Graph Neural Networks (GNNs) for prediction tasks like node classification or edge prediction have received increasing attention in recent machine learning from graphically structured data. However, a large quantity of labeled graphs is difficult to obtain, which significantly limits the true success of GNNs. Although active learning has been widely studied for addressing label-sparse issues with other data types like text, images, etc., how to make it effective over graphs is an open question for research. In this paper, we present an investigation on active learning with GNNs for node classification tasks. Specifically, we propose a new method, which uses node feature propagation followed by K-Medoids clustering of the nodes for instance selection in active learning. With a theoretical bound analysis we justify the design choice of our approach. In our experiments on four benchmark datasets, the proposed method outperforms other representative baseline methods consistently and significantly.

Centralised training with decentralised execution is an important setting for cooperative deep multi-agent reinforcement learning due to communication constraints during execution and computational tractability in training. In this paper, we analyse value-based methods that are known to have superior performance in complex environments [43]. We specifically focus on QMIX [40], the current state-of-the-art in this domain. We show that the representational constraints on the joint action-values introduced by QMIX and similar methods lead to provably poor exploration and suboptimality. Furthermore, we propose a novel approach called MAVEN that hybridises value and policy-based methods by introducing a latent space for hierarchical control. The value-based agents condition their behaviour on the shared latent variable controlled by a hierarchical policy. This allows MAVEN to achieve committed, temporally extended exploration, which is key to solving complex multi-agent tasks. Our experimental results show that MAVEN achieves significant performance improvements on the challenging SMAC domain [43].

We study layered neural networks of rectified linear units (ReLU) in a modelling framework for stochastic training processes. The comparison with sigmoidal activation functions is in the center of interest. We compute typical learning curves for shallow networks with K hidden units in matching student teacher scenarios. The systems exhibit sudden changes of the generalization performance via the process of hidden unit specialization at critical sizes of the training set. Surprisingly, our results show that the training behavior of ReLU networks is qualitatively different from that of networks with sigmoidal activations. In networks with K >= 3 sigmoidal hidden units, the transition is discontinuous: Specialized network configurations co-exist and compete with states of poor performance even for very large training sets. On the contrary, the use of ReLU activations results in continuous transitions for all K: For large enough training sets, two competing, differently specialized states display similar generalization abilities, which coincide exactly for large networks in the limit K to infinity.

Layer normalization (LayerNorm) has been successfully applied to various deep neural networks to help stabilize training and boost model convergence because of its capability in handling re-centering and re-scaling of both inputs and weight matrix. However, the computational overhead introduced by LayerNorm makes these improvements expensive and significantly slows the underlying network, e.g. RNN in particular. In this paper, we hypothesize that re-centering invariance in LayerNorm is dispensable and propose root mean square layer normalization, or RMSNorm. RMSNorm regularizes the summed inputs to a neuron in one layer according to root mean square (RMS), giving the model re-scaling invariance property and implicit learning rate adaptation ability. RMSNorm is computationally simpler and thus more efficient than LayerNorm. We also present partial RMSNorm, or pRMSNorm where the RMS is estimated from p% of the summed inputs without breaking the above properties. Extensive experiments on several tasks using diverse network architectures show that RMSNorm achieves comparable performance against LayerNorm but reduces the running time by 7%~64% on different models. Source code is available at https://github.com/bzhangGo/rmsnorm.

Recently there are increasing concerns about the fairness of Artificial Intelligence (AI) in real-world applications such as computer vision and recommendations. For example, recognition algorithms in computer vision are unfair to black people such as poorly detecting their faces and inappropriately identifying them as "gorillas". As one crucial application of AI, dialogue systems have been extensively applied in our society. They are usually built with real human conversational data; thus they could inherit some fairness issues which are held in the real world. However, the fairness of dialogue systems has not been investigated. In this paper, we perform the initial study about the fairness issues in dialogue systems. In particular, we construct the first dataset and propose quantitative measures to understand fairness in dialogue models. Our studies demonstrate that popular dialogue models show significant prejudice towards different genders and races. We will release the dataset and the measurement code later to foster the fairness research in dialogue systems.

Recent years have witnessed the great success of deep neural networks in many research areas. The fundamental idea behind the design of most neural networks is to learn similarity patterns from data for prediction and inference, which lacks the ability of logical reasoning. However, the concrete ability of logical reasoning is critical to many theoretical and practical problems. In this paper, we propose Neural Logic Network (NLN), which is a dynamic neural architecture that builds the computational graph according to input logical expressions. It learns basic logical operations as neural modules, and conducts propositional logical reasoning through the network for inference. Experiments on simulated data show that NLN achieves significant performance on solving logical equations. Further experiments on real-world data show that NLN significantly outperforms state-of-the-art models on collaborative filtering and personalized recommendation tasks.

Central to the concept of multi-domain operations (MDO) is the utilization of an intelligence, surveillance, and reconnaissance (ISR) network consisting of overlapping systems of remote and autonomous sensors, and human intelligence, distributed among multiple partners. Realising this concept requires advancement in both artificial intelligence (AI) for improved distributed data analytics and intelligence augmentation (IA) for improved human-machine cognition. The contribution of this paper is threefold: (1) we map the coalition situational understanding (CSU) concept to MDO ISR requirements, paying particular attention to the need for assured and explainable AI to allow robust human-machine decision-making where assets are distributed among multiple partners; (2) we present illustrative vignettes for AI and IA in MDO ISR, including human-machine teaming, dense urban terrain analysis, and enhanced asset interoperability; (3) we appraise the state-of-the-art in explainable AI in relation to the vignettes with a focus on human-machine collaboration to achieve more rapid and agile coalition decision-making. The union of these three elements is intended to show the potential value of a CSU approach in the context of MDO ISR, grounded in three distinct use cases, highlighting how the need for explainability in the multi-partner coalition setting is key. Introduction Multi-domain operations (MDO) require the capacity, capability, and endurance to operate across multiple domains -- from dense urban terrain to space and cyberspace -- in contested environments against near-peer adversaries (U.S. Army 2018).

The transcriptions used to train an Automatic Speech Recognition (ASR) system may contain errors. Usually, either a quality control stage discards transcriptions with too many errors, or the noisy transcriptions are used as is. We introduce Lead2Gold, a method to train an ASR system that exploits the full potential of noisy transcriptions. Based on a noise model of transcription errors, Lead2Gold searches for better transcriptions of the training data with a beam search that takes this noise model into account. The beam search is differentiable and does not require a forced alignment step, thus the whole system is trained end-to-end. Lead2Gold can be viewed as a new loss function that can be used on top of any sequence-to-sequence deep neural network. We conduct proof-of-concept experiments on noisy transcriptions generated from letter corruptions with different noise levels. We show that Lead2Gold obtains a better ASR accuracy than a competitive baseline which does not account for the (artificially-introduced) transcription noise.

Understanding which AI technologies to use to advance a project can be challenging given the rapid growth and evolution of the science. This article outlines the differences between machine learning and deep learning, and how to determine when to apply each one. In both machine learning and deep learning, engineers use software tools, such as MATLAB, to enable computers to identify trends and characteristics in data by learning from an example data set. In the case of machine learning, training data is used to build a model that the computer can use to classify test data, and ultimately real-world data. Traditionally, an important step in this workflow is the development of features – additional metrics derived from the raw data – which help the model be more accurate.

OpenAI, the research company that conducts artificial intelligence research was able to train a pair of neural networks to solve the Rubik's Cube using a robotic hand. In a blog post announcing the achievement, OpenAI said the neural networks were trained in simulation, relying on the OpenAIFive code paired with Automatic Domain Randomization, which is a new technique the firm developed. "Human hands let us solve a wide variety of tasks. For the past 60 years of robotics, hard tasks which humans accomplish with their fixed pair of hands have required designing a custom robot for each task. As an alternative, people have spent many decades trying to use general-purpose robotic hardware, but with limited success due to their high degrees of freedom.,"