arXiv subjects

Peng Li

Publications and source records attributed to Peng Li.

At least 415 records · Page 23Linked to original sources

arXiv2020

Using simulation to incorporate dynamic criteria into multiple criteria decision-making

In this paper, we present a case study demonstrating how dynamic and uncertain criteria can be incorporated into a multicriteria analysis with the help of discrete event simulation. The simulation guided multicriteria analysis can include both monetary and non-monetary criteria that are static or dynamic, whereas standard multi criteria analysis only deals with static criteria and cost benefit analysis only deals with static monetary criteria. The dynamic and uncertain criteria are incorporated by using simulation to explore how the decision options perform. The results of the simulation are then fed into the multicriteria analysis. By enabling the incorporation of dynamic and uncertain criteria, the dynamic multiple criteria analysis was able to take a unique perspective of the problem. The highest ranked option returned by the dynamic multicriteria analysis differed from the other decision aid techniques.

cs.AI↗

arXiv2020

DisenE: Disentangling Knowledge Graph Embeddings

Knowledge graph embedding (KGE), aiming to embed entities and relations into low-dimensional vectors, has attracted wide attention recently. However, the existing research is mainly based on the black-box neural models, which makes it difficult to interpret the learned representation. In this paper, we introduce DisenE, an end-to-end framework to learn disentangled knowledge graph embeddings. Specially, we introduce an attention-based mechanism that enables the model to explicitly focus on relevant components of entity embeddings according to a given relation. Furthermore, we introduce two novel regularizers to encourage each component of the entity representation to independently reflect an isolated semantic aspect. Experimental results demonstrate that our proposed DisenE investigates a perspective to address the interpretability of KGE and is proved to be an effective way to improve the performance of link prediction tasks.

cs.CL↗

arXiv2020

Experimental parameters, combined dynamics, and nonlinearity of a Magnonic-Opto-Electronic Oscillator (MOEO)

We report the construction and characterization of a comprehensive magnonic-opto-electronic oscillator (MOEO) system based on 1550-nm photonics and yttirum iron garnet (YIG) magnonics. The system exhibits a rich and synergistic parameter space because of the ability to control individual photonic, electronic, and magnonic components. Taking advantage of the spin wave dispersion of YIG, the frequency self-generation as well as the related nonlinear processes become sensitive to the external magnetic field. Besides being known as a narrowband filter and a delay element, the YIG delayline possesses spin wave modes that can be controlled to mix with the optoelectronic modes to generate higher-order harmonic beating modes. With the high sensitivity and external tunability, the MOEO system may find usefulness in sensing applications in magnetism and spintronics beyond optoelectronics and photonics.

cond-mat.mes-hall↗

arXiv2020

Skip-Connected Self-Recurrent Spiking Neural Networks with Joint Intrinsic Parameter and Synaptic Weight Training

As an important class of spiking neural networks (SNNs), recurrent spiking neural networks (RSNNs) possess great computational power and have been widely used for processing sequential data like audio and text. However, most RSNNs suffer from two problems. 1. Due to a lack of architectural guidance, random recurrent connectivity is often adopted, which does not guarantee good performance. 2. Training of RSNNs is in general challenging, bottlenecking achievable model accuracy. To address these problems, we propose a new type of RSNNs called Skip-Connected Self-Recurrent SNNs (ScSr-SNNs). Recurrence in ScSr-SNNs is introduced in a stereotyped manner by adding self-recurrent connections to spiking neurons, which implements local memory. The network dynamics is enriched by skip connections between nonadjacent layers. Constructed by simplified self-recurrent and skip connections, ScSr-SNNs are able to realize recurrent behaviors similar to those of more complex RSNNs while the error gradients can be more straightforwardly calculated due to the mostly feedforward nature of the network. Moreover, we propose a new backpropagation (BP) method called backpropagated intrinsic plasticity (BIP) to further boost the performance of ScSr-SNNs by training intrinsic model parameters. Unlike standard intrinsic plasticity rules that adjust the neuron's intrinsic parameters according to neuronal activity, the proposed BIP methods optimize intrinsic parameters based on the backpropagated error gradient of a well-defined global loss function in addition to synaptic weight training. Based upon challenging speech and neuromorphic speech datasets including TI46-Alpha, TI46-Digits, and N-TIDIGITS, the proposed ScSr-SNNs can boost performance by up to 2.55% compared with other types of RSNNs trained by state-of-the-art BP methods.

cs.NE↗

arXiv2020

MS-Ranker: Accumulating Evidence from Potentially Correct Candidates for Answer Selection

As conventional answer selection (AS) methods generally match the question with each candidate answer independently, they suffer from the lack of matching information between the question and the candidate. To address this problem, we propose a novel reinforcement learning (RL) based multi-step ranking model, named MS-Ranker, which accumulates information from potentially correct candidate answers as extra evidence for matching the question with a candidate. In specific, we explicitly consider the potential correctness of candidates and update the evidence with a gating mechanism. Moreover, as we use a listwise ranking reward, our model learns to pay more attention to the overall performance. Experiments on two benchmarks, namely WikiQA and SemEval-2016 CQA, show that our model significantly outperforms existing methods that do not rely on external resources.

cs.CL↗

arXiv2020

Ring-Frustrated Non-Hermitian $XY$ Model

We study a non-Hermitian version of XY closed chain with odd number of lattice sites. We consider both anti-ferromagnetic coupling and also a symmetric non-collinear spin coupling. It is found that the energy spectrum is real in certain region of the parameter space. In contrast to previous non-Hermitian models, the ground state is a state with one mode occupied inside this real energy spectrum region, instead of the artificially identified vacuum state. At the same time, there appears a gapless excitation, which is made by kink like spin configurations. It is also found that this kink phase has non-trivial topological invariant.

quant-ph↗

arXiv2020

MAVEN: A Massive General Domain Event Detection Dataset

Event detection (ED), which means identifying event trigger words and classifying event types, is the first and most fundamental step for extracting event knowledge from plain text. Most existing datasets exhibit the following issues that limit further development of ED: (1) Data scarcity. Existing small-scale datasets are not sufficient for training and stably benchmarking increasingly sophisticated modern neural methods. (2) Low coverage. Limited event types of existing datasets cannot well cover general-domain events, which restricts the applications of ED models. To alleviate these problems, we present a MAssive eVENt detection dataset (MAVEN), which contains 4,480 Wikipedia documents, 118,732 event mention instances, and 168 event types. MAVEN alleviates the data scarcity problem and covers much more general event types. We reproduce the recent state-of-the-art ED models and conduct a thorough evaluation on MAVEN. The experimental results show that existing ED methods cannot achieve promising results on MAVEN as on the small datasets, which suggests that ED in the real world remains a challenging task and requires further research efforts. We also discuss further directions for general domain ED with empirical analyses. The source code and dataset can be obtained from https://github.com/THU-KEG/MAVEN-dataset.

cs.CL↗

arXiv2020

Coreferential Reasoning Learning for Language Representation

Language representation models such as BERT could effectively capture contextual semantic information from plain text, and have been proved to achieve promising results in lots of downstream NLP tasks with appropriate fine-tuning. However, most existing language representation models cannot explicitly handle coreference, which is essential to the coherent understanding of the whole discourse. To address this issue, we present CorefBERT, a novel language representation model that can capture the coreferential relations in context. The experimental results show that, compared with existing baseline models, CorefBERT can achieve significant improvements consistently on various downstream NLP tasks that require coreferential reasoning, while maintaining comparable performance to previous models on other common NLP tasks. The source code and experiment details of this paper can be obtained from https://github.com/thunlp/CorefBERT.

cs.CL↗

arXiv2020

WeChat Neural Machine Translation Systems for WMT20

We participate in the WMT 2020 shared news translation task on Chinese to English. Our system is based on the Transformer (Vaswani et al., 2017a) with effective variants and the DTMT (Meng and Zhang, 2019) architecture. In our experiments, we employ data selection, several synthetic data generation approaches (i.e., back-translation, knowledge distillation, and iterative in-domain knowledge transfer), advanced finetuning approaches and self-bleu based model ensemble. Our constrained Chinese to English system achieves 36.9 case-sensitive BLEU score, which is the highest among all submissions.

cs.CL↗

arXiv2020

Exact Solution to Sodium-Iridate-BCS-Hubbard Model along the Symmetric Line: Non-trivial topology in the ferromagnetic order

We study the sodium-iridates model on the honeycomb lattice with both BCS pairing potential and Hubbard interaction term. It is shown that this model can be exactly solved with appropriate choices of amplitude of pairing gaps, where the interacting terms are transformed to external field terms. The band structures of these exact solutions on both torus and cylinder geometry are discussed in great details. It is found that the ground state assumes an anti-ferromagnetic configuration, which breaks the time reversal symmetry spontaneously and renders the superconductor topologically trivial. On the other hand, the nontrivial topology is preserved with ferromagnetic configuration and can be characterized by the isospin Chern number.

cond-mat.str-el↗

arXiv2020

Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradient

Recently, backpropagation through time inspired learning algorithms are widely introduced into SNNs to improve the performance, which brings the possibility to attack the models accurately given Spatio-temporal gradient maps. We propose two approaches to address the challenges of gradient input incompatibility and gradient vanishing. Specifically, we design a gradient to spike converter to convert continuous gradients to ternary ones compatible with spike inputs. Then, we design a gradient trigger to construct ternary gradients that can randomly flip the spike inputs with a controllable turnover rate, when meeting all zero gradients. Putting these methods together, we build an adversarial attack methodology for SNNs trained by supervised algorithms. Moreover, we analyze the influence of the training loss function and the firing threshold of the penultimate layer, which indicates a "trap" region under the cross-entropy loss that can be escaped by threshold tuning. Extensive experiments are conducted to validate the effectiveness of our solution. Besides the quantitative analysis of the influence factors, we evidence that SNNs are more robust against adversarial attack than ANNs. This work can help reveal what happens in SNN attack and might stimulate more research on the security of SNN models and neuromorphic devices.

cs.NE↗

arXiv2020

More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction

Relational facts are an important component of human knowledge, which are hidden in vast amounts of text. In order to extract these facts from text, people have been working on relation extraction (RE) for years. From early pattern matching to current neural networks, existing RE methods have achieved significant progress. Yet with explosion of Web text and emergence of new relations, human knowledge is increasing drastically, and we thus require "more" from RE: a more powerful RE system that can robustly utilize more data, efficiently learn more relations, easily handle more complicated context, and flexibly generalize to more open domains. In this paper, we look back at existing RE methods, analyze key challenges we are facing nowadays, and show promising directions towards more powerful RE. We hope our view can advance this field and inspire more efforts in the community.

cs.CL↗

arXiv2020

Impurity-driven transitions in frustrated quantum Ising ring

We study the quantum phase transitions driven by a point impurity in a chain seamed with ring frustration. Rich phases and quantum phase transitions are uncovered and characterized by both bulk and impurity correlation functions. Nonlocality of the correlation functions are emphasized in manifesting the novel features in the system. We demonstrate that the long-range correlation function can be factorized into local and nonlocal factors in the thermodynamic limit. The gapless topological extended-kink (TEK) phase is disclosed to exhibit long-range correlation but without long-range order, because its ground state is nondegenerate and thus immune to spontaneous symmetry breaking. This conclusion is also true in the classical impurity limit, which is significantly different from that for the open boundary chain without ring frustration. However, spontaneous symmetry breaking does occur in the gapped kink zero mode (KZM) phase and leads to the antiferromagnetic zero mode (AFZM), in which antiferromagnetic order develops in the bulk while entangled states persists locally around the impurity. And as a new feature of quantum phase transition induced by impurity, the transition from the TEK phase to the KZM-AFZM phase is reflected by a steplike nonlocal factor of the correlation function.

cond-mat.str-el↗

arXiv2020

Comprehensive SNN Compression Using ADMM Optimization and Activity Regularization

As well known, the huge memory and compute costs of both artificial neural networks (ANNs) and spiking neural networks (SNNs) greatly hinder their deployment on edge devices with high efficiency. Model compression has been proposed as a promising technique to improve the running efficiency via parameter and operation reduction. Whereas, this technique is mainly practiced in ANNs rather than SNNs. It is interesting to answer how much an SNN model can be compressed without compromising its functionality, where two challenges should be addressed: i) the accuracy of SNNs is usually sensitive to model compression, which requires an accurate compression methodology; ii) the computation of SNNs is event-driven rather than static, which produces an extra compression dimension on dynamic spikes. To this end, we realize a comprehensive SNN compression through three steps. First, we formulate the connection pruning and weight quantization as a constrained optimization problem. Second, we combine spatio-temporal backpropagation (STBP) and alternating direction method of multipliers (ADMM) to solve the problem with minimum accuracy loss. Third, we further propose activity regularization to reduce the spike events for fewer active operations. These methods can be applied in either a single way for moderate compression or a joint way for aggressive compression. We define several quantitative metrics to evaluation the compression performance for SNNs. Our methodology is validated in pattern recognition tasks over MNIST, N-MNIST, CIFAR10, and CIFAR100 datasets, where extensive comparisons, analyses, and insights are provided. To our best knowledge, this is the first work that studies SNN compression in a comprehensive manner by exploiting all compressible components and achieves better results.

cs.NE↗

arXiv2020

Making Robots Draw A Vivid Portrait In Two Minutes

Significant progress has been made with artistic robots. However, existing robots fail to produce high-quality portraits in a short time. In this work, we present a drawing robot, which can automatically transfer a facial picture to a vivid portrait, and then draw it on paper within two minutes averagely. At the heart of our system is a novel portrait synthesis algorithm based on deep learning. Innovatively, we employ a self-consistency loss, which makes the algorithm capable of generating continuous and smooth brush-strokes. Besides, we propose a componential sparsity constraint to reduce the number of brush-strokes over insignificant areas. We also implement a local sketch synthesis algorithm, and several pre- and post-processing techniques to deal with the background and details. The portrait produced by our algorithm successfully captures individual characteristics by using a sparse set of continuous brush-strokes. Finally, the portrait is converted to a sequence of trajectories and reproduced by a 3-degree-of-freedom robotic arm. The whole portrait drawing robotic system is named AiSketcher. Extensive experiments show that AiSketcher can produce considerably high-quality sketches for a wide range of pictures, including faces in-the-wild and universal images of arbitrary content. To our best knowledge, AiSketcher is the first portrait drawing robot that uses neural style transfer techniques. AiSketcher has attended a quite number of exhibitions and shown remarkable performance under diverse circumstances.

cs.RO↗

arXiv2020

Learning to Recover from Multi-Modality Errors for Non-Autoregressive Neural Machine Translation

Non-autoregressive neural machine translation (NAT) predicts the entire target sequence simultaneously and significantly accelerates inference process. However, NAT discards the dependency information in a sentence, and thus inevitably suffers from the multi-modality problem: the target tokens may be provided by different possible translations, often causing token repetitions or missing. To alleviate this problem, we propose a novel semi-autoregressive model RecoverSAT in this work, which generates a translation as a sequence of segments. The segments are generated simultaneously while each segment is predicted token-by-token. By dynamically determining segment length and deleting repetitive segments, RecoverSAT is capable of recovering from repetitive and missing token errors. Experimental results on three widely-used benchmark datasets show that our proposed model achieves more than 4$\times$ speedup while maintaining comparable performance compared with the corresponding autoregressive model.

cs.CL↗

arXiv2020

Implement Liquid Democracy on Ethereum: A Fast Algorithm for Realtime Self-tally Voting System

We study the liquid democracy problem, where each voter can either directly vote to a candidate or delegate his voting power to a proxy. We consider the implementation of liquid democracy on the blockchain through Ethereum smart contract and to be compatible with the realtime self-tallying property, where the contract itself can record ballots and update voting status upon receiving each voting massage. A challenge comes due to the gas fee limitation of Ethereum mainnet, that the number of instruction for processing a voting massage can not exceed a certain amount, which restrict the application scenario with respect to algorithms whose time complexity is linear to the number of voters. We propose a fast algorithm to overcome the challenge, such that i) shifts the on-chain initialization to off-chain and ii) the on-chain complexity for processing each voting massage is O(\log n), where n is the number of voters.

cs.CR↗

arXiv2020

FashionBERT: Text and Image Matching with Adaptive Loss for Cross-modal Retrieval

In this paper, we address the text and image matching in cross-modal retrieval of the fashion industry. Different from the matching in the general domain, the fashion matching is required to pay much more attention to the fine-grained information in the fashion images and texts. Pioneer approaches detect the region of interests (i.e., RoIs) from images and use the RoI embeddings as image representations. In general, RoIs tend to represent the "object-level" information in the fashion images, while fashion texts are prone to describe more detailed information, e.g. styles, attributes. RoIs are thus not fine-grained enough for fashion text and image matching. To this end, we propose FashionBERT, which leverages patches as image features. With the pre-trained BERT model as the backbone network, FashionBERT learns high level representations of texts and images. Meanwhile, we propose an adaptive loss to trade off multitask learning in the FashionBERT modeling. Two tasks (i.e., text and image matching and cross-modal retrieval) are incorporated to evaluate FashionBERT. On the public dataset, experiments demonstrate FashionBERT achieves significant improvements in performances than the baseline and state-of-the-art approaches. In practice, FashionBERT is applied in a concrete cross-modal retrieval application. We provide the detailed matching performance and inference efficiency analysis.

cs.IR↗