arXiv subjects

Hongtao Liu

Publications and source records attributed to Hongtao Liu.

32 records · Page 2Linked to original sources

arXiv2024

Review-LLM: Harnessing Large Language Models for Personalized Review Generation

Product review generation is an important task in recommender systems, which could provide explanation and persuasiveness for the recommendation. Recently, Large Language Models (LLMs, e.g., ChatGPT) have shown superior text modeling and generating ability, which could be applied in review generation. However, directly applying the LLMs for generating reviews might be troubled by the ``polite'' phenomenon of the LLMs and could not generate personalized reviews (e.g., negative reviews). In this paper, we propose Review-LLM that customizes LLMs for personalized review generation. Firstly, we construct the prompt input by aggregating user historical behaviors, which include corresponding item titles and reviews. This enables the LLMs to capture user interest features and review writing style. Secondly, we incorporate ratings as indicators of satisfaction into the prompt, which could further improve the model's understanding of user preferences and the sentiment tendency control of generated reviews. Finally, we feed the prompt text into LLMs, and use Supervised Fine-Tuning (SFT) to make the model generate personalized reviews for the given user and target item. Experimental results on the real-world dataset show that our fine-tuned model could achieve better review generation performance than existing close-source LLMs.

cs.CL↗

arXiv2024

Even-integer Quantum Hall Effect in an Oxide Caused by Hidden Rashba Effect

In the presence of high magnetic field, quantum Hall systems usually host both even- and odd-integer quantized states because of lifted band degeneracies. Selective control of these quantized states is challenging but essential to understand the exotic ground states and manipulate the spin textures. Here, we study the quantum Hall effect in Bi2O2Se thin films. In magnetic fields as high as 50 T, we observe only even-integer quantum Hall states, but no sign of odd-integer states. However, when reducing the thickness of the epitaxial Bi2O2Se film to one unit cell, we observe both odd- and even-integer states in this Janus (asymmetric) film grown on SrTiO3. By means of a Rashba bilayer model based on ab initio band structures of Bi2O2Se thin films, we can ascribe the absence of odd-integer states in thicker films to the hidden Rasbha effect, where the local inversion symmetry breaking in two sectors of the [Bi2O2]2+ layer yields opposite Rashba spin polarizations, which compensate with each other. In the one unit cell Bi2O2Se film grown on SrTiO3, the asymmetry introduced by top surface and bottom interface induces a net polar field. The resulting global Rashba effect lifts the band degeneracies present in the symmetric case of thicker films.

cond-mat.mes-hall↗

arXiv2023

PUNR: Pre-training with User Behavior Modeling for News Recommendation

News recommendation aims to predict click behaviors based on user behaviors. How to effectively model the user representations is the key to recommending preferred news. Existing works are mostly focused on improvements in the supervised fine-tuning stage. However, there is still a lack of PLM-based unsupervised pre-training methods optimized for user representations. In this work, we propose an unsupervised pre-training paradigm with two tasks, i.e. user behavior masking and user behavior generation, both towards effective user behavior modeling. Firstly, we introduce the user behavior masking pre-training task to recover the masked user behaviors based on their contextual behaviors. In this way, the model could capture a much stronger and more comprehensive user news reading pattern. Besides, we incorporate a novel auxiliary user behavior generation pre-training task to enhance the user representation vector derived from the user encoder. We use the above pre-trained user modeling encoder to obtain news and user representations in downstream fine-tuning. Evaluations on the real-world news benchmark show significant performance improvements over existing baselines.

cs.IR↗

arXiv2023

Deep Generative Modeling on Limited Data with Regularization by Nontransferable Pre-trained Models

Deep generative models (DGMs) are data-eager because learning a complex model on limited data suffers from a large variance and easily overfits. Inspired by the classical perspective of the bias-variance tradeoff, we propose regularized deep generative model (Reg-DGM), which leverages a nontransferable pre-trained model to reduce the variance of generative modeling with limited data. Formally, Reg-DGM optimizes a weighted sum of a certain divergence and the expectation of an energy function, where the divergence is between the data and the model distributions, and the energy function is defined by the pre-trained model w.r.t. the model distribution. We analyze a simple yet representative Gaussian-fitting case to demonstrate how the weighting hyperparameter trades off the bias and the variance. Theoretically, we characterize the existence and the uniqueness of the global minimum of Reg-DGM in a non-parametric setting and prove its convergence with neural networks trained by gradient-based methods. Empirically, with various pre-trained feature extractors and a data-dependent energy function, Reg-DGM consistently improves the generation performance of strong DGMs with limited data and achieves competitive results to the state-of-the-art methods. Our implementation is available at https://github.com/ML-GSAI/Reg-ADA-APA.

cs.LG↗

arXiv2021

Role of topological surface states and mirror symmetry in topological crystalline insulator SnTe as an efficient electrocatalyst

The surface orientation dependence on the hydrogen evolution reaction (HER) performance of topological crystalline insulator (TCI) SnTe thin films is studied. Their intrinsic activities are determined by linear sweep voltammetry and cyclic voltammetry measurements. It is found that SnTe (001) and (111) surfaces exhibit intrinsic activities significantly larger than the (211) surface. Density functional theory calculations reveal that pure (001) and (111) surfaces are not good electrocatalysts, while those with Sn vacancies or partially oxidized surfaces, with the latter as evidenced by X-ray photoelectron spectroscopy, have high activity. The calculated overall performance of the (001) and (111) surfaces with robust topological surface states (TSSs) is better than that of the lowly symmetric (211) surface with fragile or without TSSs, which is further supported by their measured weak antilocalization strength. The high HER activity of SnTe (001) and (111) is attributed to the enhanced charge transfer between H atoms and TSSs. We also address the effect of possible surface facets and the contrast of the HER activity of the available active sites among the three samples. Our study demonstrates that the TSSs and mirror symmetry of TCIs expedite their HER activity.

cond-mat.mtrl-sci↗

arXiv2021

Atomically sharp interface enabled ultrahigh-speed, nonvolatile memory devices

Development of memory devices with ultimate performance has played a key role in innovation of modern electronics. As a mainstream technology nonvolatile memory devices have manifested high capacity and mechanical reliability, however current major bottlenecks include low extinction ratio and slow operational speed. Although substantial effort has been employed to improve their performance, a typical hundreds of micro- or even milli- second write time remains a few orders of magnitude longer than their volatile counterparts. We have demonstrated nonvolatile, floating-gate memory devices based on van der Waals heterostructures with atomically sharp interfaces between different functional elements, and achieved ultrahigh-speed programming/erasing operations verging on an ultimate theoretical limit of nanoseconds with extinction ratio up to 10^10. This extraordinary performance has allowed new device capabilities such as multi-bit storage, thus opening up unforeseen applications in the realm of modern nanoelectronics and offering future fabrication guidelines for device scale-up.

physics.app-ph↗

arXiv2019

Observation of Electric-Dipole Transitions in the Laser-Cooling Candidate Th$^-$

Despite the fact that the laser cooling method is a well-established technique to obtain ultra-cold neutral atoms and atomic cations, it has so far never been applied to atomic anions due to the lack of suitable electric-dipole transitions. Efforts of more than a decade currently has La$^-$ as the only promising candidate for laser cooling. Our previous work [Tang et al., Phys. Rev. Lett. 123, 203002(2019)] showed that Th$^-$ is also a potential candidate. Here we report on a combination of experimental and theoretical studies to determine the relevant transition frequencies, transition rates, and branching ratios in Th$^-$. The resonant frequency of the laser cooling transition is determined to be $ν/c$ = 4118.0 (10) cm$^{-1}$. The transition rate is calculated as A=1.17x10^4 s$^{-1}$. The branching fraction to dark states is very small, 1.47x10$^{-10}$, thus this represents an ideal closed cycle for laser cooling. Since Th has zero nuclear spin, it is an excellent candidate to be used to sympathetically cool antiprotons in a Penning trap.

physics.atom-ph↗

arXiv2019

Going Negative Online? -- A Study of Negative Advertising on Social Media

A growing number of empirical studies suggest that negative advertising is effective in campaigning, while the mechanisms are rarely mentioned. With the scandal of Cambridge Analytica and Russian intervention behind the Brexit and the 2016 presidential election, people have become aware of the political ads on social media and have pressured congress to restrict political advertising on social media. Following the related legislation, social media companies began disclosing their political ads archive for transparency during the summer of 2018 when the midterm election campaign was just beginning. This research collects the data of the related political ads in the context of the U.S. midterm elections since August to study the overall pattern of political ads on social media and uses sets of machine learning methods to conduct sentiment analysis on these ads to classify the negative ads. A novel approach is applied that uses AI image recognition to study the image data. Through data visualization, this research shows that negative advertising is still the minority, Republican advertisers and third party organizations are more likely to engage in negative advertising than their counterparts. Based on ordinal regressions, this study finds that anger evoked information-seeking is one of the main mechanisms causing negative ads to be more engaging and effective rather than the negative bias theory. Overall, this study provides a unique understanding of political advertising on social media by applying innovative data science methods. Further studies can extend the findings, methods, and datasets in this study, and several suggestions are given for future research.

cs.SI↗

arXiv2019

An Empirical Study towards Characterizing Deep Learning Development and Deployment across Different Frameworks and Platforms

Deep Learning (DL) has recently achieved tremendous success. A variety of DL frameworks and platforms play a key role to catalyze such progress. However, the differences in architecture designs and implementations of existing frameworks and platforms bring new challenges for DL software development and deployment. Till now, there is no study on how various mainstream frameworks and platforms influence both DL software development and deployment in practice. To fill this gap, we take the first step towards understanding how the most widely-used DL frameworks and platforms support the DL software development and deployment. We conduct a systematic study on these frameworks and platforms by using two types of DNN architectures and three popular datasets. (1) For development process, we investigate the prediction accuracy under the same runtime training configuration or same model weights/biases. We also study the adversarial robustness of trained models by leveraging the existing adversarial attack techniques. The experimental results show that the computing differences across frameworks could result in an obvious prediction accuracy decline, which should draw the attention of DL developers. (2) For deployment process, we investigate the prediction accuracy and performance (refers to time cost and memory consumption) when the trained models are migrated/quantized from PC to real mobile devices and web browsers. The DL platform study unveils that the migration and quantization still suffer from compatibility and reliability issues. Meanwhile, we find several DL software bugs by using the results as a benchmark. We further validate the results through bug confirmation from stakeholders and industrial positive feedback to highlight the implications of our study. Through our study, we summarize practical guidelines, identify challenges and pinpoint new research directions.

cs.LG↗

arXiv2019

Neural Review Rating Prediction with Hierarchical Attentions and Latent Factors

Text reviews can provide rich useful semantic information for modeling users and items, which can benefit rating prediction in recommendation. Different words and reviews may have different informativeness for users or items. Besides, different users and items should be personalized. Most existing works regard all reviews equally or utilize a general attention mechanism. In this paper, we propose a hierarchical attention model fusing latent factor model for rating prediction with reviews, which can focus on important words and informative reviews. Specially, we use the factor vectors of Latent Factor Model to guide the attention network and combine the factor vectors with feature representation learned from reviews to predict the final ratings. Experiments on real-world datasets validate the effectiveness of our approach.

cs.IR↗

arXiv2019

NRPA: Neural Recommendation with Personalized Attention

Existing review-based recommendation methods usually use the same model to learn the representations of all users/items from reviews posted by users towards items. However, different users have different preference and different items have different characteristics. Thus, the same word or similar reviews may have different informativeness for different users and items. In this paper we propose a neural recommendation approach with personalized attention to learn personalized representations of users and items from reviews. We use a review encoder to learn representations of reviews from words, and a user/item encoder to learn representations of users or items from reviews. We propose a personalized attention model, and apply it to both review and user/item encoders to select different important words and reviews for different users/items. Experiments on five datasets validate our approach can effectively improve the performance of neural recommendation.

cs.IR↗

arXiv2018

Using deep Residual Networks to search for galaxy-Lyα emitter lens candidates based on spectroscopic-selection

More than one hundred galaxy-scale strong gravitational lens systems have been found by searching for the emission lines coming from galaxies with redshifts higher than the lens galaxies. Based on this spectroscopic-selection method, we introduce the deep Residual Networks (ResNet, a kind of deep Convolutional Neural Networks) to search for the galaxy-Ly$α$ emitter (LAE) lens candidates by recognizing the Ly$α$ emission lines coming from high redshift galaxies ($2 < z < 3$) in the spectra of early-type galaxies (ETGs) at middle redshift ($z\sim 0.5$). The spectra of the ETGs come from the Data Release 12 (DR12) of the Baryon Oscillation Spectroscopic Survey (BOSS) of the Sloan Digital Sky Survey \uppercase\expandafter{\romannumeral3} (SDSS-\uppercase\expandafter{\romannumeral3}). In this paper, we first build a 28 layers ResNet model, and then artificially synthesize 150,000 training spectra, including 140,000 spectra without Ly$α$ lines and 10,000 ones with Ly$α$ lines, to train the networks. After 20 training epochs, we obtain a near-perfect test accuracy at 0.9954. The corresponding loss is 0.0028 and the completeness is 93.6\%. We finally apply our ResNet model to our predictive data with 174 known lens candidates. We obtain 1232 hits including 161 of the 174 known candidates (92.5\% discovery rate). Apart from the hits found in other works, our ResNet model also find 536 new hits. We then perform several subsequent selections on these 536 hits and present 5 most believable lens candidates.

astro-ph.GA↗

arXiv2015

Multi-color optical monitoring of Mrk 501 from 2010 to 2015

We have monitored the BL Lac object Mrk 501 in optical $V$, $R$ and $I$ bands from 2010 to 2015. For Mrk 501, the presence of strong host galaxy component can affect the results of photometry. After subtracting the host galaxy contributions, the source shows intraday and long-term variabilities for optical flux and color indices. The average variability amplitudes of $V$, $R$ and $I$ bands are $22.05\%, 22.25\%, 23.82\%$ respectively, and the value of duty cycle 14.87 per cent. A minimal variability timescale of 106 minutes is detected. No significant time lag between $V$ and $I$ bands is found on one night. The bluer-when-brighter (BWB) trend is dominant for Mrk 501 on intermediate, short and intraday timescales which supports the shock-in-jet model. For the long timescale, Mrk 501 in different state can have different BWB trend. The corresponding results of non-correcting host galaxy contributions are also presented.

astro-ph.HE↗

arXiv2013

Transformation process of the magnetron-sputtered Ag$_2$O film in hydrogen annealing

The current paper mainly addresses the effect of the hydrogen partial pressure on the microstructure and transformation of the Ag$_2$O film. The transformation process and mechanism were also analyzed in detail. Increasing the hydrogen partial pressure can accelerate the transformation of Ag$_2$O to Ag and lower the critical transformation temperature of the film due to the enhanced hydrogen reduction, and to both of the lowered activation energy of the reaction of Ag$_2$O with hydrogen and enhanced lattice strain of the Ag$_2$O film, respectively. Hydrogen-involved reaction in the whole hydrogen annealing process is mainly hydrogen reduction reaction with Ag$_2$O. The diffusion of hydrogen and gaseous H$_2$O molecules is accompanied with the whole hydrogen annealing process.

cond-mat.mtrl-sci↗