provision of a theory for neurosymbolic AI and a semantics for deep learning.", "location": "Montreal", "day": "August 21st", "hour": "11:30", "session": "ML: Neurosymbolic AI", "poster_positions": "From board n22 to board n26" }, { "id": "JT5", "title": "Grounded predictions of teamwork as a one-shot game: A multiagent multi-armed bandits approach", "authors": "Alejandra López de Aberasturi Gómez, Jordi Sabater-Mir, Carles Sierra", "abstract": "Humans possess innate collaborative capacities. However, effective teamwork often remains challenging. This study delves into the feasibility of collaboration within teams of rational, selfinterested agents who engage in teamwork without the obligation to contribute. Drawing from psychological and game theoretical frameworks, we formalise teamwork as a one-shot aggregative game, integrating insights from Steiner’s theory of group productivity. We characterise this novel game’s Nash equilibria and propose a multiagent multi-armed bandit system that learns to converge to approximations of such equilibria. Our research contributes value to the areas of game theory and multiagent systems, paving the way for a better understanding of voluntary collaborative dynamics. We examine how team heterogeneity, task typology, and assessment difficulty inuence agents’ strategies and resulting teamwork outcomes. Finally, we empirically study the behaviour of work teams under incentive systems that defy analytical treatment. Our agents demonstrate human-like behaviour patterns, corroborating ndings from social psychology research.", "location": "Montreal", "day": "August 21st", "hour": "10:00", "session": "MAS: Formal verification, validation and synthesis", "poster_positions": "From board n62 to board n66" }, { "id": "JT6", "title": "Scalable Primal Heuristics Using Graph Neural Networks for Combinatorial Optimization", "authors": "Furkan Cantürk, Taha Varol, Reyhan Aydoğan, Okan Örsan Özener", "abstract": "By examining the patterns of solutions obtained for various instances, one can gain insights into the structure and behavior of combinatorial optimization (CO) problems and develop efficient algorithms for solving them. Machine learning techniques, especially Graph Neural Networks (GNNs), have shown promise in parametrizing and automating this laborious design process. The inductive bias of GNNs allows for learning solutions to mixed-integer programming (MIP) formulations of constrained CO problems with a relational representation of decision variables and constraints. The trained GNNs can be leveraged with primal heuristics to construct high-quality feasible solutions to CO problems quickly. However, current GNN-based end-to-end learning approaches have limitations for scalable training and generalization on larger-scale instances; therefore, they have been mostly evaluated over small-scale instances. Addressing this issue, our study builds on supervised learning of optimal solutions to the downscaled instances of given large-scale CO problems. We introduce several improvements on a recent GNN model for CO to generalize on instances of a larger scale than those used in training. We also propose a two-stage primal heuristic strategy based on uncertainty-quantification to automatically configure how solution search relies on the predicted decision values. Our models can generalize on 16x upscaled instances of commonly benchmarked five CO problems. Unlike the regressive performance of existing GNN-based CO approaches as the scale of problems increases, the CO pipelines using our models offer an incremental performance improvement relative to CPLEX. The proposed uncertainty-based primal heuristics provide 6-75% better optimality gap values and 45-99% better primal gap values for the 16x upscaled instances and brings immense speedup to obtain high-quality solutions. All these gains are achieved through a computationally efficient modeling approach without sacrificing solution quality.", "location": "Montreal", "day": "August 19th", "hour": "11:30", "session": "Constraint Satisfaction and Optimization (1\/3)", "poster_positions": "From board n67 to board n70" }, { "id": "JT7", "title": "A multi-graph representation for event extraction", "authors": "Hui Huang, Yanping Chen, Chuan Lin, Ruizhang Huang, Qinghua Zheng, Yongbin Qin", "abstract": "Event extraction has a trend in identifying event triggers and arguments in a unified framework, which has the advantage of avoiding the cascading failure in pipeline methods. The main problem is that joint models usually assume a one-to-one relationship between event triggers and arguments. It leads to the argument multiplexing problem, in which an argument mention can serve different roles in an event or shared by different events. To address this problem, we propose a multigraph-based event extraction framework. It allows parallel edges between any nodes, which is effective to represent semantic structures of an event. The framework enables the neural network to map a sentence(s) into a structurized semantic representation, which encodes multi-overlapped events. After evaluated on four public datasets, our method achieves the state-of-the-art performance, outperforming all compared models. Analytical experiments show that the multigraph representation is effective to address the argument multiplexing problem and helpful to advance the discriminability of the neural network for event extraction.", "location": "", "day": "", "hour": "", "session": "" }, { "id": "JT8", "title": "NovPhy: A physical reasoning benchmark for open-world AI systems", "authors": "Vimukthini Pinto, Chathura Gamage, Cheng Xue, Peng Zhang, Ekaterina Nikonova, Matthew Stephenson, Jochen Renz", "abstract": "Due to the emergence of AI systems that interact with the physical environment, there is an increased interest in incorporating physical reasoning capabilities into those AI systems. But is it enough to only have physical reasoning capabilities to operate in a real physical environment? In the real world, we constantly face novel situations we have not encountered before. As humans, we are competent at successfully adapting to those situations. Similarly, an agent needs to have the ability to function under the impact of novelties in order to properly operate in an open-world physical environment. To facilitate the development of such AI systems, we propose a new benchmark, NovPhy, that requires an agent to reason about physical scenarios in the presence of novelties and take actions accordingly. The benchmark consists of tasks that require agents to detect and adapt to novelties in physical scenarios. To create tasks in the benchmark, we develop eight novelties representing a diverse novelty space and apply them to five commonly encountered scenarios in a physical environment, related to applying forces and motions such as rolling, falling, and sliding of objects. According to our benchmark design, we evaluate two capabilities of an agent: the performance on a novelty when it is applied to different physical scenarios and the performance on a physical scenario when different novelties are applied to it. We conduct a thorough evaluation with human players, learning agents, and heuristic agents. Our evaluation shows that humans' performance is far beyond the agents' performance. Some agents, even with good normal task performance, perform significantly worse when there is a novelty, and the agents that can adapt to novelties typically adapt slower than humans. We promote the development of intelligent agents capable of performing at the human level or above when operating in open-world physical environments. Benchmark website: https:\/\/github.com\/phy-q\/novphy", "location": "Montreal", "day": "August 20th", "hour": "10:00", "session": "Machine Learning (2\/4)", "poster_positions": "From board n28 to board n31" }, { "id": "JT9", "title": "CureGraph: Contrastive multi-modal graph representation learning for urban living circle health profiling and prediction", "authors": "Jinlin Li, Xiao Zhou", "abstract": "The early detection and prediction of health status decline among the elderly at the neighborhood level are of great significance for urban planning and public health policymaking. While existing studies affirm the connection between living environments and health outcomes, most rely on single data modalities or simplistic feature concatenation of multi-modal information, limiting their ability to comprehensively profile the health-oriented urban environments. To fill this gap, we propose CureGraph, a contrastive multi-modal representation learning framework for urban health prediction that employs graph-based techniques to infer the prevalence of common chronic diseases among the elderly within the urban living circles of each neighborhood. CureGraph leverages rich multi-modal information, including photos and textual reviews of residential areas and their surrounding points of interest, to generate urban neighborhood embeddings. By integrating pre-trained visual and textual encoders with graph modeling techniques, CureGraph captures cross-modal spatial dependencies, offering a comprehensive understanding of urban environments tailored to elderly health considerations. Extensive experiments on real-world datasets demonstrate that CureGraph improves the best baseline by 28% on average in terms of across elderly disease risk prediction tasks. Moreover, the model enables the identification of stage-wise chronic disease progression and supports comparative public health analysis across neighborhoods, offering actionable insights for sustainable urban development and enhanced quality of life. The code is publicly available at https:\/\/github.com\/jinlin2021\/CureGraph.", "location": "Guangzhou", "day": "August 30th", "hour": "09:40", "session": "DM: Mining temporal data" }, { "id": "JT10", "title": "Modular control architecture for safe marine navigation: Reinforcement learning with predictive safety filters", "authors": "Aksel Vaaler, Svein Jostein Husa, Daniel Menges, Thomas Nakken Larsen, Adil Rasheed", "abstract": "Many autonomous systems are safety-critical, making it essential to have a closed-loop control system that satisfies constraints arising from underlying physical limitations and safety aspects in a robust manner. However, this is often challenging to achieve for real-world systems. For example, autonomous ships at sea have nonlinear and uncertain dynamics and are subject to numerous time-varying environmental disturbances such as waves, currents, and wind. There is increasing interest in using machine learning-based approaches to adapt these systems to more complex scenarios, but there are few standard frameworks that guarantee the safety and stability of such systems. Recently, predictive safety filters (PSF) have emerged as a promising method to ensure constraint satisfaction in learning-based control, bypassing the need for explicit constraint handling in the learning algorithms themselves. The safety filter approach leads to a modular separation of the problem, allowing the use of arbitrary control policies in a task-agnostic way. The filter takes in a potentially unsafe control action from the main controller and solves an optimization problem to compute a minimal perturbation of the proposed action that adheres to both physical and safety constraints. In this work, we combine reinforcement learning (RL) with predictive safety filtering in the context of marine navigation and control. The RL agent is trained on path-following and safety adherence across a wide range of randomly generated environments, while the predictive safety filter continuously monitors the agents' proposed control actions and modifies them if necessary. The combined PSF\/RL scheme is implemented on a simulated model of Cybership II, a miniature replica of a typical supply ship. Safety performance and learning rate are evaluated and compared with those of a standard, non-PSF, RL agent. It is demonstrated that the predictive safety filter is able to keep the vessel safe, while not prohibiting the learning rate and performance of the RL agent.", "location": "", "day": "", "hour": "", "session": "" }, { "id": "JT11", "title": "Efficiently Adapt to New Dynamic via Meta-Model", "authors": "Kaixin Huang, Chen Zhao, Chun Yuan", "abstract": "We delve into the realm of offline meta-reinforcement learning (OMRL), a practical paradigm in the field of reinforcement learning that leverages offline data to adapt to new tasks. While prior approaches have not explored the utilization of context-based dynamical models to tackle OMRL problems, our research endeavors to fill this gap. Our investigation uncovers shortcomings in existing context-based methods, primarily related to distribution shifts during offline learning and challenges in establishing stable task representations. To address these issues, we formulate the problem as Hidden-Parameter MDPs and propose a framework for effective model adaptation using meta-models plus latent variables, which is inferred by the transformer-based system recognition module trained in an unsupervised fashion. Through extensive experimentation encompassing diverse simulated robotics and control tasks, we validate the efficacy of our approach and demonstrate its superior generalization ability compared to existing schemes, and explore multiple strategies for obtaining policies with personalized models. Our method achieves a model with reduced prediction error, outperforming previous methods in policy performance, and facilitating efficient adaptation when compared to prior dynamic model generalization methods and OMRL algorithms.", "location": "", "day": "", "hour": "", "session": "" }, { "id": "JT12", "title": "CADS: A Systematic Literature Review on the Challenges of Abstractive Dialogue Summarization", "authors": "Frederic Kirstein, Jan Philip Wahle, Bela Gipp, Terry Ruas", "abstract": "Abstractive dialogue summarization is the task of distilling conversations into informative and concise summaries. Although focused reviews have been conducted on this topic, there is a lack of comprehensive work that details the core challenges of dialogue summarization, unifies the differing understanding of the task, and aligns proposed techniques, datasets, and evaluation metrics with the challenges. This article summarizes the research on Transformer-based abstractive summarization for English dialogues by systematically reviewing 1262 unique research papers published between 2019 and 2024, relying on the Semantic Scholar and DBLP databases. We cover the main challenges present in dialog summarization (i.e., language, structure, comprehension, speaker, salience, and factuality) and link them to corresponding techniques such as graph-based approaches, additional training tasks, and planning strategies, which typically overly rely on BART-based encoder-decoder models. Recent advances in training methods have led to substantial improvements in language-related challenges. However, challenges such as comprehension, factuality, and salience remain difficult and present significant research opportunities. We further investigate how these approaches are typically analyzed, covering the datasets for the subdomains of dialogue (e.g., meeting, customer service, and medical), the established automatic metrics (e.g., ROUGE), and common human evaluation approaches for assigning scores and evaluating annotator agreement. We observe that only a few datasets (i.e., SAMSum, AMI, DialogSum) are widely used. Despite its limitations, the ROUGE metric is the most commonly used, while human evaluation, considered the gold standard, is frequently reported without sufficient detail on the inter-annotator agreement and annotation guidelines. Additionally, we discuss the possible implications of the recently explored large language models and conclude that our described challenge taxonomy remains relevant despite a potential shift in relevance and difficulty.", "location": "Montreal", "day": "August 22nd", "hour": "10:00", "session": "Natural Language Processing (1\/2)", "poster_positions": "From board n5 to board n7" }, { "id": "JT13", "title": "Human Activity Recognition in an Open World", "authors": "Derek Prijatelj, Samuel Grieggs, Jin Huang, Dawei Du, Ameya Shringi, Christopher Funk, Adam Kaufman, Eric Robertson, Walter Scheirer", "abstract": "Managing novelty in perception-based human activity recognition (HAR) is critical in realistic settings to improve task performance over time and ensure solution generalization outside of prior seen samples. Novelty manifests in HAR as unseen samples, activities, objects, environments, and sensor changes, among other ways. Novelty may be task-relevant, such as a new class or new features, or task-irrelevant resulting in nuisance novelty, such as never before seen noise, blur, or distorted video recordings. To perform HAR optimally, algorithmic solutions must be tolerant to nuisance novelty, and learn over time in the face of novelty. This paper 1) formalizes the definition of novelty in HAR building upon the prior definition of novelty in classification tasks, 2) proposes an incremental open world learning (OWL) protocol and applies it to the Kinetics datasets to generate a new benchmark KOWL-718, 3) analyzes the performance of current stateof-the-art HAR models when novelty is introduced over time, 4) provides a containerized and packaged pipeline for reproducing the OWL protocol and for modifying for any future updates to Kinetics. The experimental analysis includes an ablation study of how the different models perform under various conditions as annotated by Kinetics-AVA. The code may be used to analyze different annotations and subsets of the Kinetics datasets in an incremental open world fashion, as well as be extended as further updates to Kinetics are released.", "location": "Montreal", "day": "August 19th", "hour": "11:30", "session": "Computer Vision (1\/3)", "poster_positions": "From board n4 to board n8" }, { "id": "JT14", "title": "Out-of-distribution detection by regaining lost clues", "authors": "Zhilin Zhao, Longbing Cao, Philip S. Yu", "abstract": "Out-of-distribution (OOD) detection identifies samples in the test phase that are drawn from distributions distinct from that of training in-distribution (ID) samples for a trained network. According to the information bottleneck, networks that classify tabular data tend to extract labeling information from features with strong associations to ground-truth labels, discarding less relevant labeling cues. This behavior leads to a predicament in which OOD samples with limited labeling information receive high-confidence predictions, rendering the network incapable of distinguishing between ID and OOD samples. Hence, exploring more labeling information from ID samples, which makes it harder for an OOD sample to obtain high-confidence predictions, can address this over-confidence issue on tabular data. Accordingly, we propose a novel transformer chain (TC), which comprises a sequence of dependent transformers that iteratively regain discarded labeling information and integrate all the labeling information to enhance OOD detection. The generalization bound theoretically reveals that TC can balance ID generalization and OOD detection capabilities. Experimental results demonstrate that TC significantly surpasses state-of-the-art methods for OOD detection in tabular data.", "location": "Guangzhou", "day": "August 30th", "hour": "11:00", "session": "ML: Transfer Learning" }, { "id": "JT15", "title": "Confidence-based Estimators for Predictive Performance in Model Monitoring", "authors": "Juhani Kivimäki, Jakub Białek, Jukka K. Nurminen, Wojtek Kuberski", "abstract": "After a machine learning model has been deployed into production, its predictive performance needs to be monitored. Ideally, such monitoring can be carried out by comparing the model’s predictions against ground truth labels. For this to be possible, the ground truth labels must be available relatively soon after inference. However, there are many use cases where ground truth labels are available only after a significant delay, or in the worst case, not at all. In such cases, directly monitoring the model’s predictive performance is impossible. Recently, novel methods for estimating the predictive performance of a model when ground truth is unavailable have been developed. Many of these methods leverage model confidence or other uncertainty estimates and are experimentally compared against a naive baseline method, namely Average Confidence (AC), which estimates model accuracy as the average of confidence scores for a given set of predictions. However, until now the theoretical properties of the AC method have not been properly explored. In this paper, we bridge this gap by reviewing the AC method and show that under certain general assumptions, it is an unbiased and consistent estimator of model accuracy. We also augment the AC method by deriving valid confidence intervals for the estimates it produces. These contributions elevate AC from an ad-hoc estimator to a principled one, encouraging its use in practice. We complement our theoretical results with empirical experiments, comparing AC against more complex estimators in a monitoring setting under covariate shift. We conduct our experiments using synthetic datasets, which allow for full control over the nature of the shift. Our experiments with binary classifiers show that the AC method is able to beat other estimators in many cases. However, the comparative quality of the different estimators is found to be heavily case-dependent.", "location": "Montreal", "day": "August 20th", "hour": "10:00", "session": "Machine Learning (2\/4)", "poster_positions": "From board n28 to board n31" }, { "id": "JT16", "title": "Credulous acceptance in high-order argumentation frameworks with necessities: An incremental approach", "authors": "Gianvincenzo Alfano, Andrea Cohen, Sebastian Gottifredi, Sergio Greco, Francesco Parisi, Guillermo R. Simari", "abstract": "Argumentation is an important research area in the field of AI. There is a substantial amount of work on different aspects of Dung's abstract Argumentation Framework (AF). Two relevant aspects considered separately so far are: i) extending the framework to account for recursive attacks and supports, and ii) considering dynamics, i.e., AFs evolving over time. In this paper, we jointly deal with these two aspects. We focus on High-Order Argumentation Frameworks with Necessities (HOAFNs) which allow for attack and support relations (interpreted as necessity) not only between arguments but also targeting attacks and supports at any level. We propose an approach for the incremental evaluation of the credulous acceptance problem in HOAFNs, by “incrementally” computing an extension (a set of accepted arguments, attacks and supports), if it exists, containing a given goal element in an updated HOAFN. In particular, we are interested in monitoring the credulous acceptance of a given argument, attack or support (goal) in an evolving HOAFN. Thus, our approach assumes to have a HOAFN Δ, a goal ϱ occurring in Δ, an extension E for Δ containing ϱ, and an update u establishing some changes in the original HOAFN, and uses the extension for first checking whether the update is relevant; for relevant updates, an extension of the updated HOAFN containing the goal is computed by translating the problem to the AF domain and leveraging on AF solvers. We provide formal results for our incremental approach and empirically show that it outperforms the evaluation from scratch of the credulous acceptance problem for an updated HOAFN.", "location": "Montreal", "day": "August 19th", "hour": "11:30", "session": "Knowledge Representation and Reasoning (1\/4)", "poster_positions": "From board n25 to board n29" }, { "id": "JT17", "title": "Explain it as simple as possible, but no simpler – Explanation via model simplification for addressing inferential gap", "authors": "Sarath Sreedharan, Siddharth Srivastava, Subbarao Kambhampati", "abstract": "One of the core challenges of explaining decisions made by modern AI systems is the need to address the potential gap in the inferential capabilities of the system generating the decision and the user trying to make sense of it. This inferential capability gap becomes even more critical when it comes to explaining sequential decisions. While there have been some isolated efforts at developing explanation methods suited for complex decision-making settings, most of these current efforts are limited in scope. In this paper, we introduce a general framework for generating explanations in the presence of inferential capability gaps. A framework that is grounded in the generation of simplified representations of the agent model through the application of a sequence of model simplifying transformations. This framework not only allows us to develop an extremely general explanation generation algorithm, but we see that many of the existing works in this direction could be seen as specific instantiations of our more general method. While the ideas presented in this paper are general enough to be applied to any decision-making framework, we will focus on instantiating the framework in the context of stochastic planning problems. As a part of this instantiation, we will also provide an exhaustive characterization of explanatory queries and an analysis of various classes of applicable transformations. We will evaluate the effectiveness of transformation-based explanations through both synthetic experiments and user studies.", "location": "Montreal", "day": "August 21st", "hour": "10:00", "session": "ML: Explainable\/Interpretable machine learning", "poster_positions": "From board n34 to board n38" } ]