Face recognition models suffer from bias: for example, the probability of a false positive (incorrect face match) strongly depends on sensitive attributes like ethnicity. As a result, these models may disproportionately and negatively impact minority groups when used in law enforcement. In this work, we introduce the Bias Mitigation Calibration (BMC) method, which (i) increases model accuracy (improving the state-of-the-art), (ii) produces fairly-calibrated probabilities, (iii) significantly reduces the gap in the false positive rates, and (iv) does not require knowledge of the sensitive attribute.

Kate Crawford studies the social and political implications of artificial intelligence. She is a research professor of communication and science and technology studies at the University of Southern California and a senior principal researcher at Microsoft Research. Her new book, Atlas of AI, looks at what it takes to make AI and what's at stake as it reshapes our world. You've written a book critical of AI but you work for a company that is among the leaders in its deployment. How do you square that circle?

The tech sphere is showering money recently. For the past two decades, artificial intelligence was encountering significant growth across many domains. But thanks to the Covid-19 pandemic, the adoption was further accelerated. The sudden surge in disruptive technologies' usage has eventually opened the door for investments in artificial intelligence. Investors are also looking to back AI companies that will one day flourish like Apple, Google, Netflix, Amazon, etc. Artificial intelligence is an umbrella term that covers many topics including machine learning, data analytics, data science, natural language processing, etc.

Path-specific effects in mediation analysis provide a useful tool for fairness analysis, which is mostly based on nested counterfactuals. However, the dictum ``no causation without manipulation'' implies that path-specific effects might be induced by certain interventions. This paper proposes a new path intervention inspired by information accounts of causality, and develops the corresponding intervention diagrams and $\pi$-formula. Compared with the interventionist approach of Robins et al.(2020) based on nested counterfactuals, our proposed path intervention method explicitly describes the manipulation in structural causal model with a simple information transferring interpretation, and does not require the non-existence of recanting witness to identify path-specific effects. Hence, it could serve useful communications and theoretical focus for mediation analysis.

Forecasting the particulate matter (PM) concentration in South Korea has become urgently necessary owing to its strong negative impact on human life. In most statistical or machine learning methods, independent and identically distributed data, for example, a Gaussian distribution, are assumed; however, time series such as air pollution and weather data do not meet this assumption. In this study, the maximum correntropy criterion for regression (MCCR) loss is used in an analysis of the statistical characteristics of air pollution and weather data. Rigorous seasonality adjustment of the air pollution and weather data was performed because of their complex seasonality patterns and the heavy-tailed distribution of data even after deseasonalization. The MCCR loss was applied to multiple models including conventional statistical models and state-of-the-art machine learning models. The results show that the MCCR loss is more appropriate than the conventional mean squared error loss for forecasting extreme values.

A new project using artificial intelligence technology could spell a medical breakthrough for people suffering from, or at risk of, coronary artery disease, the single leading cause of death in Australia. The approach being developed by researchers at The University of Western Australia could allow for more accurate diagnosis and faster reporting across all aspects of healthcare, improving the quality and consistency of patient care. The UWA team of experts in cardiac imaging and artificial intelligence was awarded more than $896,606 through a Medical Research Future Fund Frontiers grant to develop a tool to predict the risk of coronary heart disease from heart computed tomography (CT) scans. Coronary artery disease resulting from the build-up of plaque affects more than 1.2 million Australians; however traditional methods using CT imaging of the heart are cumbersome, time-consuming and may have limited accuracy. Led by Professor Girish Dwivedi, the UWA Wesfarmers Chair in Cardiology, the team, including Professor Mohammed Bennamoun, Professor Farid Boussaid, Dr Frank Sanfilippo and Dr Abdul Ihdayhid, together with medical technology company Artrya Ltd, will create an artificial intelligence-based risk assessment tool that will better detect plaque on heart CT scans.

Structural analysis methods (e.g., probing and feature attribution) are increasingly important tools for neural network analysis. We propose a new structural analysis method grounded in a formal theory of \textit{causal abstraction} that provides rich characterizations of model-internal representations and their roles in input/output behavior. In this method, neural representations are aligned with variables in interpretable causal models, and then \textit{interchange interventions} are used to experimentally verify that the neural representations have the causal properties of their aligned variables. We apply this method in a case study to analyze neural models trained on Multiply Quantified Natural Language Inference (MQNLI) corpus, a highly complex NLI dataset that was constructed with a tree-structured natural logic causal model. We discover that a BERT-based model with state-of-the-art performance successfully realizes the approximate causal structure of the natural logic causal model, whereas a simpler baseline model fails to show any such structure, demonstrating that neural representations encode the compositional structure of MQNLI examples.

In real-world applications of influence maximization (IM), the network structure is often unknown. In this case, we may identify the most influential seed nodes by exploring only a part of the underlying network given a small budget for node queries. Motivated by the fact that collecting node metadata is more cost-effective than investigating the relationship between nodes via queried nodes, we develop IM-META, an end-to-end solution to IM in networks with unknown topology by retrieving information from both queries and node metadata. However, using such metadata to aid the IM process is not without risk due to the noisy nature of metadata and uncertainties in connectivity inference. To tackle these challenges, we formulate an IM problem that aims to find two sets, i.e., seed nodes and queried nodes. We propose an effective method that iteratively performs three steps: 1) we learn the relationship between collected metadata and edges via a Siamese neural network model, 2) we select a number of inferred influential edges to construct a reinforced graph used for discovering an optimal seed set, and 3) we identify the next node to query by maximizing the inferred influence spread using a topology-aware ranking strategy. By querying only 5% of nodes, IM-META reaches 93% of the upper bound performance.

Imbalanced classification on graphs is ubiquitous yet challenging in many real-world applications, such as fraudulent node detection. Recently, graph neural networks (GNNs) have shown promising performance on many network analysis tasks. However, most existing GNNs have almost exclusively focused on the balanced networks, and would get unappealing performance on the imbalanced networks. To bridge this gap, in this paper, we present a generative adversarial graph network model, called ImGAGN to address the imbalanced classification problem on graphs. It introduces a novel generator for graph structure data, named GraphGenerator, which can simulate both the minority class nodes' attribute distribution and network topological structure distribution by generating a set of synthetic minority nodes such that the number of nodes in different classes can be balanced. Then a graph convolutional network (GCN) discriminator is trained to discriminate between real nodes and fake (i.e., generated) nodes, and also between minority nodes and majority nodes on the synthetic balanced network. To validate the effectiveness of the proposed method, extensive experiments are conducted on four real-world imbalanced network datasets. Experimental results demonstrate that the proposed method ImGAGN outperforms state-of-the-art algorithms for semi-supervised imbalanced node classification task.

Over-parameterized deep neural networks (DNNs) with sufficient capacity to memorize random noise can achieve excellent generalization performance, challenging the bias-variance trade-off in classical learning theory. Recent studies claimed that DNNs first learn simple patterns and then memorize noise; some other works showed a phenomenon that DNNs have a spectral bias to learn target functions from low to high frequencies during training. However, we show that the monotonicity of the learning bias does not always hold: under the experimental setup of deep double descent, the high-frequency components of DNNs diminish in the late stage of training, leading to the second descent of the test error. Besides, we find that the spectrum of DNNs can be applied to indicating the second descent of the test error, even though it is calculated from the training set only.