Aspect-based sentiment analysis aims to identify the sentiment polarity of a specific aspect in product reviews. We notice that about 30% of reviews do not contain obvious opinion words, but still convey clear human-aware sentiment orientation, which is known as implicit sentiment. However, recent neural network-based approaches paid little attention to implicit sentiment entailed in the reviews. To overcome this issue, we adopt Supervised Contrastive Pre-training on large-scale sentiment-annotated corpora retrieved from in-domain language resources. By aligning the representation of implicit sentiment expressions to those with the same sentiment label, the pre-training process leads to better capture of both implicit and explicit sentiment orientation towards aspects in reviews. Experimental results show that our method achieves state-of-the-art performance on SemEval2014 benchmarks, and comprehensive analysis validates its effectiveness on learning implicit sentiment.

Data-centric AI calls for better, not just bigger, datasets. As data protection laws with extra-territorial reach proliferate worldwide, ensuring datasets are legal is an increasingly crucial yet overlooked component of ``better''. To help dataset builders become more willing and able to navigate this complex legal space, this paper reviews key legal obligations surrounding ML datasets, examines the practical impact of data laws on ML pipelines, and offers a framework for building legal datasets.

Federated learning, which shares the weights of the neural network across clients, is gaining attention in the healthcare sector as it enables training on a large corpus of decentralized data while maintaining data privacy. For example, this enables neural network training for COVID-19 diagnosis on chest X-ray (CXR) images without collecting patient CXR data across multiple hospitals. Unfortunately, the exchange of the weights quickly consumes the network bandwidth if highly expressive network architecture is employed. So-called split learning partially solves this problem by dividing a neural network into a client and a server part, so that the client part of the network takes up less extensive computation resources and bandwidth. However, it is not clear how to find the optimal split without sacrificing the overall network performance. To amalgamate these methods and thereby maximize their distinct strengths, here we show that the Vision Transformer, a recently developed deep learning architecture with straightforward decomposable configuration, is ideally suitable for split learning without sacrificing performance. Even under the non-independent and identically distributed data distribution which emulates a real collaboration between hospitals using CXR datasets from multiple sources, the proposed framework was able to attain performance comparable to data-centralized training. In addition, the proposed framework along with heterogeneous multi-task clients also improves individual task performances including the diagnosis of COVID-19, eliminating the need for sharing large weights with innumerable parameters. Our results affirm the suitability of Transformer for collaborative learning in medical imaging and pave the way forward for future real-world implementations.

In the southeast of South Australia lie the Naracoorte Caves. The national park is an UNESCO World Heritage Site known for its stalactites, stalagmites and prehistoric fossils. Recently, a group of students from the University of Adelaide built a robot to complete a 3D scan of the site. The project, called CaveX, saw the group create 15 iterations of the model you see above before they settled on a final design. They went with a robot that walks on a set of six legs out of a fear that one with treads or wheels would damage the surface of the caves.

Facebook announced today that they will no longer use the Face Recognition system on their platform and will be deleting over 1 billion people's facial recognition profiles. Facebook's Face Recognition system analyzes photos taken of tagged users and associated users' profile photos to build a unique identifier or template. This template is then used to identify users in uploaded photos or automatically tag people in Memories. Now, a week after their rebranding as Meta, Facebook has announced that they are doing away with the Face Recognition feature and deleting all profile templates created by the system. "But the many specific instances where facial recognition can be helpful need to be weighed against growing concerns about the use of this technology as a whole," said Jerome Pesenti, VP of Artificial Intelligence, in an announcement published today.

Billionaire VC Tim Draper (via Draper Associates) has led a $6 million Series A in wellness tracking startup, Vivoo. Also participating in the funding round is ONCE Ventures, Revo Capital, 500 Startups (which backed its pre-seed), Global Ventures, and (the female-led consumer tech startup focused) Halogen Ventures. The personalized nutrition and lifestyle startup sells subscription-based at-home urine test kits that work in conjunction with an app. Its machine learning technology remotely analyzes a user's peed-on test strip to serve up custom'wellness' insights, then and there, offering recommendations across a range of areas such as nutrition and biological function. The startup's founding team is led by CEO and co-founder Miray Tayfun, a serial founder and bioengineer by background who graduated from Stanford's postgraduate programs.

Amazon's squadron of delivery drones was supposed to be in full flight by now. And the fall of 2021 would have been an opportune time to have little automated flying machines delivering packages to customers--what with all the trouble human workers are causing around the country with strikes and labor shortages. Amazon announced an experimental drone delivery service with great fanfare as part of a 60 Minutes feature in 2013. Amazon's promise was quite remarkable: Your packages--containing anything from toothpaste to a new smartphone--would arrive right at your doorstep (or on your lawn) by way of a drone that lands, drops your parcel and flies away. Jeff Bezos, Amazon's then-CEO, said in the televised segment that it would likely take "four to five years" to turn the "R&D project" into a reality.

About the Company: Founded in 2017, RwHealth's platform combines AI machine learning and data science to give healthcare providers access to data that can aid their decision-making. RwHealth's deep analytical capability can be used to make predictions, model treatment options, improve safety and increase efficiency so that clinicians can deliver better care to more people. Its platform has been used to help UK hospitals combat bed shortages and tackle waiting list issues caused by the pandemic. The startup works with more than 40 providers in the UK and internationally and its AI technology has processed more than 10.5 million patients in the UK and a further 5.5 million across the Middle East and Australia.

We focus on a simple, one-dimensional collective decision problem (often referred to as the facility location problem) and explore issues of strategyproofness and proportional fairness. We present several characterization results for mechanisms that satisfy strategyproofness and varying levels of proportional fairness. We also characterize one of the mechanisms as the unique equilibrium outcome for any mechanism that satisfies natural fairness and monotonicity properties. Finally, we identify strategyproof and proportionally fair mechanisms that provide the best welfare-optimal approximation among all mechanisms that satisfy the corresponding fairness axiom.

This paper aims to propose and theoretically analyze a new distributed scheme for sparse linear regression and feature selection. The primary goal is to learn the few causal features of a high-dimensional dataset based on noisy observations from an unknown sparse linear model. However, the presumed training set which includes $n$ data samples in $\mathbb{R}^p$ is already distributed over a large network with $N$ clients connected through extremely low-bandwidth links. Also, we consider the asymptotic configuration of $1\ll N\ll n\ll p$. In order to infer the causal dimensions from the whole dataset, we propose a simple, yet effective method for information sharing in the network. In this regard, we theoretically show that the true causal features can be reliably recovered with negligible bandwidth usage of $O\left(N\log p\right)$ across the network. This yields a significantly lower communication cost in comparison with the trivial case of transmitting all the samples to a single node (centralized scenario), which requires $O\left(np\right)$ transmissions. Even more sophisticated schemes such as ADMM still have a communication complexity of $O\left(Np\right)$. Surprisingly, our sample complexity bound is proved to be the same (up to a constant factor) as the optimal centralized approach for a fixed performance measure in each node, while that of a na\"{i}ve decentralized technique grows linearly with $N$. Theoretical guarantees in this paper are based on the recent analytic framework of debiased LASSO in Javanmard et al. (2019), and are supported by several computer experiments performed on both synthetic and real-world datasets.