arXiv subjects

Peijie Sun

Publications and source records attributed to Peijie Sun.

At least 55 records · Page 3Linked to original sources

arXiv2024

Intersectional Two-sided Fairness in Recommendation

Fairness of recommender systems (RS) has attracted increasing attention recently. Based on the involved stakeholders, the fairness of RS can be divided into user fairness, item fairness, and two-sided fairness which considers both user and item fairness simultaneously. However, we argue that the intersectional two-sided unfairness may still exist even if the RS is two-sided fair, which is observed and shown by empirical studies on real-world data in this paper, and has not been well-studied previously. To mitigate this problem, we propose a novel approach called Intersectional Two-sided Fairness Recommendation (ITFR). Our method utilizes a sharpness-aware loss to perceive disadvantaged groups, and then uses collaborative loss balance to develop consistent distinguishing abilities for different intersectional groups. Additionally, predicted score normalization is leveraged to align positive predicted scores to fairly treat positives in different intersectional groups. Extensive experiments and analyses on three public datasets show that our proposed approach effectively alleviates the intersectional two-sided unfairness and consistently outperforms previous state-of-the-art methods.

cs.IR↗

arXiv2024

Understanding User Experience in Large Language Model Interactions

In the rapidly evolving landscape of large language models (LLMs), most research has primarily viewed them as independent individuals, focusing on assessing their capabilities through standardized benchmarks and enhancing their general intelligence. This perspective, however, tends to overlook the vital role of LLMs as user-centric services in human-AI collaboration. This gap in research becomes increasingly critical as LLMs become more integrated into people's everyday and professional interactions. This study addresses the important need to understand user satisfaction with LLMs by exploring four key aspects: comprehending user intents, scrutinizing user experiences, addressing major user concerns about current LLM services, and charting future research paths to bolster human-AI collaborations. Our study develops a taxonomy of 7 user intents in LLM interactions, grounded in analysis of real-world user interaction logs and human verification. Subsequently, we conduct a user survey to gauge their satisfaction with LLM services, encompassing usage frequency, experiences across intents, and predominant concerns. This survey, compiling 411 anonymous responses, uncovers 11 first-hand insights into the current state of user engagement with LLMs. Based on this empirical analysis, we pinpoint 6 future research directions prioritizing the user perspective in LLM developments. This user-centered approach is essential for crafting LLMs that are not just technologically advanced but also resonate with the intricate realities of human interactions and real-world applications.

cs.HC↗

arXiv2023

Unbiased Delayed Feedback Label Correction for Conversion Rate Prediction

Conversion rate prediction is critical to many online applications such as digital display advertising. To capture dynamic data distribution, industrial systems often require retraining models on recent data daily or weekly. However, the delay of conversion behavior usually leads to incorrect labeling, which is called delayed feedback problem. Existing work may fail to introduce the correct information about false negative samples due to data sparsity and dynamic data distribution. To directly introduce the correct feedback label information, we propose an Unbiased delayed feedback Label Correction framework (ULC), which uses an auxiliary model to correct labels for observed negative feedback samples. Firstly, we theoretically prove that the label-corrected loss is an unbiased estimate of the oracle loss using true labels. Then, as there are no ready training data for label correction, counterfactual labeling is used to construct artificial training data. Furthermore, since counterfactual labeling utilizes only partial training data, we design an embedding-based alternative training method to enhance performance. Comparative experiments on both public and private datasets and detailed analyses show that our proposed approach effectively alleviates the delayed feedback problem and consistently outperforms the previous state-of-the-art methods.

cs.IR↗

arXiv2023

Intent-aware Ranking Ensemble for Personalized Recommendation

Ranking ensemble is a critical component in real recommender systems. When a user visits a platform, the system will prepare several item lists, each of which is generally from a single behavior objective recommendation model. As multiple behavior intents, e.g., both clicking and buying some specific item category, are commonly concurrent in a user visit, it is necessary to integrate multiple single-objective ranking lists into one. However, previous work on rank aggregation mainly focused on fusing homogeneous item lists with the same objective while ignoring ensemble of heterogeneous lists ranked with different objectives with various user intents. In this paper, we treat a user's possible behaviors and the potential interacting item categories as the user's intent. And we aim to study how to fuse candidate item lists generated from different objectives aware of user intents. To address such a task, we propose an Intent-aware ranking Ensemble Learning~(IntEL) model to fuse multiple single-objective item lists with various user intents, in which item-level personalized weights are learned. Furthermore, we theoretically prove the effectiveness of IntEL with point-wise, pair-wise, and list-wise loss functions via error-ambiguity decomposition. Experiments on two large-scale real-world datasets also show significant improvements of IntEL on multiple behavior objectives simultaneously compared to previous ranking ensemble models.

cs.IR↗

arXiv2023

Dipolar Spin Liquid Ending with Quantum Critical Point in a Gd-based Triangular Magnet

By performing experiment and model studies on a triangular-lattice dipolar magnet KBaGd(BO$_3$)$_2$ (KBGB), we find the highly frustrated magnet with a planar anisotropy hosts a strongly fluctuating dipolar spin liquid (DSL), which originates from the intriguing interplay between dipolar and Heisenberg interactions. The DSL constitutes an extended regime in the field-temperature phase diagram, which gets lowered in temperature as field increases and eventually ends with an unconventional quantum critical point (QCP) at $B_c\simeq 0.75$~T. Based on dipolar Heisenberg model calculations, we identify the DSL as a Berezinskii-Kosterlitz-Thouless (BKT) phase with emergent U(1) symmetry. Due to the tremendous entropy accumulation that can be related to the strong BKT and quantum fluctuations, unprecedented magnetic cooling effects are observed in the DSL regime and particularly near the QCP, making KBGB a superior dipolar coolant to commercial Gd-based refrigerants. We establish the phase diagram for triangular-lattice dipolar quantum magnets where emergent symmetry plays an essential role, and provide a basis and opens an avenue for their applications in sub-Kelvin refrigeration.

cond-mat.str-el↗

arXiv2022

A Review-aware Graph Contrastive Learning Framework for Recommendation

Most modern recommender systems predict users preferences with two components: user and item embedding learning, followed by the user-item interaction modeling. By utilizing the auxiliary review information accompanied with user ratings, many of the existing review-based recommendation models enriched user/item embedding learning ability with historical reviews or better modeled user-item interactions with the help of available user-item target reviews. Though significant progress has been made, we argue that current solutions for review-based recommendation suffer from two drawbacks. First, as review-based recommendation can be naturally formed as a user-item bipartite graph with edge features from corresponding user-item reviews, how to better exploit this unique graph structure for recommendation? Second, while most current models suffer from limited user behaviors, can we exploit the unique self-supervised signals in the review-aware graph to guide two recommendation components better? To this end, in this paper, we propose a novel Review-aware Graph Contrastive Learning (RGCL) framework for review-based recommendation. Specifically, we first construct a review-aware user-item graph with feature-enhanced edges from reviews, where each edge feature is composed of both the user-item rating and the corresponding review semantics. This graph with feature-enhanced edges can help attentively learn each neighbor node weight for user and item representation learning. After that, we design two additional contrastive learning tasks (i.e., Node Discrimination and Edge Discrimination) to provide self-supervised signals for the two components in recommendation process. Finally, extensive experiments over five benchmark datasets demonstrate the superiority of our proposed RGCL compared to the state-of-the-art baselines.

cs.IR↗

arXiv2022

ProFairRec: Provider Fairness-aware News Recommendation

News recommendation aims to help online news platform users find their preferred news articles. Existing news recommendation methods usually learn models from historical user behaviors on news. However, these behaviors are usually biased on news providers. Models trained on biased user data may capture and even amplify the biases on news providers, and are unfair for some minority news providers. In this paper, we propose a provider fairness-aware news recommendation framework (named ProFairRec), which can learn news recommendation models fair for different news providers from biased user data. The core idea of ProFairRec is to learn provider-fair news representations and provider-fair user representations to achieve provider fairness. To learn provider-fair representations from biased data, we employ provider-biased representations to inherit provider bias from data. Provider-fair and -biased news representations are learned from news content and provider IDs respectively, which are further aggregated to build fair and biased user representations based on user click history. All of these representations are used in model training while only fair representations are used for user-news matching to achieve fair news recommendation. Besides, we propose an adversarial learning task on news provider discrimination to prevent provider-fair news representation from encoding provider bias. We also propose an orthogonal regularization on provider-fair and -biased representations to better reduce provider bias in provider-fair representations. Moreover, ProFairRec is a general framework and can be applied to different news recommendation methods. Extensive experiments on a public dataset verify that our ProFairRec approach can effectively improve the provider fairness of many existing methods and meanwhile maintain their recommendation accuracy.

cs.IR↗

arXiv2021

DiffNet++: A Neural Influence and Interest Diffusion Network for Social Recommendation

Social recommendation has emerged to leverage social connections among users for predicting users' unknown preferences, which could alleviate the data sparsity issue in collaborative filtering based recommendation. Early approaches relied on utilizing each user's first-order social neighbors' interests for better user modeling and failed to model the social influence diffusion process from the global social network structure. Recently, we propose a preliminary work of a neural influence diffusion network (i.e., DiffNet) for social recommendation (Diffnet), which models the recursive social diffusion process to capture the higher-order relationships for each user. However, we argue that, as users play a central role in both user-user social network and user-item interest network, only modeling the influence diffusion process in the social network would neglect the users' latent collaborative interests in the user-item interest network. In this paper, we propose DiffNet++, an improved algorithm of DiffNet that models the neural influence diffusion and interest diffusion in a unified framework. By reformulating the social recommendation as a heterogeneous graph with social network and interest network as input, DiffNet++ advances DiffNet by injecting these two network information for user embedding learning at the same time. This is achieved by iteratively aggregating each user's embedding from three aspects: the user's previous embedding, the influence aggregation of social neighbors from the social network, and the interest aggregation of item neighbors from the user-item interest network. Furthermore, we design a multi-level attention network that learns how to attentively aggregate user embeddings from these three aspects. Finally, extensive experimental results on two real-world datasets clearly show the effectiveness of our proposed model.

cs.SI↗

arXiv2020

Generic Seebeck Effect From Spin Entropy

How magnetism affects the Seebeck effect is an important issue widely concerned in the thermoelectric community yet remaining elusive. Based on a thermodynamic analysis of spin degrees of freedom on varied $d$-electron based ferro- and anti-ferromagnets, we demonstrate that in itinerant or partially itinerant magnetic compounds there exists a generic spin contribution to the Seebeck effect over an extended temperature range from slightly below to well above the magnetic transition temperature. This contribution is interpreted as resulting from transport spin entropy of (partially) delocalized conducting $d$ electrons with strong thermal spin fluctuations, even semiquantitatively in a single-band case, in addition to the conventional diffusion part arising from their kinetic degrees of freedom. As a highly generic effect, the spin-dependent Seebeck effect might pave a feasible way to efficient "magnetic thermoelectrics".

cond-mat.mtrl-sci↗

arXiv2020

Nonsaturating magnetoresistance, anomalous Hall effect, and magnetic quantum oscillations in ferromagnetic semimetal PrAlSi

We report a comprehensive investigation of the structural, magnetic, transport and thermodynamic properties of a single crystal PrAlSi, in comparison to its nonmagnetic analogue LaAlSi. PrAlSi exhibits a ferromagnetic transition at $T_C$ = 17.8 K which, however, is followed by two weak phase transitions at lower temperatures. Based on the combined dc and ac magnetic susceptibility measurements, we propose the two reentrant magnetic phases below $T_C$ to be spin glasses or ferromagnetic cluster glasses. When the magnetic glassy states are suppressed by small field, several remarkable features appear. These include a linear, nonsaturating magnetoresistance as a function of field that is reminiscent of a topological or charge-compensated semimetal, and a large anomalous Hall conductivity amounting to $\sim$2000 $Ω^{-1}$cm$^{-1}$. Specific-heat measurements indicate a non-Kramers doublet ground state and a relatively low crystal electric field splitting of the Pr$^{3+}$ multiplets of less than 100 K. Shubnikov-de Hass oscillations are absent in LaAlSi, whereas they are clearly observed below about 25 K in PrAlSi, with an unusual temperature dependence of the dominating oscillation frequency $F$. It increases from $F$ = 18 T at 25 K to $F$ = 33 T at 2 K, hinting at an emerging Fermi pocket upon cooling into the ordered phase. These results suggest that PrAlSi is a new system where a small Fermi pocket of likely relativistic fermions is strongly coupled to magnetism. Whether hybridization between $f$ and conduction band is also involved remains an intriguing open problem.

cond-mat.mtrl-sci↗

arXiv2019

Large transverse thermoelectric figure of merit in a Dirac semimetal

Thermoelectric (TE) conversion in conducting materials is of eminent importance for providing renewable energy and solid-state cooling. Although traditionally, the Seebeck effect plays a key role for the TE figure of merit zST, it encounters fundamental constraints hindering its conversion efficiency. Most notably, there are the charge compensation of electrons and holes that diminishes this effect, and the intertwinement of the corresponding electrical and thermal conductivities through the Wiedemann-Franz (WF) law which makes their independent optimization in zST impossible. Here, we demonstrate that in the Dirac semimetal Cd3As2 the Nernst effect, i.e., the transverse counterpart of the Seebeck effect, can generate a large TE figure of merit zNT. At room temperature, zNT = 0.5 in a small field of 2 T; it significantly surmounts its longitudinal counterpart zST for any field and further increases upon warming. A large Nernst effect is generically expected in topological semimetals, benefiting from both the bipolar transport of compensated electrons and holes and their high mobilities. In this case, heat and charge transport are orthogonal, i.e., not intertwined by the WF law anymore. More importantly, further optimization of zNT by tuning the Fermi level to the Dirac node can be anticipated due to not only the enhanced bipolar transport, but also the anomalous Nernst effect arising from a pronounced Berry curvature. A combination of the former topologically trivial and the latter nontrivial advantages promises to open a new avenue towards high-efficient transverse thermoelectricity.

cond-mat.mtrl-sci↗

arXiv2019

SocialGCN: An Efficient Graph Convolutional Network based Model for Social Recommendation

Collaborative Filtering (CF) is one of the most successful approaches for recommender systems. With the emergence of online social networks, social recommendation has become a popular research direction. Most of these social recommendation models utilized each user's local neighbors' preferences to alleviate the data sparsity issue in CF. However, they only considered the local neighbors of each user and neglected the process that users' preferences are influenced as information diffuses in the social network. Recently, Graph Convolutional Networks~(GCN) have shown promising results by modeling the information diffusion process in graphs that leverage both graph structure and node feature information. To this end, in this paper, we propose an effective graph convolutional neural network based model for social recommendation. Based on a classical CF model, the key idea of our proposed model is that we borrow the strengths of GCNs to capture how users' preferences are influenced by the social diffusion process in social networks. The diffusion of users' preferences is built on a layer-wise diffusion manner, with the initial user embedding as a function of the current user's features and a free base user latent vector that is not contained in the user feature. Similarly, each item's latent vector is also a combination of the item's free latent vector, as well as its feature representation. Furthermore, we show that our proposed model is flexible when user and item features are not available. Finally, extensive experimental results on two real-world datasets clearly show the effectiveness of our proposed model.

cs.IR↗

arXiv2019

Quantum-critical phase out of frustrated magnetism in a strongly correlated metal

Strange-metal phenomena often develop at the border of antiferromagnetic order in strongly correlated metals. It has been well established that they can originate from the fluctuations anchored by the point of continuous quantum phase transition out of the antiferromagnetic order, i.e., a quantum critical point. What has been unclear is how these phenomena can be associated with a potential new phase of matter at zero temperature. Here we show that magnetic frustration of the 4f-local moments in the distorted Kagome intermetallic compound CePdAl gives rise to such a paramagnetic quantum-critical phase. Moreover, we demonstrate that this phase turns into a Fermi liquid through a Mott-like crossover; in a two-dimensional parameter space of pressure and magnetic field, this crossover is linked to a line of zero-temperature 4f-electron localization-delocalization phase transitions at low and moderate pressures. Our discovery motivates a new design principle for strongly correlated metallic states with unconventional excitations that may underlie the development of such effects as high temperature superconductivity.

cond-mat.str-el↗

arXiv2019

Giant magnetic quantum oscillations in the thermal conductivity of TaAs: Indications of chiral zero sound

Charge transport of topological semimetals has been in the focus of intensive investigations because of their non-trivial band topology. Heat transport of these materials, on the other hand, is largely unexplored and remains elusive. Here we report on an observation of unprecedented, giant magnetic quantum oscillations of thermal conductivity in the prototypical Weyl semimetal TaAs. The oscillations are antiphase with the quantum oscillating electronic density of states of a Weyl pocket, and their amplitudes amount to two orders of magnitude of the estimation based on the Wiedemann-Franz law. Our analyses show that all the conventional heat-transport mechanisms through diffusions of propagating electrons, phonons and electron-hole bipolar excitations, are far inadequate to account for these phenomena. Taking further experimental facts that the parallel field configuration favors much higher magneto-thermal conductivity, we propose that the newly proposed chiral zero sound provides a reasonable explanation to these exotic phenomena. More work focusing on other topological semimetals along the same line is badly called for.

cond-mat.mtrl-sci↗

arXiv2019

A Neural Influence Diffusion Model for Social Recommendation

Precise user and item embedding learning is the key to building a successful recommender system. Traditionally, Collaborative Filtering(CF) provides a way to learn user and item embeddings from the user-item interaction history. However, the performance is limited due to the sparseness of user behavior data. With the emergence of online social networks, social recommender systems have been proposed to utilize each user's local neighbors' preferences to alleviate the data sparsity for better user embedding modeling. We argue that, for each user of a social platform, her potential embedding is influenced by her trusted users. As social influence recursively propagates and diffuses in the social network, each user's interests change in the recursive process. Nevertheless, the current social recommendation models simply developed static models by leveraging the local neighbors of each user without simulating the recursive diffusion in the global social network, leading to suboptimal recommendation performance. In this paper, we propose a deep influence propagation model to stimulate how users are influenced by the recursive social diffusion process for social recommendation. For each user, the diffusion process starts with an initial embedding that fuses the related features and a free user latent vector that captures the latent behavior preference. The key idea of our proposed model is that we design a layer-wise influence propagation structure to model how users' latent embeddings evolve as the social diffusion process continues. We further show that our proposed model is general and could be applied when the user~(item) attributes or the social network structure is not available. Finally, extensive experimental results on two real-world datasets clearly show the effectiveness of our proposed model, with more than 13% performance improvements over the best baselines.

cs.IR↗

arXiv2019

Superconductivity in the WP single crystal

We report the discovery of superconductivity on high-quality single crystals of transition-metal pnictides WP grown by chemical vapor transport (CVT) method. Bulk superconductivity is observed at Tc = 0.84 K under ambient pressure by electrical resistivity and AC magnetic susceptibility measurements. The effects of magnetic field on the superconducting transitions are studied, leading to a large anisotropy parameter around 2 with the in-plane and out-of-plane upper critical fields of Hc2=172 Oe and Hc2\=85 Oe, respectively. Our finding demonstrates that WP is the first superconductor in 5d transition-metal at ambient pressure in MnP-type, which will help to search for new superconductors in transition-metal pnictides.

cond-mat.supr-con↗

arXiv2017

Kondo destruction in a quantum paramagnet with magnetic frustration

We report results of isothermal magnetotransport and susceptibility measurements at elevated magnetic fields B down to very low temperatures T on high-quality single crystals of the frustrated Kondo-lattice system CePdAl. They reveal a B*(T) line within the paramagnetic part of the phase diagram. This line denotes a thermally broadened 'small'-to-'large' Fermi surface crossover which substantially narrows upon cooling. At B_0* = B*(T=0) = (4.6 +/- 0.1) T, this B*(T) line merges with two other crossover lines, viz. Tp(B) below and T_FL(B) above B_0*. Tp characterizes a frustration-dominated spin-liquid state, while T_FL is the Fermi-liquid temperature associated with the lattice Kondo effect. Non-Fermi-liquid phenomena which are commonly observed near a 'Kondo destruction' quantum critical point cannot be resolved in CePdAl. Our observations reveal a rare case where Kondo coupling, frustration and quantum criticality are closely intertwined.

cond-mat.str-el↗

arXiv2017

Anomalous connection between antiferromagnetic and superconducting phases in pressurized non-centrosymmetric heavy fermion compound CeRhGe3

Unconventional superconductivity frequently emerges as the transition temperature of a magnetic phase, typically antiferromagnetic, is suppressed continuously toward zero temperature. Here, we report contrary behavior in pressurized CeRhGe3, a non-centrosymmetric heavy fermion compound. We find that its pressure-tuned antiferromagnetic transition temperature (TN) appears to avoid a continuous decrease to zero temperature by terminating abruptly above a dome of pressure-induced superconductivity. Near 21.5 GPa, evidence for TN suddenly vanishes, the electrical resistance becomes linear in temperature and the superconducting transition reaches a maximum. In light of X-ray absorption spectroscopy measurements, these characteristics appear to be related to a pressured-induced Ce valence instability, which reveals as a sharp increase in the rate of change of Ce valence with applied pressure.

cond-mat.supr-con↗