Defiant Dems receive 24/7 protection from Capitol Police after Trump accused them of'seditious behavior' and threatened them with execution What Meghan's announcements in her pseudo-Royal court get wrong and why they'speak volumes', revealed by experts Presidential hopeful is dragged into criminal probe... as shock texts emerge: 'It will open Pandora's Box' Multiple cast members speak to Daily Mail and hurl ugly allegations at each other... and reveal co-stars they can't stand Family panic as Britney Spears takes'disturbing' measures... after world was shocked by her unrecognizable new look Everybody Loves Raymond stars now unrecognizable as they reunite for sitcom's 30th anniversary Democratic candidate gives bizarre defense after comments that she'hates' Nashville resurface Private school where teacher'had sex with five students as soon as they turned 16' - and it was LEGAL Kansas City Chiefs coach slams Donald Trump in brutal putdown: 'He has no idea what's going on' Anna Kepner's ex-boyfriend claims stepbrother'climbed on top of her' months before cheerleader was found dead on cruise Bruce Willis' daughter Rumer makes heartbreaking confession about famous father's dementia battle Truth about Ariana Grande and Cynthia Erivo's'secret marriage'... and the depressing reason insiders say their friendship could soon be OVER America's most forgiving wife lists enormous $6m NYC apartment she shares with disgraced CEO caught with woman on Coldplay kisscam Kessler twins who worked with Frank Sinatra and wowed Elvis Presley'paid a lot of money' to die together at 89 A lion's roar is undeniably one of the most fearsome sounds across the entire animal kingdom. Now, it turns out these majestic creatures produce not just one, but two distinct types of roar. That's according to researchers from the University of Exeter, who have identified a brand new type of growl in African lions. The animals - often referred to as the'King of the Jungle' - are best known for their full-throated roar, an immensely powerful vocalization that can be heard up to five miles away. However, using AI, the researchers were able to identify a second type of roar, which they've called the'intermediary roar'.

We propose an empirical measure of the approximate accuracy of feature importance estimates in deep neural networks.

As predictive models are increasingly being deployed in high-stakes decision making (e.g., loan approvals), there has been growing interest in post-hoc techniques

Neural Information Processing Systems http://nips.cc/

As predictive models are increasingly being deployed in high-stakes decision making (e.g., loan approvals), there has been growing interest in post-hoc techniques

In the astronomical observation field, determining the allocation of observation resources of the telescope array and planning follow-up observations for targets of opportunity (ToOs) are indispensable components of astronomical scientific discovery. This problem is computationally challenging, given the online observation setting and the abundance of time-varying factors that can affect whether an observation can be conducted. This paper presents ROARS, a reinforcement learning approach for online astronomical resource-constrained scheduling. To capture the structure of the astronomical observation scheduling, we depict every schedule using a directed acyclic graph (DAG), illustrating the dependency of timing between different observation tasks within the schedule. Deep reinforcement learning is used to learn a policy that can improve the feasible solution by iteratively local rewriting until convergence. It can solve the challenge of obtaining a complete solution directly from scratch in astronomical observation scenarios, due to the high computational complexity resulting from numerous spatial and temporal constraints. A simulation environment is developed based on real-world scenarios for experiments, to evaluate the effectiveness of our proposed scheduling approach. The experimental results show that ROARS surpasses 5 popular heuristics, adapts to various observation scenarios and learns effective strategies with hindsight.

Summary --- This paper proposes to evaluate saliency/importance visual explanations by removing "important" pixels and measuring whether a re-trained classifier can still classify such images correctly. Many explanations fail to remove such class-relevant information, but some ensembling techniques succeed by completely removing objects. Those are said to be better explanations. This paper takes the view that important information is that information which a classifier can use to predict the correct label. As a result, we can measure whether an importance estimate is good by measuring how much performance drops when the important pixels are removed from all images in both train and val sets.

Identifying the relevant input features that have a critical influence on the output results is indispensable for the development of explainable artificial intelligence (XAI). Remove-and-Retrain (ROAR) is a widely accepted approach for assessing the importance of individual pixels by measuring changes in accuracy following their removal and subsequent retraining of the modified dataset. However, we uncover notable limitations in pixel-perturbation strategies. When viewed from a geometric perspective, we discover that these metrics fail to discriminate between differences among feature attribution methods, thereby compromising the reliability of the evaluation. To address this challenge, we introduce an alternative feature-perturbation approach named Geometric Remove-and-Retrain (GOAR). Through a series of experiments with both synthetic and real datasets, we substantiate that GOAR transcends the limitations of pixel-centric metrics.

Knowledge graph reasoning (KGR) -- answering complex logical queries over large knowledge graphs -- represents an important artificial intelligence task, entailing a range of applications (e.g., cyber threat hunting). However, despite its surging popularity, the potential security risks of KGR are largely unexplored, which is concerning, given the increasing use of such capability in security-critical domains. This work represents a solid initial step towards bridging the striking gap. We systematize the security threats to KGR according to the adversary's objectives, knowledge, and attack vectors. Further, we present ROAR, a new class of attacks that instantiate a variety of such threats. Through empirical evaluation in representative use cases (e.g., medical decision support, cyber threat hunting, and commonsense reasoning), we demonstrate that ROAR is highly effective to mislead KGR to suggest pre-defined answers for target queries, yet with negligible impact on non-target ones. Finally, we explore potential countermeasures against ROAR, including filtering of potentially poisoning knowledge and training with adversarially augmented queries, which leads to several promising research directions.

A recourse action aims to explain a particular algorithmic decision by showing one specific way in which the instance could be modified to receive an alternate outcome. Existing recourse generation methods often assume that the machine learning model does not change over time. However, this assumption does not always hold in practice because of data distribution shifts, and in this case, the recourse action may become invalid. To redress this shortcoming, we propose the Distributionally Robust Recourse Action (DiRRAc) framework, which generates a recourse action that has a high probability of being valid under a mixture of model shifts. We formulate the robustified recourse setup as a min-max optimization problem, where the max problem is specified by Gelbrich distance over an ambiguity set around the distribution of model parameters. Then we suggest a projected gradient descent algorithm to find a robust recourse according to the min-max objective. We show that our DiRRAc framework can be extended to hedge against the misspecification of the mixture weights. Numerical experiments with both synthetic and three real-world datasets demonstrate the benefits of our proposed framework over state-of-the-art recourse methods.