Recent work has suggested post-hoc explainers might be ineffective for detecting spurious correlations in Deep Neural Networks (DNNs). However, we show there are serious weaknesses with the existing evaluation frameworks for this setting. Previously proposed metrics are extremely difficult to interpret and are not directly comparable between explainer methods. To alleviate these constraints, we propose a new evaluation methodology, Explainer Divergence Scores (EDS), grounded in an information theory approach to evaluate explainers. EDS is easy to interpret and naturally comparable across explainers. We use our methodology to compare the detection performance of three different explainers - feature attribution methods, influential examples and concept extraction, on two different image datasets. We discover post-hoc explainers often contain substantial information about a DNN's dependence on spurious artifacts, but in ways often imperceptible to human users. This suggests the need for new techniques that can use this information to better detect a DNN's reliance on spurious correlations.

Recently, powerful Transformer architectures have proven superior in generating high-quality sentences. Nevertheless, these models tend to produce dull high-frequency phrases, severely hurting the diversity and novelty of generated text. In this work, we dig into the intrinsic mechanism of this problem and found that sparser attention values in Transformer could improve diversity. To understand such a phenomenon, we first conduct both empirical and theoretical analysis and then attribute it to representation degeneration caused by the attentive mixture of the hidden states during training. We term this process the Trap of Mediocrity. To escape from such a trap, we introduce a novel attention regularization loss to control the sharpness of the attention distribution, which is transparent to model structures and can be easily implemented within 20 lines of python code. We prove that this method could be mathematically regarded as learning a Bayesian approximation of posterior attention. Experiments show that our method improved the diversity and novelty of the generated text while maintaining comparable quality on a variety of conditional and unconditional generation tasks.

Probing has become a go-to methodology for interpreting and analyzing deep neural models in natural language processing. However, there is still a lack of understanding of the limitations and weaknesses of various types of probes. In this work, we suggest a strategy for input-level intervention on naturalistic sentences. Using our approach, we intervene on the morpho-syntactic features of a sentence, while keeping the rest of the sentence unchanged. Such an intervention allows us to causally probe pre-trained models. We apply our naturalistic causal probing framework to analyze the effects of grammatical gender and number on contextualized representations extracted from three pre-trained models in Spanish: the multilingual versions of BERT, RoBERTa, and GPT-2. Our experiments suggest that naturalistic interventions lead to stable estimates of the causal effects of various linguistic properties. Moreover, our experiments demonstrate the importance of naturalistic causal probing when analyzing pre-trained models.

The availability of large pre-trained models is changing the landscape of Machine Learning research and practice, moving from a training-from-scratch to a fine-tuning paradigm. While in some applications the goal is to "nudge" the pre-trained distribution towards preferred outputs, in others it is to steer it towards a different distribution over the sample space. Two main paradigms have emerged to tackle this challenge: Reward Maximization (RM) and, more recently, Distribution Matching (DM). RM applies standard Reinforcement Learning (RL) techniques, such as Policy Gradients, to gradually increase the reward signal. DM prescribes to first make explicit the target distribution that the model is fine-tuned to approximate. Here we explore the theoretical connections between the two paradigms, and show that methods such as KL-control developed for RM can also be construed as belonging to DM. We further observe that while DM differs from RM, it can suffer from similar training difficulties, such as high gradient variance. We leverage connections between the two paradigms to import the concept of baseline into DM methods. We empirically validate the benefits of adding a baseline on an array of controllable language generation tasks such as constraining topic, sentiment, and gender distributions in texts sampled from a language model. We observe superior performance in terms of constraint satisfaction, stability and sample efficiency.

The recent development of Monkeypox disease among various nations poses a global pandemic threat when the world is still fighting Coronavirus Disease-2019 (COVID-19). At its dawn, the slow and steady transmission of Monkeypox disease among individuals needs to be addressed seriously. Over the years, Deep learning (DL) based disease prediction has demonstrated true potential by providing early, cheap, and affordable diagnosis facilities. Considering this opportunity, we have conducted two studies where we modified and tested six distinct deep learning models-VGG16, InceptionResNetV2, ResNet50, ResNet101, MobileNetV2, and VGG19-using transfer learning approaches. Our preliminary computational results show that the proposed modified InceptionResNetV2 and MobileNetV2 models perform best by achieving an accuracy ranging from 93% to 99%. Our findings are reinforced by recent academic work that demonstrates improved performance in constructing multiple disease diagnosis models using transfer learning approaches. Lastly, we further explain our model prediction using Local Interpretable Model-Agnostic Explanations (LIME), which play an essential role in identifying important features that characterize the onset of Monkeypox disease.

Recently, Flat-LAttice Transformer (FLAT) has achieved great success in Chinese Named Entity Recognition (NER). FLAT performs lexical enhancement by constructing flat lattices, which mitigates the difficulties posed by blurred word boundaries and the lack of word semantics. In FLAT, the positions of starting and ending characters are used to connect a matching word. However, this method is likely to match more words when dealing with long texts, resulting in long input sequences. Therefore, it significantly increases the memory and computational costs of the self-attention module. To deal with this issue, we advocate a novel lexical enhancement method, InterFormer, that effectively reduces the amount of computational and memory costs by constructing non-flat lattices. Furthermore, with InterFormer as the backbone, we implement NFLAT for Chinese NER. NFLAT decouples lexicon fusion and context feature encoding. Compared with FLAT, it reduces unnecessary attention calculations in "word-character" and "word-word". This reduces the memory usage by about 50% and can use more extensive lexicons or higher batches for network training. The experimental results obtained on several well-known benchmarks demonstrate the superiority of the proposed method over the state-of-the-art hybrid (character-word) models.

Over the course of the last two years, we interviewed mayors, city officials, urban planners, academics, and citizens in cities around the world to identify the trends that are making urban living more sustainable, affordable, and human. One theme that emerged was cities' increasingly important role in ensuring the health and well-being of their residents.4 Cities currently represent just 3% of the world's territory but harbor 55% of the world's population. By 2050, it's estimated that 70% of the world's population will live in urban centers.5 At an economic level, cities generate around 80% of the global GDP,6 and are responsible for 80% of energy consumption and more than 70% of carbon emissions and global waste.7

A growing number of Americans are seeing their job security erode in the face of automation and it's undermining their health, according to a new study. The report, conducted by three Ball State University researchers with the school's Center for Business and Economic Research, shows that a 10 percentage point increase in automation risk increases average per-county costs related to medical expenses and lost productivity. "People who live and work in areas where automation is taking place are sickened by the thought of losing their jobs and having no way of providing for themselves or their families," said Michael Hicks, the center's director, who helped conduct the research. Costs associated with an increase in poor or fair health rise by $24 million to $174 million, costs related to increased physical distress rise by $6 million to $40 million and costs linked to mental distress increase by $7 million to $47 million. "This should give us pause about thinking through the benefits and costs of these technologies," Hicks said.

On August 8th, 2021, Spanish police and customs agents intercepted the cargo ship NATALIA on suspicion of narcotics trafficking. The ship was en route from Lebanon via Iskenderun, Turkey, to Lagos, Nigeria, and hidden on board was nearly 20 tons of hashish worth $470 million. That may sound like the opening scene of an action flick, but it's the kind of occurrence that happens more frequently than you might expect on the high seas. Drug smuggling, illegal fishing, and piracy are constant threats. Following a number of recent piracy incidents in the Gulf of Aden, Iran, Russia, and China recently began naval and air drills seeking to counter maritime piracy.

Histological staining is the gold standard for tissue examination in clinical pathology and life-science research, which visualizes the tissue and cellular structures using chromatic dyes or fluorescence labels to aid the microscopic assessment of tissue. However, the current histological staining workflow requires tedious sample preparation steps, specialized laboratory infrastructure, and trained histotechnologists, making it expensive, time-consuming, and not accessible in resource-limited settings. Deep learning techniques created new opportunities to revolutionize staining methods by digitally generating histological stains using trained neural networks, providing rapid, cost-effective, and accurate alternatives to standard chemical staining methods. These techniques, broadly referred to as virtual staining, were extensively explored by multiple research groups and demonstrated to be successful in generating various types of histological stains from label-free microscopic images of unstained samples; similar approaches were also used for transforming images of an already stained tissue sample into another type of stain, performing virtual stain-to-stain transformations. In this Review, we provide a comprehensive overview of the recent research advances in deep learning-enabled virtual histological staining techniques. The basic concepts and the typical workflow of virtual staining are introduced, followed by a discussion of representative works and their technical innovations. We also share our perspectives on the future of this emerging field, aiming to inspire readers from diverse scientific fields to further expand the scope of deep learning-enabled virtual histological staining techniques and their applications.