Multi-view datasets offer diverse forms of data that can enhance prediction models by providing complementary information. However, the use of multi-view data leads to an increase in high-dimensional data, which poses significant challenges for the prediction models that can lead to poor generalization. Therefore, relevant feature selection from multi-view datasets is important as it not only addresses the poor generalization but also enhances the interpretability of the models. Despite the success of traditional feature selection methods, they have limitations in leveraging intrinsic information across modalities, lacking generalizability, and being tailored to specific classification tasks. We propose a novel genetic algorithm strategy to overcome these limitations of traditional feature selection methods for multi-view data. Our proposed approach, called the multi-view multi-objective feature selection genetic algorithm (MMFS-GA), simultaneously selects the optimal subset of features within a view and between views under a unified framework. The MMFS-GA framework demonstrates superior performance and interpretability for feature selection on multi-view datasets in both binary and multiclass classification tasks. The results of our evaluations on three benchmark datasets, including synthetic and real data, show improvement over the best baseline methods. This work provides a promising solution for multi-view feature selection and opens up new possibilities for further research in multi-view datasets.

Much of the recent work developing formal methods techniques to specify or learn the behavior of autonomous systems is predicated on a belief that formal specifications are interpretable and useful for humans when checking systems. Though frequently asserted, this assumption is rarely tested. We performed a human experiment (N = 62) with a mix of people who were and were not familiar with formal methods beforehand, asking them to validate whether a set of signal temporal logic (STL) constraints would keep an agent out of harm and allow it to complete a task in a gridworld capture-the-flag setting. Validation accuracy was $45\% \pm 20\%$ (mean $\pm$ standard deviation). The ground-truth validity of a specification, subjects' familiarity with formal methods, and subjects' level of education were found to be significant factors in determining validation correctness. Participants exhibited an affirmation bias, causing significantly increased accuracy on valid specifications, but significantly decreased accuracy on invalid specifications. Additionally, participants, particularly those familiar with formal methods, tended to be overconfident in their answers, and be similarly confident regardless of actual correctness. Our data do not support the belief that formal specifications are inherently human-interpretable to a meaningful degree for system validation. We recommend ergonomic improvements to data presentation and validation training, which should be tested before claims of interpretability make their way back into the formal methods literature.

During crisis situations, social media allows people to quickly share information, including messages requesting help. This can be valuable to emergency responders, who need to categorise and prioritise these messages based on the type of assistance being requested. However, the high volume of messages makes it difficult to filter and prioritise them without the use of computational techniques. Fully supervised filtering techniques for crisis message categorisation typically require a large amount of annotated training data, but this can be difficult to obtain during an ongoing crisis and is expensive in terms of time and labour to create. This thesis focuses on addressing the challenge of low data availability when categorising crisis messages for emergency response. It first presents domain adaptation as a solution for this problem, which involves learning a categorisation model from annotated data from past crisis events (source domain) and adapting it to categorise messages from an ongoing crisis event (target domain). In many-to-many adaptation, where the model is trained on multiple past events and adapted to multiple ongoing events, a multi-task learning approach is proposed using pre-trained language models. This approach outperforms baselines and an ensemble approach further improves performance...

The reliability of current autonomous driving systems is often jeopardized in situations when the vehicle's field-of-view is limited by nearby occluding objects. To mitigate this problem, vehicle-to-vehicle communication to share sensor information among multiple autonomous driving vehicles has been proposed. However, to enable timely processing and use of shared sensor data, it is necessary to constrain communication bandwidth, and prior work has done so by restricting the number of other cooperative vehicles and randomly selecting the subset of vehicles to exchange information with from all those that are within communication range. Although simple and cost effective from a communication perspective, this selection approach suffers from its susceptibility to missing those vehicles that possess the perception information most critical to navigation planning. Inspired by recent multi-agent path finding research, we propose a novel selective communication algorithm for cooperative perception to address this shortcoming. Implemented with a lightweight perception network and a previously developed control network, our algorithm is shown to produce higher success rates than a random selection approach on previously studied safety-critical driving scenario simulations, with minimal additional communication overhead.

Event argument extraction (EAE) identifies event arguments and their specific roles for a given event. Recent advancement in generation-based EAE models has shown great performance and generalizability over classification-based models. However, existing generation-based EAE models mostly focus on problem re-formulation and prompt design, without incorporating additional information that has been shown to be effective for classification-based models, such as the abstract meaning representation (AMR) of the input passages. Incorporating such information into generation-based models is challenging due to the heterogeneous nature of the natural language form prevalently used in generation-based models and the structured form of AMRs. In this work, we study strategies to incorporate AMR into generation-based EAE models. We propose AMPERE, which generates AMR-aware prefixes for every layer of the generation model. Thus, the prefix introduces AMR information to the generation-based EAE model and then improves the generation. We also introduce an adjusted copy mechanism to AMPERE to help overcome potential noises brought by the AMR graph. Comprehensive experiments and analyses on ACE2005 and ERE datasets show that AMPERE can get 4% - 10% absolute F1 score improvements with reduced training data and it is in general powerful across different training sizes.

Decentralized Finance (DeFi) is a system of financial products and services built and delivered through smart contracts on various blockchains. In the past year, DeFi has gained popularity and market capitalization. However, it has also been connected to crime, in particular, various types of securities violations. The lack of Know Your Customer requirements in DeFi poses challenges to governments trying to mitigate potential offending in this space. This study aims to uncover whether this problem is suited to a machine learning approach, namely, whether we can identify DeFi projects potentially engaging in securities violations based on their tokens' smart contract code. We adapt prior work on detecting specific types of securities violations across Ethereum, building classifiers based on features extracted from DeFi projects' tokens' smart contract code (specifically, opcode-based features). Our final model is a random forest model that achieves an 80\% F-1 score against a baseline of 50\%. Notably, we further explore the code-based features that are most important to our model's performance in more detail, analyzing tokens' Solidity code and conducting cosine similarity analyses. We find that one element of the code our opcode-based features may be capturing is the implementation of the SafeMath library, though this does not account for the entirety of our features. Another contribution of our study is a new data set, comprised of (a) a verified ground truth data set for tokens involved in securities violations and (b) a set of legitimate tokens from a reputable DeFi aggregator. This paper further discusses the potential use of a model like ours by prosecutors in enforcement efforts and connects it to the wider legal context.

Sen. Ted Cruz, R-Texas, argues why President Biden doesn't want to take a debt default off the table. Inflation continues to be the top concern for voters as large numbers rate both the nation's economy and their individual finances negatively. That's according to a new Fox News survey that contains little good news for an incumbent president running for re-election. Some 83% of voters say the economy is in only fair or poor shape. That's more negative by 5 points compared to last month (78%) and worse by 14 points compared to President Biden's 100-day mark in April 2021 (69%).

This week, Emily Bazelon, John Dickerson, and David Plotz discuss the imminent X Date when the United States hits the debt ceiling and could default; the presidential campaign announcements of Ron DeSantis and Tim Scott; and the possibilities of regulating artificial intelligence. Here are some notes and references from this week's show: Ezra Klein for The New York Times: "Liberals Are Persuading Themselves of a Debt Ceiling Plan That Won't Work" John Dickerson for CBS News Prime Time: "Former Google executive speaks out against AI" Emily Conover for Science News Explores: "A new supercomputer just set a world record for speed" Here are this week's chatters: John: Oliver Whang for The New York Times: "A Paralyzed Man Can Walk Naturally Again With Brain and Spine Implants"; Henri Lorach, et al., for Nature: "Walking naturally after spinal cord injury using a brain-spine interface" David: NatureSweet Twilights tomato; join David at a live taping of City Cast DC on Saturday June 3 at 1 p.m., Right Proper Brewing's Brookland production house and tasting room. For this week's Slate Plus bonus segment, David, Emily, and John discuss Harlan Crow's collections and Graeme Wood's article in The Atlantic: "Inside the Garden of Evil." Tickets are on sale now.

Deep fake videos of President Joe Biden and Republican frontrunner Donald Trump highlight how the 2024 presidential race could be the first serious test of American democracy's resilience to artificial intelligence. Videos of Biden dressed as trans star Dylan Mulvaney promoting Bud Light and Trump teaching tax evasion inside a quiet Albuquerque nail salon show that not even the nation's most powerful figures are safe from AI identity theft. Experts say that while today it is relatively easy to spot these fakes, it will be impossible in the coming years because technology is advancing at such a fast pace. There have already been glimpses of the real-world harms of AI. Just earlier this week, an AI-crafted image of black smoke billowing out of the Pentagon sent shockwaves through the stock market before media factcheckers could finally correct the record.

A former Google CEO has warned that artificial intelligence be used to kill people in the future. Eric Schmidt - who spent two decades at the helm of the search giant, told a gathering of senior executives Wednesday that he believes AI presents an'existential risk' for humanity'defined as many, many, many, many people harmed or killed.' The software PhD said the technology, which Google is helping spearhead through its relatively primitive Bard chatbot system - could be'misused by evil people' when it becomes more advanced. Schmidt, who recently chaired the US National Security Commission on AI, is the latest in a slew of former Google staffers to come out publicly against the rapid development of the technology in recent weeks. Schmidt told a CEO summit in London that'misused' AI could lead to'many, many, many, many people harmed or killed.'