Conceptual graphs, which is a particular type of Knowledge Graphs, play an essential role in semantic search. Prior conceptual graph construction approaches typically extract high-frequent, coarse-grained, and time-invariant concepts from formal texts. In real applications, however, it is necessary to extract less-frequent, fine-grained, and time-varying conceptual knowledge and build taxonomy in an evolving manner. In this paper, we introduce an approach to implementing and deploying the conceptual graph at Alibaba. Specifically, We propose a framework called AliCG which is capable of a) extracting fine-grained concepts by a novel bootstrapping with alignment consensus approach, b) mining long-tail concepts with a novel low-resource phrase mining approach, c) updating the graph dynamically via a concept distribution estimation method based on implicit and explicit user behaviors. We have deployed the framework at Alibaba UC Browser. Extensive offline evaluation as well as online A/B testing demonstrate the efficacy of our approach.

The recent rapid development of artificial intelligence (AI, mainly driven by machine learning research, especially deep learning) has achieved phenomenal success in various applications. However, to further apply AI technologies in real-world context, several significant issues regarding the AI ecosystem should be addressed. We identify the main issues as data privacy, ownership, and exchange, which are difficult to be solved with the current centralized paradigm of machine learning training methodology. As a result, we propose a novel model training paradigm based on blockchain, named Galaxy Learning, which aims to train a model with distributed data and to reserve the data ownership for their owners. In this new paradigm, encrypted models are moved around instead, and are federated once trained. Model training, as well as the communication, is achieved with blockchain and its smart contracts. Pricing of training data is determined by its contribution, and therefore it is not about the exchange of data ownership. In this position paper, we describe the motivation, paradigm, design, and challenges as well as opportunities of Galaxy Learning.

ARTICLE HISTORY Compiled September 25, 2018 ABSTRACT Lin et al. (Reports, 7 September 2018, p. 1004) reported a remarkable proposal that employs a passive, strictly linear optical setup to perform pattern classifications. But interpreting the multilayer diffractive setup as a deep neural network and advocating it as an all-optical deep learning framework are not well justified and represent a mischaracterization of the system by overlooking its defining characteristics of perfect linearity and strict passivity. Lin et al. [1] proposed a combination of methods for creating a computer-generated volumetric hologram (CGVH) made of multiple planar diffractive elements, and using such hologram to scatter and directionally focus each of a multitude of patternimprinted coherent light fields into a designated spatial region on an image sensor, effectively realizing a functionality of pattern recognition and classification. Their alloptical multi-planed setup bears a certain resemblance to the multi-layered structure of a deep neural network (DNN) [2], but that is about as far as the similarity goes. It is a mischaracterization to interpret the CGVH construct as a DNN, when its functionality is strictly limited to linear transformations of the input light field, thus unable to perform any task of statistical inference/prediction beyond the capacity of a single layer perceptron [2,3].

Emojis have gone viral on the Internet across platforms and devices. Interwoven into our daily communications, they have become a ubiquitous new language. However, little has been done to analyze the usage of emojis at scale and in depth. Why do some emojis become especially popular while others don't? How are people using them among the words? In this work, we take the initiative to study the collective usage and behavior of emojis, and specifically, how emojis interact with their context. We base our analysis on a very large corpus collected from a popular emoji keyboard, which contains a full month of inputs from millions of users. Our analysis is empowered by a state-of-the-art machine learning tool that computes the embeddings of emojis and words in a semantic space. We find that emojis with clear semantic meanings are more likely to be adopted. While entity-related emojis are more likely to be used as alternatives to words, sentiment-related emojis often play a complementary role in a message. Overall, emojis are significantly more prevalent in a sentimental context.

We develop a new compressive sensing (CS) inversion algorithm by utilizing the Gaussian mixture model (GMM). While the compressive sensing is performed globally on the entire image as implemented in our lensless camera, a low-rank GMM is imposed on the local image patches. This low-rank GMM is derived via eigenvalue thresholding of the GMM trained on the projection of the measurement data, thus learned {\em in situ}. The GMM and the projection of the measurement data are updated iteratively during the reconstruction. Our GMM algorithm degrades to the piecewise linear estimator (PLE) if each patch is represented by a single Gaussian model. Inspired by this, a low-rank PLE algorithm is also developed for CS inversion, constituting an additional contribution of this paper. Extensive results on both simulation data and real data captured by the lensless camera demonstrate the efficacy of the proposed algorithm. Furthermore, we compare the CS reconstruction results using our algorithm with the JPEG compression. Simulation results demonstrate that when limited bandwidth is available (a small number of measurements), our algorithm can achieve comparable results as JPEG.