Fairness in Graph Convolutional Neural Networks (GCNs) becomes a more and more important concern as GCNs are adopted in many crucial applications. Societal biases against sensitive groups may exist in many real world graphs. GCNs trained on those graphs may be vulnerable to being affected by such biases. In this paper, we adopt the well-known fairness notion of demographic parity and tackle the challenge of training fair and accurate GCNs efficiently. We present an in-depth analysis on how graph structure bias, node attribute bias, and model parameters may affect the demographic parity of GCNs. Our insights lead to FairSample, a framework that jointly mitigates the three types of biases. We employ two intuitive strategies to rectify graph structures. First, we inject edges across nodes that are in different sensitive groups but similar in node features. Second, to enhance model fairness and retain model quality, we develop a learnable neighbor sampling policy using reinforcement learning. To address the bias in node features and model parameters, FairSample is complemented by a regularization objective to optimize fairness.

In many applications, an organization may want to acquire data from many data owners. Data marketplaces allow data owners to produce data assemblage needed by data buyers through coalition. To encourage coalitions to produce data, it is critical to allocate revenue to data owners in a fair manner according to their contributions. Although in literature Shapley fairness and alternatives have been well explored to facilitate revenue allocation in data assemblage, computing exact Shapley value for many data owners and large assembled data sets through coalition remains challenging due to the combinatoric nature of Shapley value. In this paper, we explore the decomposability of utility in data assemblage by formulating the independent utility assumption. We argue that independent utility enjoys many applications. Moreover, we identify interesting properties of independent utility and develop fast computation techniques for exact Shapley value under independent utility. Our experimental results on a series of benchmark data sets show that our new approach not only guarantees the exactness of Shapley value, but also achieves faster computation by orders of magnitudes.

Data is one of the most critical resources in the AI Era. While substantial research has been dedicated to training machine learning models using various types of data, much less efforts have been invested in the exploration of assessing and governing data assets in end-to-end processes of machine learning and data science, that is, the pipeline where data is collected and processed, and then machine learning models are produced, requested, deployed, shared and evolved. To provide a state-of-the-art overall picture of this important and novel area and advocate the related research and development, we present a tutorial addressing two essential problems. First, in the pipeline of machine learning, how can data and machine learning models be priced properly so that contributions from various parties can be assessed and recognized in a fair manner? Second, in the collaboration among many parties in building, distributing and sharing machine learning models, how can data as assets be managed? Accordingly, the first part of our proposal surveys data and model pricing in the pipeline of machine learning, while the second part discusses data asset governance for collaborative artificial intelligence. Each part is self-contained. At the same time, the two parts echo each other and connect a series of interesting and important problems into a dynamic big picture.

The Kolmogorov-Smirnov (KS) test is popularly used in many applications, such as anomaly detection, astronomy, database security and AI systems. One challenge remained untouched is how we can obtain an explanation on why a test set fails the KS test. In this paper, we tackle the problem of producing counterfactual explanations for test data failing the KS test. Concept-wise, we propose the notion of most comprehensible counterfactual explanations, which accommodates both the KS test data and the user domain knowledge in producing explanations. Computation-wise, we develop an efficient algorithm MOCHE (for MOst CompreHensible Explanation) that avoids enumerating and checking an exponential number of subsets of the test set failing the KS test. MOCHE not only guarantees to produce the most comprehensible counterfactual explanations, but also is orders of magnitudes faster than the baselines. Experiment-wise, we present a systematic empirical study on a series of benchmark real datasets to verify the effectiveness, efficiency and scalability of most comprehensible counterfactual explanations and MOCHE.

More and more AI services are provided through APIs on cloud where predictive models are hidden behind APIs. To build trust with users and reduce potential application risk, it is important to interpret how such predictive models hidden behind APIs make their decisions. The biggest challenge of interpreting such predictions is that no access to model parameters or training data is available. Existing works interpret the predictions of a model hidden behind an API by heuristically probing the response of the API with perturbed input instances. However, these methods do not provide any guarantee on the exactness and consistency of their interpretations. In this paper, we propose an elegant closed form solution named OpenAPI to compute exact and consistent interpretations for the family of Piecewise Linear Models (PLM), which includes many popular classification models. The major idea is to first construct a set of overdetermined linear equation systems with a small set of perturbed instances and the predictions made by the model on those instances. Then, we solve the equation systems to identify the decision features that are responsible for the prediction on an input instance. Our extensive experiments clearly demonstrate the exactness and consistency of our method.