arXiv subjects

Qi Zhang

Publications and source records attributed to Qi Zhang.

At least 883 records · Page 49Linked to original sources

arXiv2022

Edge-Varying Fourier Graph Networks for Multivariate Time Series Forecasting

The key problem in multivariate time series (MTS) analysis and forecasting aims to disclose the underlying couplings between variables that drive the co-movements. Considerable recent successful MTS methods are built with graph neural networks (GNNs) due to their essential capacity for relational modeling. However, previous work often used a static graph structure of time-series variables for modeling MTS failing to capture their ever-changing correlations over time. To this end, a fully-connected supra-graph connecting any two variables at any two timestamps is adaptively learned to capture the high-resolution variable dependencies via an efficient graph convolutional network. Specifically, we construct the Edge-Varying Fourier Graph Networks (EV-FGN) equipped with Fourier Graph Shift Operator (FGSO) which efficiently performs graph convolution in the frequency domain. As a result, a high-efficiency scale-free parameter learning scheme is derived for MTS analysis and forecasting according to the convolution theorem. Extensive experiments show that EV-FGN outperforms state-of-the-art methods on seven real-world MTS datasets.

cs.LG↗

arXiv2022

Local entropy and nonextensivity of networks ensembles

Nonextensivity is foreseeable in network ensembles, as heterogeneous interactions generally exist in complex networked systems that need to be described by network ensembles. But this nonextensivity has not been literatured proved yet. In this work, the existence of nonextensivity in the binary and weighted network ensembles is theoretically proved for the first time (both in the microcanonical and canonical ensemble) based on the finding of the local entropy's nonlinear change when new nodes are added to the network ensembles. This proof also shows that the existence of nonextensivity is the main difference between the network ensembles and other traditional models in statistical physics (Ising model).

cond-mat.stat-mech↗

arXiv2022

Manipulating THz Spin Current Dynamics by the Dzyaloshinskii-Moriya Interaction in Antiferromagnetic Hematite

An important vision of modern magnetic research is to use antiferromagnets as controllable and active ultrafast components in spintronic devices. Hematite is a promising model material in this respect because its pronounced Dzyaloshinskii-Moriya interaction leads to the coexistence of antiferromagnetism and weak ferromagnetism. Here, we use femtosecond laser pulses to drive terahertz spin currents from hematite into an adjacent Pt layer. We find two contributions to the generation of the spin current with distinctly different dynamics: the impulsive stimulated Raman scatting that relies on the antiferromagnetic order and the ultrafast spin Seebeck effect that relies on the net magnetization. The total THz spin current dynamics can thus be manipulated by a medium-strength magnetic field. The controllability of the THz spin current achieved in hematite opens the pathway toward controlling the exact spin current dynamics from ultrafast antiferromagnetic spin sources.

cond-mat.mes-hall↗

arXiv2022

Magnetization switching in polycrystalline Mn3Sn thin film induced by self-generated spin-polarized current

Electrical manipulation of spins is essential to design state-of-the-art spintronic devices and commonly relies on the spin current injected from a second heavy-metal material. The fact that chiral antiferromagnets produce spin current inspires us to explore the magnetization switching of chiral spins using self-generated spin torque. Here, we demonstrate the electric switching of noncollinear antiferromagnetic state in Mn3Sn by observing a crossover from conventional spin-orbit torque to the self-generated spin torque when increasing the MgO thickness in Ta/MgO/Mn3Sn polycrystalline films. The spin current injection from the Ta layer can be controlled and even blocked by varying the MgO thickness, but the switching sustains even at a large MgO thickness. Furthermore, the switching polarity reverses when the MgO thickness exceeds around 3 nm, which cannot be explained by the spin-orbit torque scenario due to spin current injection from the Ta layer. Evident current-induced switching is also observed in MgO/Mn3Sn and Ti/Mn3Sn bilayers, where external injection of spin Hall current to Mn3Sn is negligible. The inter-grain spin-transfer torque induced by spin-polarized current explains the experimental observations. Our findings provide an alternative pathway for electrical manipulation of non-collinear antiferromagnetic state without resorting to the conventional bilayer structure.

cond-mat.mtrl-sci↗

arXiv2022

Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective

Natural language understanding (NLU) models tend to rely on spurious correlations (i.e., dataset bias) to achieve high performance on in-distribution datasets but poor performance on out-of-distribution ones. Most of the existing debiasing methods often identify and weaken these samples with biased features (i.e., superficial surface features that cause such spurious correlations). However, down-weighting these samples obstructs the model in learning from the non-biased parts of these samples. To tackle this challenge, in this paper, we propose to eliminate spurious correlations in a fine-grained manner from a feature space perspective. Specifically, we introduce Random Fourier Features and weighted re-sampling to decorrelate the dependencies between features to mitigate spurious correlations. After obtaining decorrelated features, we further design a mutual-information-based method to purify them, which forces the model to learn features that are more relevant to tasks. Extensive experiments on two well-studied NLU tasks demonstrate that our method is superior to other comparative approaches.

cs.CL↗

arXiv2022

Room-temperature quantum spin Hall edge state in a higher-order topological insulator Bi$_4$Br$_4$

Room-temperature realization of macroscopic quantum phenomena is one of the major pursuits in fundamental physics. The quantum spin Hall state, a topological quantum phenomenon that features a two-dimensional insulating bulk and a helical edge state, has not yet been realized at room temperature. Here, we use scanning tunneling microscopy to visualize a quantum spin Hall edge state on the surface of the higher-order topological insulator Bi4Br4. We find that the atomically resolved lattice exhibits a large insulating gap of over 200meV, and an atomically sharp monolayer step edge hosts a striking in-gap gapless state, suggesting the topological bulk-boundary correspondence. An external magnetic field can gap the edge state, consistent with the time-reversal symmetry protection inherent to the underlying topology. We further identify the geometrical hybridization of such edge states, which not only attests to the Z2 topology of the quantum spin Hall state but also visualizes the building blocks of the higher-order topological insulator phase. Remarkably, both the insulating gap and topological edge state are observed to persist up to 300K. Our results point to the realization of the room-temperature quantum spin Hall edge state in a higher-order topological insulator.

cond-mat.mes-hall↗

arXiv2022

A Multi-Format Transfer Learning Model for Event Argument Extraction via Variational Information Bottleneck

Event argument extraction (EAE) aims to extract arguments with given roles from texts, which have been widely studied in natural language processing. Most previous works have achieved good performance in specific EAE datasets with dedicated neural architectures. Whereas, these architectures are usually difficult to adapt to new datasets/scenarios with various annotation schemas or formats. Furthermore, they rely on large-scale labeled data for training, which is unavailable due to the high labelling cost in most cases. In this paper, we propose a multi-format transfer learning model with variational information bottleneck, which makes use of the information especially the common knowledge in existing datasets for EAE in new datasets. Specifically, we introduce a shared-specific prompt framework to learn both format-shared and format-specific knowledge from datasets with different formats. In order to further absorb the common knowledge for EAE and eliminate the irrelevant noise, we integrate variational information bottleneck into our architecture to refine the shared representation. We conduct extensive experiments on three benchmark datasets, and obtain new state-of-the-art performance on EAE.

cs.CL↗

arXiv2022

An Ion Exchange Mechanism Inspired Story Ending Generator for Different Characters

Story ending generation aims at generating reasonable endings for a given story context. Most existing studies in this area focus on generating coherent or diversified story endings, while they ignore that different characters may lead to different endings for a given story. In this paper, we propose a Character-oriented Story Ending Generator (CoSEG) to customize an ending for each character in a story. Specifically, we first propose a character modeling module to learn the personalities of characters from their descriptive experiences extracted from the story context. Then, inspired by the ion exchange mechanism in chemical reactions, we design a novel vector breaking/forming module to learn the intrinsic interactions between each character and the corresponding context through an analogical information exchange procedure. Finally, we leverage the attention mechanism to learn effective character-specific interactions and feed each interaction into a decoder to generate character-orient endings. Extensive experimental results and case studies demonstrate that CoSEG achieves significant improvements in the quality of generated endings compared with state-of-the-art methods, and it effectively customizes the endings for different characters.

cs.CL↗

arXiv2022

NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results

This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results. In this challenge, the new Large-scale Diverse Video (LDV) dataset is employed. The challenge has three tracks. Tracks 1 and 2 aim at enhancing the videos compressed by HEVC at a fixed QP, while Track 3 is designed for enhancing the videos compressed by x265 at a fixed bit-rate. Besides, the quality enhancement of Tracks 1 and 3 targets at improving the fidelity (PSNR), and Track 2 targets at enhancing the perceptual quality. The three tracks totally attract 482 registrations. In the test phase, 12 teams, 8 teams and 11 teams submitted the final results of Tracks 1, 2 and 3, respectively. The proposed methods and solutions gauge the state-of-the-art of video quality enhancement. The homepage of the challenge: https://github.com/RenYang-home/NTIRE21_VEnh

eess.IV↗

arXiv2022

AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Results

This paper reviews the Challenge on Super-Resolution of Compressed Image and Video at AIM 2022. This challenge includes two tracks. Track 1 aims at the super-resolution of compressed image, and Track~2 targets the super-resolution of compressed video. In Track 1, we use the popular dataset DIV2K as the training, validation and test sets. In Track 2, we propose the LDV 3.0 dataset, which contains 365 videos, including the LDV 2.0 dataset (335 videos) and 30 additional videos. In this challenge, there are 12 teams and 2 teams that submitted the final results to Track 1 and Track 2, respectively. The proposed methods and solutions gauge the state-of-the-art of super-resolution on compressed image and video. The proposed LDV 3.0 dataset is available at https://github.com/RenYang-home/LDV_dataset. The homepage of this challenge is at https://github.com/RenYang-home/AIM22_CompressSR.

eess.IV↗

arXiv2022

Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering

Multi-hop reasoning requires aggregating multiple documents to answer a complex question. Existing methods usually decompose the multi-hop question into simpler single-hop questions to solve the problem for illustrating the explainable reasoning process. However, they ignore grounding on the supporting facts of each reasoning step, which tends to generate inaccurate decompositions. In this paper, we propose an interpretable stepwise reasoning framework to incorporate both single-hop supporting sentence identification and single-hop question generation at each intermediate step, and utilize the inference of the current hop for the next until reasoning out the final result. We employ a unified reader model for both intermediate hop reasoning and final hop inference and adopt joint optimization for more accurate and robust multi-hop reasoning. We conduct experiments on two benchmark datasets HotpotQA and 2WikiMultiHopQA. The results show that our method can effectively boost performance and also yields a better interpretable reasoning process without decomposition supervision.

cs.CL↗

arXiv2022

Causal Intervention Improves Implicit Sentiment Analysis

Despite having achieved great success for sentiment analysis, existing neural models struggle with implicit sentiment analysis. This may be due to the fact that they may latch onto spurious correlations ("shortcuts", e.g., focusing only on explicit sentiment words), resulting in undermining the effectiveness and robustness of the learned model. In this work, we propose a causal intervention model for Implicit Sentiment Analysis using Instrumental Variable (ISAIV). We first review sentiment analysis from a causal perspective and analyze the confounders existing in this task. Then, we introduce an instrumental variable to eliminate the confounding causal effects, thus extracting the pure causal effect between sentence and sentiment. We compare the proposed ISAIV model with several strong baselines on both the general implicit sentiment analysis and aspect-based implicit sentiment analysis tasks. The results indicate the great advantages of our model and the efficacy of implicit sentiment reasoning.

cs.CL↗

arXiv2022

Exploring Anchor-based Detection for Ego4D Natural Language Query

In this paper we provide the technique report of Ego4D natural language query challenge in CVPR 2022. Natural language query task is challenging due to the requirement of comprehensive understanding of video contents. Most previous works address this task based on third-person view datasets while few research interest has been placed in the ego-centric view by far. Great progress has been made though, we notice that previous works can not adapt well to ego-centric view datasets e.g., Ego4D mainly because of two reasons: 1) most queries in Ego4D have a excessively small temporal duration (e.g., less than 5 seconds); 2) queries in Ego4D are faced with much more complex video understanding of long-term temporal orders. Considering these, we propose our solution of this challenge to solve the above issues.

cs.CV↗

arXiv2022

Quantum reflection of single photons in a cold Rydberg atomic gas

We propose and analyze a scheme for realizing the quantum reflection of single photons in a cold Rydberg atomic gas via electromagnetically induced transparency, by which a deep and tunable attractive potential well can be prepared by using stored gate photons. Such a scheme is promising for designing dispersion-type single-photon switches, and may be taken as a quantum device for observing the wave and particle natures of photons simultaneously.

quant-ph↗

arXiv2022

A Semantic Alignment System for Multilingual Query-Product Retrieval

This paper mainly describes our winning solution (team name: www) to Amazon ESCI Challenge of KDD CUP 2022, which achieves a NDCG score of 0.9043 and wins the first place on task 1: the query-product ranking track. In this competition, participants are provided with a real-world large-scale multilingual shopping queries data set and it contains query-product pairs in English, Japanese and Spanish. Three different tasks are proposed in this competition, including ranking the results list as task 1, classifying the query/product pairs into Exact, Substitute, Complement, or Irrelevant (ESCI) categories as task 2 and identifying substitute products for a given query as task 3. We mainly focus on task 1 and propose a semantic alignment system for multilingual query-product retrieval. Pre-trained multilingual language models (LM) are adopted to get the semantic representation of queries and products. Our models are all trained with cross-entropy loss to classify the query-product pairs into ESCI 4 categories at first, and then we use weighted sum with the 4-class probabilities to get the score for ranking. To further boost the model, we also do elaborative data preprocessing, data augmentation by translation, specially handling English texts with English LMs, adversarial training with AWP and FGM, self distillation, pseudo labeling, label smoothing and ensemble. Finally, Our solution outperforms others both on public and private leaderboard.

cs.IR↗

arXiv2022

PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation

Pixel synthesis is a promising research paradigm for image generation, which can well exploit pixel-wise prior knowledge for generation. However, existing methods still suffer from excessive memory footprint and computation overhead. In this paper, we propose a progressive pixel synthesis network towards efficient image generation, coined as PixelFolder. Specifically, PixelFolder formulates image generation as a progressive pixel regression problem and synthesizes images via a multi-stage structure, which can greatly reduce the overhead caused by large tensor transformations. In addition, we introduce novel pixel folding operations to further improve model efficiency while maintaining pixel-wise prior knowledge for end-to-end regression. With these innovative designs, we greatly reduce the expenditure of pixel synthesis, e.g., reducing 89% computation and 53% parameters compared with the latest pixel synthesis method CIPS. To validate our approach, we conduct extensive experiments on two benchmark datasets, namely FFHQ and LSUN Church. The experimental results show that with much less expenditure, PixelFolder obtains new state-of-the-art (SOTA) performance on two benchmark datasets, i.e., 3.77 FID and 2.45 FID on FFHQ and LSUN Church, respectively.Meanwhile, PixelFolder is also more efficient than the SOTA methods like StyleGAN2, reducing about 72% computation and 31% parameters, respectively. These results greatly validate the effectiveness of the proposed PixelFolder.

cs.CV↗

arXiv2022

PanGu-Coder: Program Synthesis with Function-Level Language Modeling

We present PanGu-Coder, a pretrained decoder-only language model adopting the PanGu-Alpha architecture for text-to-code generation, i.e. the synthesis of programming language solutions given a natural language problem description. We train PanGu-Coder using a two-stage strategy: the first stage employs Causal Language Modelling (CLM) to pre-train on raw programming language data, while the second stage uses a combination of Causal Language Modelling and Masked Language Modelling (MLM) training objectives that focus on the downstream task of text-to-code generation and train on loosely curated pairs of natural language program definitions and code functions. Finally, we discuss PanGu-Coder-FT, which is fine-tuned on a combination of competitive programming problems and code with continuous integration tests. We evaluate PanGu-Coder with a focus on whether it generates functionally correct programs and demonstrate that it achieves equivalent or better performance than similarly sized models, such as CodeX, while attending a smaller context window and training on less data.

cs.LG↗

arXiv2022

Receptive Field-based Segmentation for Distributed CNN Inference Acceleration in Collaborative Edge Computing

This paper studies inference acceleration using distributed convolutional neural networks (CNNs) in collaborative edge computing network. To avoid inference accuracy loss in inference task partitioning, we propose receptive field-based segmentation (RFS). To reduce the computation time and communication overhead, we propose a novel collaborative edge computing using fused-layer parallelization to partition a CNN model into multiple blocks of convolutional layers. In this scheme, the collaborative edge servers (ESs) only need to exchange small fraction of the sub-outputs after computing each fused block. In addition, to find the optimal solution of partitioning a CNN model into multiple blocks, we use dynamic programming, named as dynamic programming for fused-layer parallelization (DPFP). The experimental results show that DPFP can accelerate inference of VGG-16 up to 73% compared with the pre-trained model, which outperforms the existing work MoDNN in all tested scenarios. Moreover, we evaluate the service reliability of DPFP under time-variant channel, which shows that DPFP is an effective solution to ensure high service reliability with strict service deadline.

cs.DC↗