Vaishak Belle (University of Edinburgh & Alan Turing Institute) and Ioannis Papantonis (University of Edinburgh) which presents a taxonomy of explainable AI (XAI). XAI is a complex subject and as far as I can see, I have not yet seen a taxonomy of XAI. Model-agnostic Explainability Approaches are designed to be flexible and do not depend on the intrinsic architecture of a model(such as Random forest). These approaches solely relate the inputs to the outputs. Model agnistic approaches could be explanation by simplification, explanation by feature relevance or explanation by visualizations.

Across the world's coronavirus disease 2019 (COVID-19) hot spots, the need to streamline patient diagnosis and management has become more pressing than ever. As one of the main imaging tools, chest X-rays (CXRs) are common, fast, non-invasive, relatively cheap, and potentially bedside to monitor the progression of the disease. This paper describes the first public COVID-19 image data collection as well as a preliminary exploration of possible use cases for the data. This dataset currently contains hundreds of frontal view X-rays and is the largest public resource for COVID-19 image and prognostic data, making it a necessary resource to develop and evaluate tools to aid in the treatment of COVID-19. It was manually aggregated from publication figures as well as various web based repositories into a machine learning (ML) friendly format with accompanying dataloader code. We collected frontal and lateral view imagery and metadata such as the time since first symptoms, intensive care unit (ICU) status, survival status, intubation status, or hospital location.

Temporal relational modeling in video is essential for human action understanding, such as action recognition and action segmentation. Although Graph Convolution Networks (GCNs) have shown promising advantages in relation reasoning on many tasks, it is still a challenge to apply graph convolution networks on long video sequences effectively. The main reason is that large number of nodes (i.e., video frames) makes GCNs hard to capture and model temporal relations in videos. To tackle this problem, in this paper, we introduce an effective GCN module, Dilated Temporal Graph Reasoning Module (DTGRM), designed to model temporal relations and dependencies between video frames at various time spans. In particular, we capture and model temporal relations via constructing multi-level dilated temporal graphs where the nodes represent frames from different moments in video. Moreover, to enhance temporal reasoning ability of the proposed model, an auxiliary self-supervised task is proposed to encourage the dilated temporal graph reasoning module to find and correct wrong temporal relations in videos. Our DTGRM model outperforms state-of-the-art action segmentation models on three challenging datasets: 50Salads, Georgia Tech Egocentric Activities (GTEA), and the Breakfast dataset. The code is available at https://github.com/redwang/DTGRM.

The pre-training models such as BERT have achieved great results in various natural language processing problems. However, a large number of parameters need significant amounts of memory and the consumption of inference time, which makes it difficult to deploy them on edge devices. In this work, we propose a knowledge distillation method LRC-BERT based on contrastive learning to fit the output of the intermediate layer from the angular distance aspect, which is not considered by the existing distillation methods. Furthermore, we introduce a gradient perturbation-based training architecture in the training phase to increase the robustness of LRC-BERT, which is the first attempt in knowledge distillation. Additionally, in order to better capture the distribution characteristics of the intermediate layer, we design a two-stage training method for the total distillation loss. Finally, by verifying 8 datasets on the General Language Understanding Evaluation (GLUE) benchmark, the performance of the proposed LRC-BERT exceeds the existing state-of-the-art methods, which proves the effectiveness of our method.

Most explanation methods in deep learning map importance estimates for a model's prediction back to the original input space. These "visual" explanations are often insufficient, as the model's actual concept remains elusive. Moreover, without insights into the model's semantic concept, it is difficult -- if not impossible -- to intervene on the model's behavior via its explanations, called Explanatory Interactive Learning. Consequently, we propose to intervene on a Neuro-Symbolic scene representation, which allows one to revise the model on the semantic level, e.g. "never focus on the color to make your decision". We compiled a novel confounded visual scene data set, the CLEVR-Hans data set, capturing complex compositions of different objects. The results of our experiments on CLEVR-Hans demonstrate that our semantic explanations, i.e. compositional explanations at a per-object level, can identify confounders that are not identifiable using "visual" explanations only. More importantly, feedback on this semantic level makes it possible to revise the model from focusing on these confounding factors.

Background: Misinformation spread through social media is a growing problem, and the emergence of COVID-19 has caused an explosion in new activity and renewed focus on the resulting threat to public health. Given this increased visibility, in-depth analysis of COVID-19 misinformation spread is critical to understanding the evolution of ideas with potential negative public health impact. Methods: Using a curated data set of COVID-19 tweets (N ~120 million tweets) spanning late January to early May 2020, we applied methods including regular expression filtering, supervised machine learning, sentiment analysis, geospatial analysis, and dynamic topic modeling to trace the spread of misinformation and to characterize novel features of COVID-19 conspiracy theories. Results: Random forest models for four major misinformation topics provided mixed results, with narrowly-defined conspiracy theories achieving F1 scores of 0.804 and 0.857, while more broad theories performed measurably worse, with scores of 0.654 and 0.347. Despite this, analysis using model-labeled data was beneficial for increasing the proportion of data matching misinformation indicators. We were able to identify distinct increases in negative sentiment, theory-specific trends in geospatial spread, and the evolution of conspiracy theory topics and subtopics over time. Conclusions: COVID-19 related conspiracy theories show that history frequently repeats itself, with the same conspiracy theories being recycled for new situations. We use a combination of supervised learning, unsupervised learning, and natural language processing techniques to look at the evolution of theories over the first four months of the COVID-19 outbreak, how these theories intertwine, and to hypothesize on more effective public health messaging to combat misinformation in online spaces.

This time last year, I was in Hong Kong, meeting with human rights activists and documenting the large pro-democracy demonstrations. The police were cracking down on protestors, using excessive force in the streets, and perpetrating abuse behind closed doors. An independent inquiry into police abuses was, and is, crucial - and I proposed just that. On a typical Saturday evening on Nathan Road, thousands of young people would be marching and singing, and many, if not most, would be using their phones to film police using tear gas, batons, and other weapons throughout the night. At the same time, camerapersons both amateur and professional captured footage that circulated around the world via news broadcasts and social media.

In March of 2015, protests broke out at the University of Cape Town in South Africa over the campus statue of British colonialist Cecil Rhodes. Rhodes, a mining magnate who had gifted the land on which the university was built, had committed genocide against Africans and laid the foundations for apartheid. Under the rallying banner of "Rhodes Must Fall," students demanded that the statue be removed. Their protests sparked a global movement to eradicate the colonial legacies that endure in education. The events also provoked Shakir Mohamed, a South African AI researcher at DeepMind, to reflect on what colonial legacies might exist in his research as well.

Open-world learning is a problem where an autonomous agent detects things that it does not know and learns them over time from a non-stationary and never-ending stream of data; in an open-world environment, the training data and objective criteria are never available at once. The agent should grasp new knowledge from learning without forgetting acquired prior knowledge. Researchers proposed a few open-world learning agents for image classification tasks that operate in complex scenarios. However, all prior work on open-world learning has all labeled data to learn the new classes from the stream of images. In scenarios where autonomous agents should respond in near real-time or work in areas with limited communication infrastructure, human labeling of data is not possible. Therefore, supervised open-world learning agents are not scalable solutions for such applications. Herein, we propose a new framework that enables agents to learn new classes from a stream of unlabeled data in an unsupervised manner. Also, we study the robustness and learning speed of such agents with supervised and unsupervised feature representation. We also introduce a new metric for open-world learning without labels. We anticipate our theories and method to be a starting point for developing autonomous true open-world never-ending learning agents.

Peter Hotez deceives New York Times readers about the odds of dying from measles in the US to persuade parents to comply with the CDC's vaccine schedule. On January 9, the New York Times published an article written by Dr. Peter J. Hotez titled "You Are Unvaccinated and Got Sick. His purpose in writing is to persuade parents to vaccinate their children according to the routine schedule recommended by the Centers for Disease Control and Prevention (CDC). To that end, he purports to compare "the dangerous effects of three diseases with the minimal side effects of their corresponding vaccines." "To state it bluntly," Hotez writes, "being unvaccinated can result in illness or death. Vaccines, in contrast, are extremely unlikely to lead to side effects, even minor ones like fainting." He laments that "vaccination rates have fallen", resulting in a resurgence of measles globally. He cites the example of Samoa, where "almost 5,700 measles cases have been recorded since September, resulting in at least 83 deaths. Almost all of those who died were young children." In the US, he writes, "vaccine hesitancy is contributing to" measles outbreaks. Hotez presents data ostensibly to enable parents "to compare the risks of becoming ill with measles . . . to the minute chances of experiencing side effects from their corresponding vaccines." Hotez goes on to assert, "Moreover, new research reveals that, even when patients recover, the measles virus can suppress the immune system, rendering children susceptible to serious infections like pneumonia and the flu." "misinformation spread after an article implying a link between measles vaccinations and autism was published in The Lancet in 1998; it was retracted in 2010 over concerns about the validity of the results and the conduct of the study.