Shap explanations are a popular feature-attribution mechanism for explainable AI. They use game-theoretic notions to measure the influence of individual features on the prediction of a machine learning model. Despite a lot of recent interest from both academia and industry, it is not known whether Shap explanations of common machine learning models can be computed efficiently. In this paper, we establish the complexity of computing the Shap explanation in three important settings. First, we consider fully-factorized data distributions, and show that the complexity of computing the Shap explanation is the same as the complexity of computing the expected value of the model. This fully-factorized setting is often used to simplify the Shap computation, yet our results show that the computation can be intractable for commonly used models such as logistic regression. Going beyond fully-factorized distributions, we show that computing Shap explanations is already intractable for a very simple setting: computing Shap explanations of trivial classifiers over naive Bayes distributions. Finally, we show that even computing Shap over the empirical distribution is #P-hard.

Last year, researchers from Curtin University tracked the fall of a meteorite in Western Australia, using advanced technologies.

Researchers have warned against possible harms from AI that processes and generates text.Credit: Getty An international team of around 1,000 largely academic volunteers has tried to break big tech's stranglehold on natural-language processing and reduce its harms. Trained with US$7-million-worth of publicly funded computing time, the BLOOM language model will rival in scale those made by firms Google and OpenAI, but will be open-source. BLOOM will also be the first model of its scale to be multilingual. The collaboration, called BigScience, launched an early version of the model on 17 June, and hopes that it will ultimately help to reduce harmful outputs of artificial intelligence (AI) language systems. Models that recognize and generate language are increasingly used by big tech firms in applications from chat bots to translators, and can sound so eerily human that a Google engineer this month claimed that the firm's AI model was sentient (Google strongly denies that the AI possesses sentience).

Bilevel optimization have gained growing interests, with numerous applications found in meta learning, minimax games, reinforcement learning, and nested composition optimization. This paper studies the problem of distributed bilevel optimization over a network where agents can only communicate with neighbors, including examples from multi-task, multi-agent learning and federated learning. In this paper, we propose a gossip-based distributed bilevel learning algorithm that allows networked agents to solve both the inner and outer optimization problems in a single timescale and share information via network propagation. We show that our algorithm enjoys the $\mathcal{O}(\frac{1}{K \epsilon^2})$ per-agent sample complexity for general nonconvex bilevel optimization and $\mathcal{O}(\frac{1}{K \epsilon})$ for strongly convex objective, achieving a speedup that scales linearly with the network size. The sample complexities are optimal in both $\epsilon$ and $K$. We test our algorithm on the examples of hyperparameter tuning and decentralized reinforcement learning. Simulated experiments confirmed that our algorithm achieves the state-of-the-art training efficiency and test accuracy.

It is common in computer vision to be confronted with domain shift: images which have the same class but different acquisition conditions. In domain adaptation (DA), one wants to classify unlabeled target images using source labeled images. Unfortunately, deep neural networks trained on a source training set perform poorly on target images which do not belong to the training domain. One strategy to improve these performances is to align the source and target image distributions in an embedded space using optimal transport (OT). However OT can cause negative transfer, i.e. aligning samples with different labels, which leads to overfitting especially in the presence of label shift between domains. In this work, we mitigate negative alignment by explaining it as a noisy label assignment to target images. We then mitigate its effect by appropriate regularization. We propose to couple the MixUp regularization \citep{zhang2018mixup} with a loss that is robust to noisy labels in order to improve domain adaptation performance. We show in an extensive ablation study that a combination of the two techniques is critical to achieve improved performance. Finally, we evaluate our method, called \textsc{mixunbot}, on several benchmarks and real-world DA problems.

A tough day at the office changes our voices, a study suggests. They also asked them to report on the stressors they had experienced that day and their perceived stress levels. When they analysed the voice recordings using computer software they noticed some distinct changes on the days people reported more stressors. They found that people talked more quickly and with more intensity when they'd had more strains that day, regardless of how stressed they actually felt. A tough day at the office changes our voices, a study suggests.

Knowing "what is happening" and "what will happen" of the mobility in a city is the building block of a data-driven smart city system. In recent years, mobility digital twin that makes a virtual replication of human mobility and predicting or simulating the fine-grained movements of the subjects in a virtual space at a metropolitan scale in near real-time has shown its great potential in modern urban intelligent systems. However, few studies have provided practical solutions. The main difficulties are four-folds. 1) The daily variation of human mobility is hard to model and predict; 2) the transportation network enforces a complex constraints on human mobility; 3) generating a rational fine-grained human trajectory is challenging for existing machine learning models; and 4) making a fine-grained prediction incurs high computational costs, which is challenging for an online system. Bearing these difficulties in mind, in this paper we propose a two-stage human mobility predictor that stratifies the coarse and fine-grained level predictions. In the first stage, to encode the daily variation of human mobility at a metropolitan level, we automatically extract citywide mobility trends as crowd contexts and predict long-term and long-distance movements at a coarse level. In the second stage, the coarse predictions are resolved to a fine-grained level via a probabilistic trajectory retrieval method, which offloads most of the heavy computations to the offline phase. We tested our method using a real-world mobile phone GPS dataset in the Kanto area in Japan, and achieved good prediction accuracy and a time efficiency of about 2 min in predicting future 1h movements of about 220K mobile phone users on a single machine to support more higher-level analysis of mobility prediction.

Using machine learning and analytical behaviour, the system focuses on … "Combining this intelligence with our internal data allows us to …

In the past few months, there has been a suite of new artificial intelligence products that go far beyond what has been made available to the public before. Last week, the high-profile suspension of a Google employee after he went public about an AI chat bot that he thought was (almost certainly incorrectly) sentient put a spotlight on just how far AI has come. One major advancement has been the new AI model Generative Pre-trained Transformer-3 (GPT-3) by research firm OpenAI, released in 2020. Since its initial release, OpenAI has slowly rolled out access to the model for various uses -- carefully allowing access to it due to fear of the powerful technology being misused. Just how powerful is this technology? Rather than telling you, why don't we get the AI to tell you?

In the past few months, there has been a suite of new artificial intelligence products that go far beyond what has been made available to the public before. Last week, the high-profile suspension of a Google employee after he went public about an AI chat bot that he thought was (almost certainly incorrectly) sentient put a spotlight on just how far AI has come. One major advancement has been the new AI model Generative Pre-trained Transformer-3 (GPT-3) by research firm OpenAI, released in 2020. Since its initial release, OpenAI has slowly rolled out access to the model for various uses -- carefully allowing access to it due to fear of the powerful technology being misused. Just how powerful is this technology?