Exploration of Quantum Neural Architecture by Mixing Quantum Neuron Designs

With the constant increase of the number of quantum bits (qubits) in the actual quantum computers, implementing and accelerating the prevalent deep learning on quantum computers are becoming possible. Along with this trend, there emerge quantum neural architectures based on different designs of quantum neurons. A fundamental question in quantum deep learning arises: what is the best quantum neural architecture? Inspired by the design of neural architectures for classical computing which typically employs multiple types of neurons, this paper makes the very first attempt to mix quantum neuron designs to build quantum neural architectures. We observe that the existing quantum neuron designs may be quite different but complementary, such as neurons from variation quantum circuits (VQC) and Quantumflow. More specifically, VQC can apply real-valued weights but suffer from being extended to multiple layers, while QuantumFlow can build a multi-layer network efficiently, but is limited to use binary weights. To take their respective advantages, we propose to mix them together and figure out a way to connect them seamlessly without additional costly measurement. We further investigate the design principles to mix quantum neurons, which can provide guidance for quantum neural architecture exploration in the future. Experimental results demonstrate that the identified quantum neural architectures with mixed quantum neurons can achieve 90.62% of accuracy on the MNIST dataset, compared with 52.77% and 69.92% on the VQC and QuantumFlow, respectively.

Towards Controllable and Photorealistic Region-wise Image Manipulation

Adaptive and flexible image editing is a desirable function of modern generative models. In this work, we present a generative model with auto-encoder architecture for per-region style manipulation. We apply a code consistency loss to enforce an explicit disentanglement between content and style latent representations, making the content and style of generated samples consistent with their corresponding content and style references. The model is also constrained by a content alignment loss to ensure the foreground editing will not interfere background contents. As a result, given interested region masks provided by users, our model supports foreground region-wise style transfer. Specially, our model receives no extra annotations such as semantic labels except for self-supervision. Extensive experiments show the effectiveness of the proposed method and exhibit the flexibility of the proposed model for various applications, including region-wise style editing, latent space interpolation, cross-domain style transfer.

Joint Multiple Intent Detection and Slot Filling via Self-distillation

Intent detection and slot filling are two main tasks in natural language understanding (NLU) for identifying users needs from their utterances. These two tasks are highly related and often trained jointly. However, most previous works assume that each utterance only corresponds to one intent, ignoring the fact that a user utterance in many cases could include multiple intents. In this paper, we propose a novel Self-Distillation Joint NLU model (SDJN) for multi-intent NLU. First, we formulate multiple intent detection as a weakly supervised problem and approach with multiple instance learning (MIL). Then, we design an auxiliary loop via self-distillation with three orderly arranged decoders: Initial Slot Decoder, MIL Intent Decoder, and Final Slot Decoder. The output of each decoder will serve as auxiliary information for the next decoder. With the auxiliary knowledge provided by the MIL Intent Decoder, we set Final Slot Decoder as the teacher model that imparts knowledge back to Initial Slot Decoder to complete the loop. The auxiliary loop enables intents and slots to guide mutually in-depth and further boost the overall NLU performance. Experimental results on two public multi-intent datasets indicate that our model achieves strong performance compared to others.

Binary Complex Neural Network Acceleration on FPGA

Being able to learn from complex data with phase information is imperative for many signal processing applications. Today s real-valued deep neural networks (DNNs) have shown efficiency in latent information analysis but fall short when applied to the complex domain. Deep complex networks (DCN), in contrast, can learn from complex data, but have high computational costs; therefore, they cannot satisfy the instant decision-making requirements of many deployable systems dealing with short observations or short signal bursts. Recent, Binarized Complex Neural Network (BCNN), which integrates DCNs with binarized neural networks (BNN), shows great potential in classifying complex data in real-time. In this paper, we propose a structural pruning based accelerator of BCNN, which is able to provide more than 5000 frames/s inference throughput on edge devices. The high performance comes from both the algorithm and hardware sides. On the algorithm side, we conduct structural pruning to the original BCNN models and obtain 20 $times$ pruning rates with negligible accuracy loss; on the hardware side, we propose a novel 2D convolution operation accelerator for the binary complex neural network. Experimental results show that the proposed design works with over 90% utilization and is able to achieve the inference throughput of 5882 frames/s and 4938 frames/s for complex NIN-Net and ResNet-18 using CIFAR-10 dataset and Alveo U280 Board.

Finding important edges in networks through local information

In transportation, communication, social and other real complex networks, some critical edges act a pivotal part in controlling the flow of information and maintaining the integrity of the structure. Due to the importance of critical edges in theoretical studies and practical applications, the identification of critical edges gradually become a hot topic in current researches. Considering the overlap of communities in the neighborhood of edges, a novel and effective metric named subgraph overlap (SO) is proposed to quantifying the significance of edges. The experimental results show that SO outperforms all benchmarks in identifying critical edges which are crucial in maintaining the integrity of the structure and functions of networks.

Predicting Critical Nodes in Temporal Networks by Dynamic Graph Convolutional Networks

Many real-world systems can be expressed in temporal networks with nodes playing far different roles in structure and function and edges representing the relationships between nodes. Identifying critical nodes can help us control the spread of public opinions or epidemics, predict leading figures in academia, conduct advertisements for various commodities, and so on. However, it is rather difficult to identify critical nodes because the network structure changes over time in temporal networks. In this paper, considering the sequence topological information of temporal networks, a novel and effective learning framework based on the combination of special GCNs and RNNs is proposed to identify nodes with the best spreading ability. The effectiveness of the approach is evaluated by weighted Susceptible-Infected-Recovered model. Experimental results on four real-world temporal networks demonstrate that the proposed method outperforms both traditional and deep learning benchmark methods in terms of the Kendall $tau$ coefficient and top $k$ hit rate.

Server Averaging for Federated Learning

Federated learning allows distributed devices to collectively train a model without sharing or disclosing the local dataset with a central server. The global model is optimized by training and averaging the model parameters of all local participants. However, the improved privacy of federated learning also introduces challenges including higher computation and communication costs. In particular, federated learning converges slower than centralized training. We propose the server averaging algorithm to accelerate convergence. Sever averaging constructs the shared global model by periodically averaging a set of previous global models. Our experiments indicate that server averaging not only converges faster, to a target accuracy, than federated averaging (FedAvg), but also reduces the computation costs on the client-level through epoch decay.

ConfInLog: Leveraging Software Logs to Infer Configuration Constraints

Misconfigurations have become the dominant causes of software failures in recent years, drawing tremendous attention for their increasing prevalence and severity. Configuration constraints can preemptively avoid misconfiguration by defining the conditions that configuration options should satisfy. Documentation is the main source of configuration constraints, but it might be incomplete or inconsistent with the source code. In this regard, prior researches have focused on obtaining configuration constraints from software source code through static analysis. However, the difficulty in pointer analysis and context comprehension prevents them from collecting accurate and comprehensive constraints. In this paper, we observed that software logs often contain configuration constraints. We conducted an empirical study and summarized patterns of configuration-related log messages. Guided by the study, we designed and implemented ConfInLog, a static tool to infer configuration constraints from log messages. ConfInLog first selects configuration-related log messages from source code by using the summarized patterns, then infers constraints from log messages based on the summarized natural language patterns. To evaluate the effectiveness of ConfInLog, we applied our tool on seven popular open-source software systems. ConfInLog successfully inferred 22 to 163 constraints, in which 59.5% to 61.6% could not be inferred by the state-of-the-art work. Finally, we submitted 67 documentation patches regarding the constraints inferred by ConfInLog. The constraints in 29 patches have been confirmed by the developers, among which 10 patches have been accepted.

Planets Across Space and Time (PAST). I. Characterizing the Memberships of Galactic Components and Stellar Ages: Revisiting the Kinematic Methods and Applying to Planet Host Stars

Over 4,000 exoplanets have been identified and thousands of candidates are to be confirmed. The relations between the characteristics of these planetary systems and the kinematics, Galactic components, and ages of their host stars have yet to be well explored. Aiming to addressing these questions, we conduct a research project, dubbed as PAST (Planets Across Space and Time). To do this, one of the key steps is to accurately characterize the planet host stars. In this paper, the Paper I of the PAST series, we revisit the kinematic method for classification of Galactic components and extend the applicable range of velocity ellipsoid from about 100 pc to 1, 500 pc from the sun in order to cover most known planet hosts. Furthermore, we revisit the Age-Velocity dispersion Relation (AVR), which allows us to derive kinematic age with a typical uncertainty of 10-20% for an ensemble of stars. Applying the above revised methods, we present a catalog of kinematic properties (i.e. Galactic positions, velocities, the relative membership probabilities among the thin disk, thick disk, Hercules stream, and the halo) as well as other basic stellar parameters for 2,174 host stars of 2,872 planets by combining data from Gaia, LAMOST, APOGEE, RAVE, and the NASA exoplanet archive. The revised kinematic method and AVR as well as the stellar catalog of kinematic properties and ages lay foundation for future studies on exoplanets from two dimensions of space and time in the Galactic context.

PIN: A Novel Parallel Interactive Network for Spoken Language Understanding

Spoken Language Understanding (SLU) is an essential part of the spoken dialogue system, which typically consists of intent detection (ID) and slot filling (SF) tasks. Recently, recurrent neural networks (RNNs) based methods achieved the state-of-the-art for SLU. It is noted that, in the existing RNN-based approaches, ID and SF tasks are often jointly modeled to utilize the correlation information between them. However, we noted that, so far, the efforts to obtain better performance by supporting bidirectional and explicit information exchange between ID and SF are not well studied.In addition, few studies attempt to capture the local context information to enhance the performance of SF. Motivated by these findings, in this paper, Parallel Interactive Network (PIN) is proposed to model the mutual guidance between ID and SF. Specifically, given an utterance, a Gaussian self-attentive encoder is introduced to generate the context-aware feature embedding of the utterance which is able to capture local context information. Taking the feature embedding of the utterance, Slot2Intent module and Intent2Slot module are developed to capture the bidirectional information flow for ID and SF tasks. Finally, a cooperation mechanism is constructed to fuse the information obtained from Slot2Intent and Intent2Slot modules to further reduce the prediction bias.The experiments on two benchmark datasets, i.e., SNIPS and ATIS, demonstrate the effectiveness of our approach, which achieves a competitive result with state-of-the-art models. More encouragingly, by using the feature embedding of the utterance generated by the pre-trained language model BERT, our method achieves the state-of-the-art among all comparison approaches.