arXiv subjects

Qi He

Publications and source records attributed to Qi He.

87 records · Page 5Linked to original sources

arXiv2024

Large Language Models for Social Networks: Applications, Challenges, and Solutions

Large Language Models (LLMs) are transforming the way people generate, explore, and engage with content. We study how we can develop LLM applications for online social networks. Despite LLMs' successes in other domains, it is challenging to develop LLM-based products for social networks for numerous reasons, and it has been relatively under-reported in the research community. We categorize LLM applications for social networks into three categories. First is knowledge tasks where users want to find new knowledge and information, such as search and question-answering. Second is entertainment tasks where users want to consume interesting content, such as getting entertaining notification content. Third is foundational tasks that need to be done to moderate and operate the social networks, such as content annotation and LLM monitoring. For each task, we share the challenges we found, solutions we developed, and lessons we learned. To the best of our knowledge, this is the first comprehensive paper about developing LLM applications for social networks.

cs.SI↗

arXiv2023

Let AI Entertain You: Increasing User Engagement with Generative AI and Rejection Sampling

While generative AI excels in content generation, it does not always increase user engagement. This can be attributed to two main factors. First, generative AI generates content without incorporating explicit or implicit feedback about user interactions. Even if the generated content seems to be more informative or well-written, it does not necessarily lead to an increase in user activities, such as clicks. Second, there is a concern with the quality of the content generative AI produces, which often lacks the distinctiveness and authenticity that human-created content possesses. These two factors can lead to content that fails to meet specific needs and preferences of users, ultimately reducing its potential to be engaging. This paper presents a generic framework of how to improve user engagement with generative AI by leveraging user feedback. Our solutions employ rejection sampling, a technique used in reinforcement learning, to boost engagement metrics. We leveraged the framework in the context of email notification subject lines generation for an online social network, and achieved significant engagement metric lift including +1% Session and +0.4% Weekly Active Users. We believe our work offers a universal framework that enhances user engagement with generative AI, particularly when standard generative AI reaches its limits in terms of enhancing content to be more captivating. To the best of our knowledge, this represents an early milestone in the industry's successful use of generative AI to enhance user engagement.

cs.HC↗

arXiv2023

Improving Anomaly Segmentation with Multi-Granularity Cross-Domain Alignment

Anomaly segmentation plays a pivotal role in identifying atypical objects in images, crucial for hazard detection in autonomous driving systems. While existing methods demonstrate noteworthy results on synthetic data, they often fail to consider the disparity between synthetic and real-world data domains. Addressing this gap, we introduce the Multi-Granularity Cross-Domain Alignment (MGCDA) framework, tailored to harmonize features across domains at both the scene and individual sample levels. Our contributions are twofold: i) We present the Multi-source Domain Adversarial Training module. This integrates a multi-source adversarial loss coupled with dynamic label smoothing, facilitating the learning of domain-agnostic representations across multiple processing stages. ii) We propose an innovative Cross-domain Anomaly-aware Contrastive Learning methodology.} This method adeptly selects challenging anchor points and images using an anomaly-centric strategy, ensuring precise alignment at the sample level. Extensive evaluations of the Fishyscapes and RoadAnomaly datasets demonstrate MGCDA's superior performance and adaptability. Additionally, its ability to perform parameter-free inference and function with various network architectures highlights its distinctiveness in advancing the frontier of anomaly segmentation.

cs.CV↗

arXiv2023

Two-Way Semantic Transmission of Images without Feedback

As a competitive technology for 6G, semantic communications can significantly improve transmission efficiency. However, many existing semantic communication systems require information feedback during the training coding process, resulting in a significant communication overhead. In this article, we consider a two-way semantic communication (TW-SC) system, where information feedback can be omitted by exploiting the weight reciprocity in the transceiver. Particularly, the channel simulator and semantic transceiver are implemented on both TW-SC nodes and the channel distribution is modeled by a conditional generative adversarial network. Simulation results demonstrate that the proposed TW-SC system performs closing to the state-of-the-art one-way semantic communication systems but requiring no feedback between the transceiver in the training process.

eess.SP↗

arXiv2023

Robust Deep Learning Framework for Constitutive-Relation Modeling

Modeling the full-range deformation behaviors of materials under complex loading and materials conditions is a significant challenge for constitutive relations (CRs) modeling. We propose a general encoder-decoder deep learning framework that can model high-dimensional stress-strain data and complex loading histories with robustness and universal capability. The framework employs an encoder to project high-dimensional input information (e.g., loading history, loading conditions, and materials information) to a lower-dimensional hidden space and a decoder to map the hidden representation to the stress of interest. We evaluated various encoder architectures, including gated recurrent unit (GRU), GRU with attention, temporal convolutional network (TCN), and the Transformer encoder, on two complex stress-strain datasets that were designed to include a wide range of complex loading histories and loading conditions. All architectures achieved excellent test results with an RMSE below 1 MPa. Additionally, we analyzed the capability of the different architectures to make predictions on out-of-domain applications, with an uncertainty estimation based on deep ensembles. The proposed approach provides a robust alternative to empirical/semi-empirical models for CRs modeling, offering the potential for more accurate and efficient materials design and optimization.

cond-mat.mtrl-sci↗

arXiv2023

Infrared ellipsometry study of the charge dynamics in K3p-terphenyl

We report an infrared ellipsometry study of the charge carrier dynamics in polycrystalline Kxp-terphenyl samples with nominal $x=3$, for which signatures of high-temperature superconductivity were previously reported. The infrared spectra are dominated by two Lorentzian bands with maxima around 4 000 cm$^{-1}$ and 12 000 cm$^{-1}$ which, from a comparison with calculations based on a Hückel model are assigned to intra-molecular excitations of $π$ electrons of the anionic p-terphenyl molecules. The inter-molecular electronic excitations are much weaker and give rise to a Drude peak and a similarly weak Lorentzian band around 220 cm$^{-1}$. A dc resistivity of about 0.3 $Ω$ cm at 300 K is deduced from the IR data, comparable to values measured by electrical resistivity on a twin sample. The analysis of the temperature dependence of the low-frequency response reveals a gradual decrease of the plasma frequency and the scattering rate of the Drude peak below 300 K that gets anomalously enhanced below 90 K. The corresponding missing spectral weight of the Drude peak appears blue-shifted towards the Lorentz-band at 220 cm$^{-1}$. This characteristic blue-shift signifies an enhanced localization of the charge carriers at low temperatures and contrasts the behavior expected for a bulk superconducting state for which the missing spectral weight would be redshifted to a delta-function at zero frequency that accounts for the loss-free response of the superconducting condensate. Our data might still be compatible with a filamentary superconducting state with a volume fraction well below the percolation limit for which the spatial confinement of the condensate can result in a plasmonic resonance at finite frequency.

cond-mat.mtrl-sci↗

arXiv2022

Ion-Beam Radiation-Induced Eshelby Transformations: The Mean and Variance in Hydrostatic and Shear Residual Stresses

Ion beam plays a pivotal role in ion implantations and the fabrication of nanostructures. However, there lacks a quantitative model to describe the residual stresses associated with the ion-beam radiation. Radiation-induced residual stress/transformation strain have been mostly recognized in the hydrostatic sub strain space. Here, we use molecular dynamics (MD) simulations to show that the response of a material to irradiation is generally anisotropic that depends on the ion-beam direction, and should be described using tensorial quantities. We demonstrate that accelerator-based ion beam irradiation, combined with the intrinsic lattice anisotropy and externally induced anisotropy (such as anisotropic mechanical loadings), causes radiation-actuated shear transformation strains in addition to hydrostatic expansion. We map out these complex correlations for several materials. Radiation-induced defects are shown to be responsible for residual shear stresses in the manner of Eshelby inclusion transformation. We propose such tensorial response model should be considered for accurate nanoscale fabrication using ion-beam irradiation.

cond-mat.mtrl-sci↗

arXiv2021

Trees in transformers: a theoretical analysis of the Transformer's ability to represent trees

Transformer networks are the de facto standard architecture in natural language processing. To date, there are no theoretical analyses of the Transformer's ability to capture tree structures. We focus on the ability of Transformer networks to learn tree structures that are important for tree transduction problems. We first analyze the theoretical capability of the standard Transformer architecture to learn tree structures given enumeration of all possible tree backbones, which we define as trees without labels. We then prove that two linear layers with ReLU activation function can recover any tree backbone from any two nonzero, linearly independent starting backbones. This implies that a Transformer can learn tree structures well in theory. We conduct experiments with synthetic data and find that the standard Transformer achieves similar accuracy compared to a Transformer where tree position information is explicitly encoded, albeit with slower convergence. This confirms empirically that Transformers can learn tree structures.

cs.CL↗

arXiv2020

Deep Job Understanding at LinkedIn

As the world's largest professional network, LinkedIn wants to create economic opportunity for everyone in the global workforce. One of its most critical missions is matching jobs with processionals. Improving job targeting accuracy and hire efficiency align with LinkedIn's Member First Motto. To achieve those goals, we need to understand unstructured job postings with noisy information. We applied deep transfer learning to create domain-specific job understanding models. After this, jobs are represented by professional entities, including titles, skills, companies, and assessment questions. To continuously improve LinkedIn's job understanding ability, we designed an expert feedback loop where we integrated job understanding models into LinkedIn's products to collect job posters' feedback. In this demonstration, we present LinkedIn's job posting flow and demonstrate how the integrated deep job understanding work improves job posters' satisfaction and provides significant metric lifts in LinkedIn's job recommendation system.

cs.IR↗

arXiv2020

Salience and Market-aware Skill Extraction for Job Targeting

At LinkedIn, we want to create economic opportunity for everyone in the global workforce. To make this happen, LinkedIn offers a reactive Job Search system, and a proactive Jobs You May Be Interested In (JYMBII) system to match the best candidates with their dream jobs. One of the most challenging tasks for developing these systems is to properly extract important skill entities from job postings and then target members with matched attributes. In this work, we show that the commonly used text-based \emph{salience and market-agnostic} skill extraction approach is sub-optimal because it only considers skill mention and ignores the salient level of a skill and its market dynamics, i.e., the market supply and demand influence on the importance of skills. To address the above drawbacks, we present \model, our deployed \emph{salience and market-aware} skill extraction system. The proposed \model ~shows promising results in improving the online performance of job recommendation (JYMBII) ($+1.92\%$ job apply) and skill suggestions for job posters ($-37\%$ suggestion rejection rate). Lastly, we present case studies to show interesting insights that contrast traditional skill recognition method and the proposed \model~from occupation, industry, country, and individual skill levels. Based on the above promising results, we deployed the \model ~online to extract job targeting skills for all $20$M job postings served at LinkedIn.

cs.IR↗

arXiv2020

Learning to Ask Screening Questions for Job Postings

At LinkedIn, we want to create economic opportunity for everyone in the global workforce. A critical aspect of this goal is matching jobs with qualified applicants. To improve hiring efficiency and reduce the need to manually screening each applicant, we develop a new product where recruiters can ask screening questions online so that they can filter qualified candidates easily. To add screening questions to all $20$M active jobs at LinkedIn, we propose a new task that aims to automatically generate screening questions for a given job posting. To solve the task of generating screening questions, we develop a two-stage deep learning model called Job2Questions, where we apply a deep learning model to detect intent from the text description, and then rank the detected intents by their importance based on other contextual features. Since this is a new product with no historical data, we employ deep transfer learning to train complex models with limited training data. We launched the screening question product and our AI models to LinkedIn users and observed significant impact in the job marketplace. During our online A/B test, we observed $+53.10\%$ screening question suggestion acceptance rate, $+22.17\%$ job coverage, $+190\%$ recruiter-applicant interaction, and $+11$ Net Promoter Score. In sum, the deployed Job2Questions model helps recruiters to find qualified applicants and job seekers to find jobs they are qualified for.

cs.IR↗

arXiv2019

Representation Learning in Heterogeneous Professional Social Networks with Ambiguous Social Connections

Network representations have been shown to improve performance within a variety of tasks, including classification, clustering, and link prediction. However, most models either focus on moderate-sized, homogeneous networks or require a significant amount of auxiliary input to be provided by the user. Moreover, few works have studied network representations in real-world heterogeneous social networks with ambiguous social connections and are often incomplete. In the present work, we investigate the problem of learning low-dimensional node representations in heterogeneous professional social networks (HPSNs), which are incomplete and have ambiguous social connections. We present a general heterogeneous network representation learning model called Star2Vec that learns entity and person embeddings jointly using a social connection strength-aware biased random walk combined with a node-structure expansion function. Experiments on LinkedIn's Economic Graph and publicly available snapshots of Facebook's network show that Star2Vec outperforms existing methods on members' industry and social circle classification, skill and title clustering, and member-entity link predictions. We also conducted large-scale case studies to demonstrate practical applications of the Star2Vec embeddings trained on LinkedIn's Economic Graph such as next career move, alternative career suggestions, and general entity similarity searches.

cs.SI↗

arXiv2019

Distinguishing Individual Red Pandas from Their Faces

Individual identification is essential to animal behavior and ecology research and is of significant importance for protecting endangered species. Red pandas, among the world's rarest animals, are currently identified mainly by visual inspection and microelectronic chips, which are costly and inefficient. Motivated by recent advancement in computer-vision-based animal identification, in this paper, we propose an automatic framework for identifying individual red pandas based on their face images. We implement the framework by exploring well-established deep learning models with necessary adaptation for effectively dealing with red panda images. Based on a database of red panda images constructed by ourselves, we evaluate the effectiveness of the proposed automatic individual red panda identification method. The evaluation results show the promising potential of automatically recognizing individual red pandas from their faces. We are going to release our database and model in the public domain to promote the research on automatic animal identification and particularly on the technique for protecting red pandas.

cs.CV↗

arXiv2017

Compressive Channel Estimation and Multi-user Detection in C-RAN

This paper considers the channel estimation (CE) and multi-user detection (MUD) problems in cloud radio access network (C-RAN). Assuming that active users are sparse in the network, we solve CE and MUD problems with compressed sensing (CS) technology to greatly reduce the long identification pilot overhead. A mixed L{2,1}-regularization functional for extended sparse group-sparsity recovery is proposed to exploit the inherently sparse property existing both in user activities and remote radio heads (RRHs) that active users are attached to. Empirical and theoretical guidelines are provided to help choosing tuning parameters which have critical effect on the performance of the penalty functional. To speed up the processing procedure, based on alternating direction method of multipliers and variable splitting strategy, an efficient algorithm is formulated which is guaranteed to be convergent. Numerical results are provided to illustrate the effectiveness of the proposed functional and efficient algorithm.

cs.IT↗

arXiv2015

Another pedagogy for pure-integer Gomory

We present pure-integer Gomory cuts in a way so that they are derived with respect to a "dual form" pure-integer optimization problem and applied on the standard-form primal side as columns, using the primal simplex algorithm. The input integer problem is not in standard form, and so the cuts are derived a bit differently. In this manner, we obtain a finitely-terminating version of pure-integer Gomory cuts that employs the primal rather than the dual simplex algorithm.

math.OC↗