arXiv subjects

Qi Zhang

Publications and source records attributed to Qi Zhang.

At least 937 records · Page 52Linked to original sources

arXiv2022

Bitcoin Transaction Forecasting with Deep Network Representation Learning

Bitcoin and its decentralized computing paradigm for digital currency trading are one of the most disruptive technology in the 21st century. This paper presents a novel approach to developing a Bitcoin transaction forecast model, DLForecast, by leveraging deep neural networks for learning Bitcoin transaction network representations. DLForecast makes three original contributions. First, we explore three interesting properties between Bitcoin transaction accounts: topological connectivity pattern of Bitcoin accounts, transaction amount pattern, and transaction dynamics. Second, we construct a time-decaying reachability graph and a time-decaying transaction pattern graph, aiming at capturing different types of spatial-temporal Bitcoin transaction patterns. Third, we employ node embedding on both graphs and develop a Bitcoin transaction forecasting system between user accounts based on historical transactions with built-in time-decaying factor. To maintain an effective transaction forecasting performance, we leverage the multiplicative model update (MMU) ensemble to combine prediction models built on different transaction features extracted from each corresponding Bitcoin transaction graph. Evaluated on real-world Bitcoin transaction data, we show that our spatial-temporal forecasting model is efficient with fast runtime and effective with forecasting accuracy over 60\% and improves the prediction performance by 50\% when compared to forecasting model built on the static graph baseline.

cs.SI↗

arXiv2022

Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents

Text semantic matching is a fundamental task that has been widely used in various scenarios, such as community question answering, information retrieval, and recommendation. Most state-of-the-art matching models, e.g., BERT, directly perform text comparison by processing each word uniformly. However, a query sentence generally comprises content that calls for different levels of matching granularity. Specifically, keywords represent factual information such as action, entity, and event that should be strictly matched, while intents convey abstract concepts and ideas that can be paraphrased into various expressions. In this work, we propose a simple yet effective training strategy for text semantic matching in a divide-and-conquer manner by disentangling keywords from intents. Our approach can be easily combined with pre-trained language models (PLM) without influencing their inference efficiency, achieving stable performance improvements against a wide range of PLMs on three benchmarks.

cs.CL↗

arXiv2022

Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval

Ad-hoc search calls for the selection of appropriate answers from a massive-scale corpus. Nowadays, the embedding-based retrieval (EBR) becomes a promising solution, where deep learning based document representation and ANN search techniques are allied to handle this task. However, a major challenge is that the ANN index can be too large to fit into memory, given the considerable size of answer corpus. In this work, we tackle this problem with Bi-Granular Document Representation, where the lightweight sparse embeddings are indexed and standby in memory for coarse-grained candidate search, and the heavyweight dense embeddings are hosted in disk for fine-grained post verification. For the best of retrieval accuracy, a Progressive Optimization framework is designed. The sparse embeddings are learned ahead for high-quality search of candidates. Conditioned on the candidate distribution induced by the sparse embeddings, the dense embeddings are continuously learned to optimize the discrimination of ground-truth from the shortlisted candidates. Besides, two techniques: the contrastive quantization and the locality-centric sampling are introduced for the learning of sparse and dense embeddings, which substantially contribute to their performances. Thanks to the above features, our method effectively handles massive-scale EBR with strong advantages in accuracy: with up to +4.3% recall gain on million-scale corpus, and up to +17.5% recall gain on billion-scale corpus. Besides, Our method is applied to a major sponsored search platform with substantial gains on revenue (+1.95%), Recall (+1.01%) and CTR (+0.49%). Our code is available at https://github.com/microsoft/BiDR.

cs.IR↗

arXiv2022

An Effective Way for Cross-Market Recommendation with Hybrid Pre-Ranking and Ranking Models

The Cross-Market Recommendation task of WSDM CUP 2022 is about finding solutions to improve individual recommendation systems in resource-scarce target markets by leveraging data from similar high-resource source markets. Finally, our team OPDAI won the first place with NDCG@10 score of 0.6773 on the leaderboard. Our solution to this task will be detailed in this paper. To better transform information from source markets to target markets, we adopt two stages of ranking. In pre-ranking stage, we adopt diverse pre-ranking methods or models to do feature generation. After elaborate feature analysis and feature selection, we train LightGBM with 10-fold bagging to do the final ranking.

cs.IR↗

arXiv2022

Bayesian Sequential Stacking Algorithm for Concurrently Designing Molecules and Synthetic Reaction Networks

In the last few years, de novo molecular design using machine learning has made great technical progress but its practical deployment has not been as successful. This is mostly owing to the cost and technical difficulty of synthesizing such computationally designed molecules. To overcome such barriers, various methods for synthetic route design using deep neural networks have been studied intensively in recent years. However, little progress has been made in designing molecules and their synthetic routes simultaneously. Here, we formulate the problem of simultaneously designing molecules with the desired set of properties and their synthetic routes within the framework of Bayesian inference. The design variables consist of a set of reactants in a reaction network and its network topology. The design space is extremely large because it consists of all combinations of purchasable reactants, often in the order of millions or more. In addition, the designed reaction networks can adopt any topology beyond simple multistep linear reaction routes. To solve this hard combinatorial problem, we present a powerful sequential Monte Carlo algorithm that recursively designs a synthetic reaction network by sequentially building up single-step reactions. In a case study of designing drug-like molecules based on commercially available compounds, compared with heuristic combinatorial search methods, the proposed method shows overwhelming performance in terms of computational efficiency and coverage and novelty with respect to existing compounds.

q-bio.BM↗

arXiv2022

Visualizing the out-of-plane electronic dispersions in an intercalated transition metal dichalcogenide

Layered transition metal dichalcogenides have rich phase diagram and they feature two dimensionality on numerous physical properties. Co1/3NbS2 is one of the newest members of this family where Co atoms are intercalated into the Van der Waals gaps between NbS2 layers. We study the three-dimensional electronic band structure of Co1/3NbS2 using both surface and bulk sensitive angle-resolved photoemission spectroscopy. We show that the electronic bands do not fit into the rigid-band-shift picture after the Co intercalation. Instead, Co1/3NbS2 displays a different orbital character near the Fermi level compared to the pristine NbS2 compound and has a clear band dispersion in kz direction despite its layered structure. Our photoemission study demonstrates the out-of-plane electronic correlations introduced by the Co intercalation, thus offering a new perspective on this compound. Finally, we propose how Fermi level tuning could lead to exotic phases such as spin density wave instability.

cond-mat.mtrl-sci↗

arXiv2022

Quantum Squeezing of Slow-Light Solitons

We investigate the quantum squeezing of slow-light solitons generated in a $Λ$-shaped three-level atomic system working under condition of electromagnetically induced transparency (EIT). We show that due to the giant Kerr nonlinearity contributed from the EIT effect, significant quantum squeezing of the slow-light soliton can be realized within a short propagation distance. The results reported here are helpful for understanding the quantum property of slow-light solitons and for realizing light squeezing via EIT in cold atomic gases experimentally.

physics.optics↗

arXiv2022

Uni-Retriever: Towards Learning The Unified Embedding Based Retriever in Bing Sponsored Search

Embedding based retrieval (EBR) is a fundamental building block in many web applications. However, EBR in sponsored search is distinguished from other generic scenarios and technically challenging due to the need of serving multiple retrieval purposes: firstly, it has to retrieve high-relevance ads, which may exactly serve user's search intent; secondly, it needs to retrieve high-CTR ads so as to maximize the overall user clicks. In this paper, we present a novel representation learning framework Uni-Retriever developed for Bing Search, which unifies two different training modes knowledge distillation and contrastive learning to realize both required objectives. On one hand, the capability of making high-relevance retrieval is established by distilling knowledge from the ``relevance teacher model''. On the other hand, the capability of making high-CTR retrieval is optimized by learning to discriminate user's clicked ads from the entire corpus. The two training modes are jointly performed as a multi-objective learning process, such that the ads of high relevance and CTR can be favored by the generated embeddings. Besides the learning strategy, we also elaborate our solution for EBR serving pipeline built upon the substantially optimized DiskANN, where massive-scale EBR can be performed with competitive time and memory efficiency, and accomplished in high-quality. We make comprehensive offline and online experiments to evaluate the proposed techniques, whose findings may provide useful insights for the future development of EBR systems. Uni-Retriever has been mainstreamed as the major retrieval path in Bing's production thanks to the notable improvements on the representation and EBR serving quality.

cs.IR↗

arXiv2022

MQBench: Towards Reproducible and Deployable Model Quantization Benchmark

Model quantization has emerged as an indispensable technique to accelerate deep learning inference. While researchers continue to push the frontier of quantization algorithms, existing quantization work is often unreproducible and undeployable. This is because researchers do not choose consistent training pipelines and ignore the requirements for hardware deployments. In this work, we propose Model Quantization Benchmark (MQBench), a first attempt to evaluate, analyze, and benchmark the reproducibility and deployability for model quantization algorithms. We choose multiple different platforms for real-world deployments, including CPU, GPU, ASIC, DSP, and evaluate extensive state-of-the-art quantization algorithms under a unified training pipeline. MQBench acts like a bridge to connect the algorithm and the hardware. We conduct a comprehensive analysis and find considerable intuitive or counter-intuitive insights. By aligning the training settings, we find existing algorithms have about the same performance on the conventional academic track. While for the hardware-deployable quantization, there is a huge accuracy gap which remains unsettled. Surprisingly, no existing algorithm wins every challenge in MQBench, and we hope this work could inspire future research directions.

cs.LG↗

arXiv2022

A Multi-agent Reinforcement Learning Approach for Efficient Client Selection in Federated Learning

Federated learning (FL) is a training technique that enables client devices to jointly learn a shared model by aggregating locally-computed models without exposing their raw data. While most of the existing work focuses on improving the FL model accuracy, in this paper, we focus on the improving the training efficiency, which is often a hurdle for adopting FL in real-world applications. Specifically, we design an efficient FL framework which jointly optimizes model accuracy, processing latency and communication efficiency, all of which are primary design considerations for real implementation of FL. Inspired by the recent success of Multi-Agent Reinforcement Learning (MARL) in solving complex control problems, we present \textit{FedMarl}, an MARL-based FL framework which performs efficient run-time client selection. Experiments show that FedMarl can significantly improve model accuracy with much lower processing latency and communication cost.

cs.LG↗

arXiv2021

Joint State Estimation Under Attack of Discrete Event Systems

The problem of state estimation in the setting of partially-observed discrete event systems subject to cyber attacks is considered. An operator observes a plant through a natural projection that hides the occurrence of certain events. The objective of the operator is that of estimating the current state of the system. The observation is corrupted by an attacker which can tamper with the readings of a set of sensors thus inserting some fake events or erasing some observations. The aim of the attacker is that of altering the state estimation of the operator. An automaton, called joint estimator, is defined to describe the set of all possible attacks. In more details, an unbounded joint estimator is obtained by concurrent composition of two state observers, the attacker observer and the operator observer. The joint estimator shows, for each possible corrupted observation, the joint state estimation, i.e., the set of states consistent with the uncorrupted observation and the set of states consistent with the corrupted observation. Such a structure can be used to establish if an attack function is harmful w.r.t. a misleading relation. Our approach is also extended to the case in which the attacker may insert at most n events between two consecutive observations.

cs.CR↗

arXiv2021

Decomposition and Adaptive Sampling for Data-Driven Inverse Linear Optimization

This work addresses inverse linear optimization where the goal is to infer the unknown cost vector of a linear program. Specifically, we consider the data-driven setting in which the available data are noisy observations of optimal solutions that correspond to different instances of the linear program. We introduce a new formulation of the problem that, compared to other existing methods, allows the recovery of a less restrictive and generally more appropriate admissible set of cost estimates. It can be shown that this inverse optimization problem yields a finite number of solutions, and we develop an exact two-phase algorithm to determine all such solutions. Moreover, we propose an efficient decomposition algorithm to solve large instances of the problem. The algorithm extends naturally to an online learning environment where it can be used to provide quick updates of the cost estimate as new data becomes available over time. For the online setting, we further develop an effective adaptive sampling strategy that guides the selection of the next samples. The efficacy of the proposed methods is demonstrated in computational experiments involving two applications, customer preference learning and cost estimation for production planning. The results show significant reductions in computation and sampling efforts.

math.OC↗

arXiv2021

Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training

Aspect-based sentiment analysis aims to identify the sentiment polarity of a specific aspect in product reviews. We notice that about 30% of reviews do not contain obvious opinion words, but still convey clear human-aware sentiment orientation, which is known as implicit sentiment. However, recent neural network-based approaches paid little attention to implicit sentiment entailed in the reviews. To overcome this issue, we adopt Supervised Contrastive Pre-training on large-scale sentiment-annotated corpora retrieved from in-domain language resources. By aligning the representation of implicit sentiment expressions to those with the same sentiment label, the pre-training process leads to better capture of both implicit and explicit sentiment orientation towards aspects in reviews. Experimental results show that our method achieves state-of-the-art performance on SemEval2014 benchmarks, and comprehensive analysis validates its effectiveness on learning implicit sentiment.

cs.CL↗

arXiv2021

A Survey: Non-Orthogonal Multiple Access with Compressed Sensing Multiuser Detection for mMTC

One objective of the 5G communication system and beyond is to support massive machine type of communication (mMTC) to propel the fast growth of diverse Internet of Things use cases. The mMTC aims to provide connectivity to tens of billions sensor nodes. The dramatic increase of sensor devices and massive connectivity impose critical challenges for the network to handle the enormous control signaling overhead with limited radio resource. Non-Orthogonal Multiple Access (NOMA) is a new paradigm shift in the design of multiple user detection and multiple access. NOMA with compressive sensing based multiuser detection is one of the promising candidates to address the challenges of mMTC. The survey article aims at providing an overview of the current state-of-art research work in various compressive sensing based techniques that enable NOMA. We present characteristics of different algorithms and compare their pros and cons, thereby provide useful insights for researchers to make further contributions in NOMA using compressive sensing techniques.

eess.SP↗

arXiv2021

Multi-Exit Vision Transformer for Dynamic Inference

Deep neural networks can be converted to multi-exit architectures by inserting early exit branches after some of their intermediate layers. This allows their inference process to become dynamic, which is useful for time critical IoT applications with stringent latency requirements, but with time-variant communication and computation resources. In particular, in edge computing systems and IoT networks where the exact computation time budget is variable and not known beforehand. Vision Transformer is a recently proposed architecture which has since found many applications across various domains of computer vision. In this work, we propose seven different architectures for early exit branches that can be used for dynamic inference in Vision Transformer backbones. Through extensive experiments involving both classification and regression problems, we show that each one of our proposed architectures could prove useful in the trade-off between accuracy and speed.

cs.CV↗

arXiv2021

Improving Non-autoregressive Generation with Mixup Training

While pre-trained language models have achieved great success on various natural language understanding tasks, how to effectively leverage them into non-autoregressive generation tasks remains a challenge. To solve this problem, we present a non-autoregressive generation model based on pre-trained transformer models. To bridge the gap between autoregressive and non-autoregressive models, we propose a simple and effective iterative training method called MIx Source and pseudo Target (MIST). Unlike other iterative decoding methods, which sacrifice the inference speed to achieve better performance based on multiple decoding iterations, MIST works in the training stage and has no effect on inference time. Our experiments on three generation benchmarks including question generation, summarization and paraphrase generation, show that the proposed framework achieves the new state-of-the-art results for fully non-autoregressive models. We also demonstrate that our method can be used to a variety of pre-trained models. For instance, MIST based on the small pre-trained model also obtains comparable performance with seq2seq models.

cs.CL↗

arXiv2021

Plug-Tagger: A Pluggable Sequence Labeling Framework Using Language Models

Plug-and-play functionality allows deep learning models to adapt well to different tasks without requiring any parameters modified. Recently, prefix-tuning was shown to be a plug-and-play method on various text generation tasks by simply inserting corresponding continuous vectors into the inputs. However, sequence labeling tasks invalidate existing plug-and-play methods since different label sets demand changes to the architecture of the model classifier. In this work, we propose the use of label word prediction instead of classification to totally reuse the architecture of pre-trained models for sequence labeling tasks. Specifically, for each task, a label word set is first constructed by selecting a high-frequency word for each class respectively, and then, task-specific vectors are inserted into the inputs and optimized to manipulate the model predictions towards the corresponding label words. As a result, by simply switching the plugin vectors on the input, a frozen pre-trained language model is allowed to perform different tasks. Experimental results on three sequence labeling tasks show that the performance of the proposed method can achieve comparable performance with standard fine-tuning with only 0.1\% task-specific parameters. In addition, our method is up to 70 times faster than non-plug-and-play methods while switching different tasks under the resource-constrained scenario.

cs.CL↗

arXiv2021

SAM: A Self-adaptive Attention Module for Context-Aware Recommendation System

Recently, textual information has been proved to play a positive role in recommendation systems. However, most of the existing methods only focus on representation learning of textual information in ratings, while potential selection bias induced by the textual information is ignored. In this work, we propose a novel and general self-adaptive module, the Self-adaptive Attention Module (SAM), which adjusts the selection bias by capturing contextual information based on its representation. This module can be embedded into recommendation systems that contain learning components of contextual information. Experimental results on three real-world datasets demonstrate the effectiveness of our proposal, and the state-of-the-art models with SAM significantly outperform the original ones.

cs.IR↗