1,720,964 research outputs found
Explaining Deep Graph Networks via Input Perturbation
No full textDeep graph networks (DGNs) are a family of machine learning models for structured data which are finding heavy application in life sciences (drug repurposing, molecular property predictions) and on social network data (recommendation systems). The privacy and safety-critical nature of such domains motivates the need for developing effective explainability methods for this family of models. So far, progress in this field has been challenged by the combinatorial nature and complexity of graph structures. In this respect, we present a novel local explanation framework specifically tailored to graph data and DGNs. Our approach leverages reinforcement learning to generate meaningful local perturbations of the input graph, whose prediction we seek an interpretation for. These perturbed data points are obtained by optimizing a multiobjective score taking into account similarities both at a structural level as well as at the level of the deep model outputs. By this means, we are able to populate a set of informative neighboring samples for the query graph, which is then used to fit an interpretable model for the predictive behavior of the deep network locally to the query graph prediction. We show the effectiveness of the proposed explainer by a qualitative analysis on two chemistry datasets, TOX21 and Estimated SOLubility (ESOL) and by quantitative results on a benchmark dataset for explanations, CYCLIQ
A Tropical View of Graph Neural Networks
No full textLearning dynamic programming algorithms with Graph Neural Networks (GNNs) is a research direction which is increasingly gaining popularity. Prior work has demonstrated that in order to learn such algorithms, it is necessary to have an ``alignment'' between the neural architecture and the dynamics of the target algorithms, and that GNNs align, in fact, with dynamic programming. Here, we provide a different view of this alignment, studying it through the lens of tropical algebra. We show that GNNs can approximate dynamic programming algorithms up to arbitrary precision, provided that their input and output are appropriately pre- and post-processed
MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks
No full textExplainable AI (XAI) is a research area whose objective is to increase trustworthiness and to enlighten the hidden mechanism of opaque machine learning techniques. This becomes increasingly important in case such models are applied to the chemistry domain, for its potential impact on humans' health, e.g. toxicity analysis in pharmacology. In this paper, we present a novel approach to tackle explainability of deep graph networks in the context of molecule property prediction t asks, named MEG (Molecular Explanation Generator). We generate informative counterfactual explanations for a specific prediction under the form of (valid) compounds with high structural similarity and different predicted properties. Given a trained DGN, we train a reinforcement learning based generator to output counterfactual explanations. At each step, MEG feeds the current candidate counterfactual into the DGN, collects the prediction and uses it to reward the RL agent to guide the exploration. Furthermore, we restrict the action space of the agent in order to only keep actions that maintain the molecule in a valid state. We discuss the results showing how the model can convey non-ML experts with key insights into the learning model focus in the neighbourhood of a molecule
Reasoning Algorithmically in Graph Neural Networks
No full textArtificial intelligence (AI) research has long focused on developing systems capable of advanced reasoning. Early work centered on symbolic approaches with hand-coded knowledge and rules. The rise of machine learning shifted the focus to systems that learn directly from data. Neural Algorithmic Reasoning (NAR) seeks to blend the strengths of both, allowing neural networks to learn and execute rule-based algorithms.
This dissertation explores NAR's theoretical and practical contributions. It examines fundamental concepts, provides an overview of key NAR principles, and investigates the connection between neural networks and tropical algebra. This connection leads to neural architectures provably capable of approximating certain dynamic programming algorithms. The work also demonstrates how these neural reasoners can learn advanced concepts like strong duality in combinatorial optimization.
Extensive empirical studies demonstrate the real-world value of NAR networks. These networks are successfully applied to tasks including planning, classifying large-scale graphs, and learning approximate solutions to difficult combinatorial optimization problems. The research highlights the exciting potential of integrating algorithmic reasoning into machine learning models
Explaining Deep Graph Networks by Structured Counterfactual Generation
No full textDeep Graph Networks are a set of powerful models for solving complex graph-related tasks and have become an interesting research topic that has been consistently growing in popularity in the latest years. However, providing explanations for their predictions is an extremely difficult time-demanding task and is still an open research area. In contrast to the significant amount of work that has been done for the interpretation of vectorial deep learning models, explainability on deep graph networks is still a wide unexplored area.
Based on the current literature, this work tackles the explainability problem for deep graph networks by generating counterfactual explanations in a chemical context. Given an instance and its prediction made by the deep graph network being explained, the generation is formulated as a reinforcement learning problem, in which the generative agent learns to modify the original query graph the least, in order to obtain a substantial change of prediction. Finally, we employ GNNExplainer, a model-agnostic local interpretation method, to produce explanations on both the input graph and its counterfactual explanations, in order to analyse how it behaves in the range of a given input
Explaining Deep Graph Networks with Molecular Counterfactuals
No full textWe present a novel approach to tackle explainability of deep graph networks
in the context of molecule property prediction tasks, named MEG (Molecular
Explanation Generator). We generate informative counterfactual explanations for
a specific prediction under the form of (valid) compounds with high structural
similarity and different predicted properties. We discuss preliminary results
showing how the model can convey non-ML experts with key insights into the
learning model focus in the neighborhood of a molecule
Dual Algorithmic Reasoning
Get PDFNeural Algorithmic Reasoning is an emerging area of machine learning which seeks to infuse algorithmic computation in neural networks, typically by training neural models to approximate steps of classical algorithms. In this context, much of the current work has focused on learning reachability and shortest path graph algorithms, showing that joint learning on similar algorithms is beneficial for generalisation. However, when targeting more complex problems, such similar algorithms become more difficult to find. Here, we propose to learn algorithms by exploiting duality of the underlying algorithmic problem. Many algorithms solve optimisation problems. We demonstrate that simultaneously learning the dual definition of these optimisation problems in algorithmic learning allows for better learning and qualitatively better solutions. Specifically, we exploit the max-flow min-cut theorem to simultaneously learn these two algorithms over synthetically generated graphs, demonstrating the effectiveness of the proposed approach. We then validate the real-world utility of our dual algorithmic reasoner by deploying it on a challenging brain vessel classification task, which likely depends on the vessels' flow properties. We demonstrate a clear performance gain when using our model within such a context, and empirically show that learning the max-flow and min-cut algorithms together is critical for achieving such a result
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
- …
