Data-driven artificial intelligence models fed with published scientific findings have been used to create powerful prediction engines for scientific and technological advance, such as the discovery of novel materials with desired properties and the targeted invention of new therapies and vaccines. These AI approaches typically ignore the distribution of human prediction engines -- scientists and inventor -- who continuously alter the landscape of discovery and invention. As a result, AI hypotheses are designed to substitute for human experts, failing to complement them for punctuated collective advance. Here we show that incorporating the distribution of human expertise into self-supervised models by training on inferences cognitively available to experts dramatically improves AI prediction of future human discoveries and inventions. Including expert-awareness into models that propose (a) valuable energy-relevant materials increases the precision of materials predictions by ~100%, (b) repurposing thousands of drugs to treat new diseases increases precision by 43%, and (c) COVID-19 vaccine candidates examined in clinical trials by 260%. These models succeed by predicting human predictions and the scientists who will make them. By tuning AI to avoid the crowd, however, it generates scientifically promising "alien" hypotheses unlikely to be imagined or pursued without intervention, not only accelerating but punctuating scientific advance. By identifying and correcting for collective human bias, these models also suggest opportunities to improve human prediction by reformulating science education for discovery.

This paper models residential consumers' energy-consumption behavior by load patterns and distributions and reveals the relationship between consumers' load patterns and socioeconomic features by machine learning. We analyze the real-world smart meter data and extract load patterns using K-Medoids clustering, which is robust to outliers. We develop an analytical framework with feature selection and deep learning models to estimate the relationship between load patterns and socioeconomic features. Specifically, we use an entropy-based feature selection method to identify the critical socioeconomic characteristics that affect load patterns and benefit our method's interpretability. We further develop a customized deep neural network model to characterize the relationship between consumers' load patterns and selected socioeconomic features. Numerical studies validate our proposed framework using Pecan Street smart meter data and survey. We demonstrate that our framework can capture the relationship between load patterns and socioeconomic information and outperform benchmarks such as regression and single DNN models.

Machine Learning (ML) techniques are becoming an invaluable support for network intrusion detection, especially in revealing anomalous flows, which often hide cyber-threats. Typically, ML algorithms are exploited to classify/recognize data traffic on the basis of statistical features such as inter-arrival times, packets length distribution, mean number of flows, etc. Dealing with the vast diversity and number of features that typically characterize data traffic is a hard problem. This results in the following issues: i) the presence of so many features leads to lengthy training processes (particularly when features are highly correlated), while prediction accuracy does not proportionally improve; ii) some of the features may introduce bias during the classification process, particularly those that have scarce relation with the data traffic to be classified. To this end, by reducing the feature space and retaining only the most significant features, Feature Selection (FS) becomes a crucial pre-processing step in network management and, specifically, for the purposes of network intrusion detection. In this review paper, we complement other surveys in multiple ways: i) evaluating more recent datasets (updated w.r.t. obsolete KDD 99) by means of a designed-from-scratch Python-based procedure; ii) providing a synopsis of most credited FS approaches in the field of intrusion detection, including Multi-Objective Evolutionary techniques; iii) assessing various experimental analyses such as feature correlation, time complexity, and performance. Our comparisons offer useful guidelines to network/security managers who are considering the incorporation of ML concepts into network intrusion detection, where trade-offs between performance and resource consumption are crucial.

We derive a simple and model-independent formula for the change in the generalization gap due to a gradient descent update. We then compare the change in the test error for stochastic gradient descent to the change in test error from an equivalent number of gradient descent updates and show explicitly that stochastic gradient descent acts to regularize generalization error by decorrelating nearby updates. These calculations depends on the details of the model only through the mean and covariance of the gradient distribution, which may be readily measured for particular models of interest. We discuss further improvements to these calculations and comment on possible implications for stochastic optimization. Note added: this paper appeared in the "Workshop on Integration of Deep Learning Theories" at NeurIPS in 2018 [1]. Given the current interest in this topic (see e.g.

Interactions between several features sometimes play an important role in prediction tasks. But taking all the interactions into consideration will lead to an extremely heavy computational burden. For categorical features, the situation is more complicated since the input will be extremely high-dimensional and sparse if one-hot encoding is applied. Inspired by association rule mining, we propose a method that selects interactions of categorical features, called Random Intersection Chains. It uses random intersections to detect frequent patterns, then selects the most meaningful ones among them. At first a number of chains are generated, in which each node is the intersection of the previous node and a random chosen observation. The frequency of patterns in the tail nodes is estimated by maximum likelihood estimation, then the patterns with largest estimated frequency are selected. After that, their confidence is calculated by Bayes' theorem. The most confident patterns are finally returned by Random Intersection Chains. We show that if the number and length of chains are appropriately chosen, the patterns in the tail nodes are indeed the most frequent ones in the data set. We analyze the computation complexity of the proposed algorithm and prove the convergence of the estimators. The results of a series of experiments verify the efficiency and effectiveness of the algorithm.

We propose a deep Graph Neural Network (GNN) model that alternates two types of layers. The first type is inspired by Reservoir Computing (RC) and generates new vertex features by iterating a non-linear map until it converges to a fixed point. The second type of layer implements graph pooling operations, that gradually reduce the support graph and the vertex features, and further improve the computational efficiency of the RC-based GNN. The architecture is, therefore, pyramidal. In the last layer, the features of the remaining vertices are combined into a single vector, which represents the graph embedding. Through a mathematical derivation introduced in this paper, we show formally how graph pooling can reduce the computational complexity of the model and speed-up the convergence of the dynamical updates of the vertex features. Our proposed approach to the design of RC-based GNNs offers an advantageous and principled trade-off between accuracy and complexity, which we extensively demonstrate in experiments on a large set of graph datasets.

It is widely known that Google Trends have become one of the most popular free tools used by forecasters both in academics and in the private and public sectors. There are many papers, from several different fields, concluding that Google Trends improve forecasts' accuracy. However, what seems to be widely unknown, is that each sample of Google search data is different from the other, even if you set the same search term, data and location. This means that it is possible to find arbitrary conclusions merely by chance. This paper aims to show why and when it can become a problem and how to overcome this obstacle.

We study in this paper lower bounds for the generalization error of models derived from multi-layer neural networks, in the regime where the size of the layers is commensurate with the number of samples in the training data. We show that unbiased estimators have unacceptable performance for such nonlinear networks in this regime. We derive explicit generalization lower bounds for general biased estimators, in the cases of linear regression and of two-layered networks. In the linear case the bound is asymptotically tight. In the nonlinear case, we provide a comparison of our bounds with an empirical study of the stochastic gradient descent algorithm. The analysis uses elements from the theory of large random matrices.

Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-of-the-art results with regard to various benchmarks, this process is still vulnerable to small and imperceptible permutations originating from legitimate inputs. Intuitively, the representations should be similar in the feature space with subtle input permutations, while large variations occur with different meanings. This motivates us to investigate the learning of robust textual representation in a contrastive manner. However, it is non-trivial to obtain opposing semantic instances for textual samples. In this study, we propose a disentangled contrastive learning method that separately optimizes the uniformity and alignment of representations without negative sampling. Specifically, we introduce the concept of momentum representation consistency to align features and leverage power normalization while conforming the uniformity. Our experimental results for the NLP benchmarks demonstrate that our approach can obtain better results compared with the baselines, as well as achieve promising improvements with invariance tests and adversarial attacks. The code is available in https://github.com/zjunlp/DCL.

In this paper, we focus on the unsupervised multi-view feature selection which tries to handle high dimensional data in the field of multi-view learning. Although some graph-based methods have achieved satisfactory performance, they ignore the underlying data structure across different views. Besides, their pre-defined laplacian graphs are sensitive to the noises in the original data space, and fail to get the optimal neighbor assignment. To address the above problems, we propose a novel unsupervised multi-view feature selection model based on graph learning, and the contributions are threefold: (1) during the feature selection procedure, the consensus similarity graph shared by different views is learned. Therefore, the proposed model can reveal the data relationship from the feature subset. (2) a reasonable rank constraint is added to optimize the similarity matrix to obtain more accurate information; (3) an auto-weighted framework is presented to assign view weights adaptively, and an effective alternative iterative algorithm is proposed to optimize the problem. Experiments on various datasets demonstrate the superiority of the proposed method compared with the state-of-the-art methods.