arXiv subjects

Xiao Zhang

Publications and source records attributed to Xiao Zhang.

At least 289 records · Page 16Linked to original sources

arXiv2024

QAGCF: Graph Collaborative Filtering for Q&A Recommendation

Question and answer (Q&A) platforms usually recommend question-answer pairs to meet users' knowledge acquisition needs, unlike traditional recommendations that recommend only one item. This makes user behaviors more complex, and presents two challenges for Q&A recommendation, including: the collaborative information entanglement, which means user feedback is influenced by either the question or the answer; and the semantic information entanglement, where questions are correlated with their corresponding answers, and correlations also exist among different question-answer pairs. Traditional recommendation methods treat the question-answer pair as a whole or only consider the answer as a single item, which overlooks the two challenges and cannot effectively model user interests. To address these challenges, we introduce Question & Answer Graph Collaborative Filtering (QAGCF), a graph neural network model that creates separate graphs for collaborative and semantic views to disentangle the information in question-answer pairs. The collaborative view disentangles questions and answers to individually model collaborative information, while the semantic view captures the semantic information both within and between question-answer pairs. These views are further merged into a global graph to integrate the collaborative and semantic information. Polynomial-based graph filters are used to address the high heterophily issues of the global graph. Additionally, contrastive learning is utilized to obtain robust embeddings during training. Extensive experiments on industrial and public datasets demonstrate that QAGCF consistently outperforms baselines and achieves state-of-the-art results.

cs.IR↗

arXiv2024

Transferable Availability Poisoning Attacks

We consider availability data poisoning attacks, where an adversary aims to degrade the overall test accuracy of a machine learning model by crafting small perturbations to its training data. Existing poisoning strategies can achieve the attack goal but assume the victim to employ the same learning method as what the adversary uses to mount the attack. In this paper, we argue that this assumption is strong, since the victim may choose any learning algorithm to train the model as long as it can achieve some targeted performance on clean data. Empirically, we observe a large decrease in the effectiveness of prior poisoning attacks if the victim employs an alternative learning algorithm. To enhance the attack transferability, we propose Transferable Poisoning, which first leverages the intrinsic characteristics of alignment and uniformity to enable better unlearnability within contrastive learning, and then iteratively utilizes the gradient information from supervised and unsupervised contrastive learning paradigms to generate the poisoning perturbations. Through extensive experiments on image benchmarks, we show that our transferable poisoning attack can produce poisoned samples with significantly improved transferability, not only applicable to the two learners used to devise the attack but also to learning algorithms and even paradigms beyond.

cs.CR↗

arXiv2024

Conditional Language Learning with Context

Language models can learn sophisticated language understanding skills from fitting raw text. They also unselectively learn useless corpus statistics and biases, especially during finetuning on domain-specific corpora. In this paper, we propose a simple modification to causal language modeling called conditional finetuning, which performs language modeling conditioned on a context. We show that a context can "explain away" certain corpus statistics and make the model avoid learning them. In this fashion, conditional finetuning achieves selective learning from a corpus, learning knowledge useful for downstream tasks while avoiding learning useless corpus statistics like topic biases. This selective learning effect leads to less forgetting and better stability-plasticity tradeoff in domain finetuning, potentially benefitting lifelong learning with language models.

cs.CL↗

arXiv2024

Leveraging Unknown Objects to Construct Labeled-Unlabeled Meta-Relationships for Zero-Shot Object Navigation

Zero-shot object navigation (ZSON) addresses situation where an agent navigates to an unseen object that does not present in the training set. Previous works mainly train agent using seen objects with known labels, and ignore the seen objects without labels. In this paper, we introduce seen objects without labels, herein termed as ``unknown objects'', into training procedure to enrich the agent's knowledge base with distinguishable but previously overlooked information. Furthermore, we propose the label-wise meta-correlation module (LWMCM) to harness relationships among objects with and without labels, and obtain enhanced objects information. Specially, we propose target feature generator (TFG) to generate the features representation of the unlabeled target objects. Subsequently, the unlabeled object identifier (UOI) module assesses whether the unlabeled target object appears in the current observation frame captured by the camera and produces an adapted target features representation specific to the observed context. In meta contrastive feature modifier (MCFM), the target features is modified via approaching the features of objects within the observation frame while distancing itself from features of unobserved objects. Finally, the meta object-graph learner (MOGL) module is utilized to calculate the relationships among objects based on the features. Experiments conducted on AI2THOR and RoboTHOR platforms demonstrate the effectiveness of our proposed method.

cs.CV↗

arXiv2024

ReCODE: Modeling Repeat Consumption with Neural ODE

In real-world recommender systems, such as in the music domain, repeat consumption is a common phenomenon where users frequently listen to a small set of preferred songs or artists repeatedly. The key point of modeling repeat consumption is capturing the temporal patterns between a user's repeated consumption of the items. Existing studies often rely on heuristic assumptions, such as assuming an exponential distribution for the temporal gaps. However, due to the high complexity of real-world recommender systems, these pre-defined distributions may fail to capture the intricate dynamic user consumption patterns, leading to sub-optimal performance. Drawing inspiration from the flexibility of neural ordinary differential equations (ODE) in capturing the dynamics of complex systems, we propose ReCODE, a novel model-agnostic framework that utilizes neural ODE to model repeat consumption. ReCODE comprises two essential components: a user's static preference prediction module and the modeling of user dynamic repeat intention. By considering both immediate choices and historical consumption patterns, ReCODE offers comprehensive modeling of user preferences in the target context. Moreover, ReCODE seamlessly integrates with various existing recommendation models, including collaborative-based and sequential-based models, making it easily applicable in different scenarios. Experimental results on two real-world datasets consistently demonstrate that ReCODE significantly improves the performance of base models and outperforms other baseline methods.

cs.IR↗

arXiv2024

Impact of crystal symmetries and Weyl nodes on high-harmonic generation in Weyl semimetal TaAs

High-harmonic generation (HHG) offers an all-optical approach to discern structural symmetries through its selection rules and probe topological phases with its spectral signatures. Here we develop a universal theoretical framework -- the Jones matrix formalism -- establishing the fundamental relationship between pulse-crystal shared symmetries and HHG selection rules. Applying this to the Weyl semimetal (WSM) material TaAs, shows that the anomalous harmonics excited by linearly and circularly polarized pulses are governed respectively by the shared twofold and fourfold rotational symmetries of laser pulses and lattice, rather than the topology of Weyl nodes. The common observables of HHG, including intensity, circular dichroism, ellipticity dependence, and carrier-envelope phase dependence, are not found to carry a signature of the Weyl cones. This insight into TaAs can be extended to other WSMs, indicating that HHG is not a particularly effective tool for investigating the topological features of WSMs. However, the Jones matrix formalism lays the groundwork for both HHG probing crystal symmetry and controlling harmonic polarization states.

cond-mat.mtrl-sci↗

arXiv2024

UOEP: User-Oriented Exploration Policy for Enhancing Long-Term User Experiences in Recommender Systems

Reinforcement learning (RL) has gained traction for enhancing user long-term experiences in recommender systems by effectively exploring users' interests. However, modern recommender systems exhibit distinct user behavioral patterns among tens of millions of items, which increases the difficulty of exploration. For example, user behaviors with different activity levels require varying intensity of exploration, while previous studies often overlook this aspect and apply a uniform exploration strategy to all users, which ultimately hurts user experiences in the long run. To address these challenges, we propose User-Oriented Exploration Policy (UOEP), a novel approach facilitating fine-grained exploration among user groups. We first construct a distributional critic which allows policy optimization under varying quantile levels of cumulative reward feedbacks from users, representing user groups with varying activity levels. Guided by this critic, we devise a population of distinct actors aimed at effective and fine-grained exploration within its respective user group. To simultaneously enhance diversity and stability during the exploration process, we further introduce a population-level diversity regularization term and a supervision module. Experimental results on public recommendation datasets demonstrate that our approach outperforms all other baselines in terms of long-term performance, validating its user-oriented exploration effectiveness. Meanwhile, further analyses reveal our approach's benefits of improved performance for low-activity users as well as increased fairness among users.

cs.IR↗

arXiv2024

Effective In-Context Example Selection through Data Compression

In-context learning has been extensively validated in large language models. However, the mechanism and selection strategy for in-context example selection, which is a crucial ingredient in this approach, lacks systematic and in-depth research. In this paper, we propose a data compression approach to the selection of in-context examples. We introduce a two-stage method that can effectively choose relevant examples and retain sufficient information about the training dataset within the in-context examples. Our method shows a significant improvement of an average of 5.90% across five different real-world datasets using four language models.

cs.CL↗

arXiv2024

Integrating View Conditions for Image Synthesis

In the field of image processing, applying intricate semantic modifications within existing images remains an enduring challenge. This paper introduces a pioneering framework that integrates viewpoint information to enhance the control of image editing tasks, especially for interior design scenes. By surveying existing object editing methodologies, we distill three essential criteria -- consistency, controllability, and harmony -- that should be met for an image editing method. In contrast to previous approaches, our framework takes the lead in satisfying all three requirements for addressing the challenge of image synthesis. Through comprehensive experiments, encompassing both quantitative assessments and qualitative comparisons with contemporary state-of-the-art methods, we present compelling evidence of our framework's superior performance across multiple dimensions. This work establishes a promising avenue for advancing image synthesis techniques and empowering precise object modifications while preserving the visual coherence of the entire composition.

cs.CV↗

arXiv2024

Combining Retrieval and Classification: Balancing Efficiency and Accuracy in Duplicate Bug Report Detection

In the realm of Duplicate Bug Report Detection (DBRD), conventional methods primarily focus on statically analyzing bug databases, often disregarding the running time of the model. In this context, complex models, despite their high accuracy potential, can be time-consuming, while more efficient models may compromise on accuracy. To address this issue, we propose a transformer-based system designed to strike a balance between time efficiency and accuracy performance. The existing methods primarily address it as either a retrieval or classification task. However, our hybrid approach leverages the strengths of both models. By utilizing the retrieval model, we can perform initial sorting to reduce the candidate set, while the classification model allows for more precise and accurate classification. In our assessment of commonly used models for retrieval and classification tasks, sentence BERT and RoBERTa outperform other baseline models in retrieval and classification, respectively. To provide a comprehensive evaluation of performance and efficiency, we conduct rigorous experimentation on five public datasets. The results reveal that our system maintains accuracy comparable to a classification model, significantly outperforming it in time efficiency and only slightly behind a retrieval model in time, thereby achieving an effective trade-off between accuracy and efficiency.

cs.SE↗

arXiv2024

Electron mobility of SnO2 from first principles

The transparent conducting oxide SnO2 is a wide bandgap semiconductor that is easily n-type doped and widely used in various electronic and optoelectronic applications. Experimental reports of the electron mobility of this material vary widely depending on the growth conditions and doping concentrations. In this work, we calculate the electron mobility of SnO2 from first principles to examine the temperature- and doping-concentration dependence, and to elucidate the scattering mechanisms that limit transport. We include both electron-phonon scattering and electron-ionized impurity scattering to accurately model scattering in a doped semiconductor. We find a strongly anisotropic mobility that favors transport in the direction parallel to the c-axis. At room temperature and intrinsic carrier concentrations, the low-energy polar-optical phonon modes dominate scattering, while ionized-impurity scattering dominates above 10^18 cm^-3.

cond-mat.mtrl-sci↗

arXiv2024

Nonexistence of Time-periodic Solutions of the Dirac Equation in Kerr-Newman-(A)dS Spacetime

In this paper, we study the nonexistence of nontrivial time-periodic solutions of the Dirac equation in Kerr-Newman-(A)dS spacetime. In the non-extreme Kerr-Newman-dS spacetime, we prove that there is no nontrivial $L^p$ integrable Dirac particle for arbitrary $(λ,p)\in \mathbb{R}\times[2,+\infty)$. In the extreme Kerr-Newman-dS and extreme Kerr-Newman-AdS spacetime, we show the equation relations between the energy eigenvalue $ω$, the horizon radius, the angular momentum, the electric charge and the cosmological constant if there exists nontrivial $L^p$ integrable time-periodic solution of the Dirac equation, and further give the necessary conditions for the existence of nontrivial solutions.

gr-qc↗

arXiv2024

Evaluation of Machine Translation Based on Semantic Dependencies and Keywords

In view of the fact that most of the existing machine translation evaluation algorithms only consider the lexical and syntactic information, but ignore the deep semantic information contained in the sentence, this paper proposes a computational method for evaluating the semantic correctness of machine translations based on reference translations and incorporating semantic dependencies and sentence keyword information. Use the language technology platform developed by the Social Computing and Information Retrieval Research Center of Harbin Institute of Technology to conduct semantic dependency analysis and keyword analysis on sentences, and obtain semantic dependency graphs, keywords, and weight information corresponding to keywords. It includes all word information with semantic dependencies in the sentence and keyword information that affects semantic information. Construct semantic association pairs including word and dependency multi-features. The key semantics of the sentence cannot be highlighted in the semantic information extracted through semantic dependence, resulting in vague semantics analysis. Therefore, the sentence keyword information is also included in the scope of machine translation semantic evaluation. To achieve a comprehensive and in-depth evaluation of the semantic correctness of sentences, the experimental results show that the accuracy of the evaluation algorithm has been improved compared with similar methods, and it can more accurately measure the semantic correctness of machine translation.

cs.CL↗

arXiv2024

UniSAR: Modeling User Transition Behaviors between Search and Recommendation

Nowadays, many platforms provide users with both search and recommendation services as important tools for accessing information. The phenomenon has led to a correlation between user search and recommendation behaviors, providing an opportunity to model user interests in a fine-grained way. Existing approaches either model user search and recommendation behaviors separately or overlook the different transitions between user search and recommendation behaviors. In this paper, we propose a framework named UniSAR that effectively models the different types of fine-grained behavior transitions for providing users a Unified Search And Recommendation service. Specifically, UniSAR models the user transition behaviors between search and recommendation through three steps: extraction, alignment, and fusion, which are respectively implemented by transformers equipped with pre-defined masks, contrastive learning that aligns the extracted fine-grained user transitions, and cross-attentions that fuse different transitions. To provide users with a unified service, the learned representations are fed into the downstream search and recommendation models. Joint learning on both search and recommendation data is employed to utilize the knowledge and enhance each other. Experimental results on two public datasets demonstrated the effectiveness of UniSAR in terms of enhancing both search and recommendation simultaneously. The experimental analysis further validates that UniSAR enhances the results by successfully modeling the user transition behaviors between search and recommendation.

cs.IR↗

arXiv2024

Trajectory-Oriented Policy Optimization with Sparse Rewards

Mastering deep reinforcement learning (DRL) proves challenging in tasks featuring scant rewards. These limited rewards merely signify whether the task is partially or entirely accomplished, necessitating various exploration actions before the agent garners meaningful feedback. Consequently, the majority of existing DRL exploration algorithms struggle to acquire practical policies within a reasonable timeframe. To address this challenge, we introduce an approach leveraging offline demonstration trajectories for swifter and more efficient online RL in environments with sparse rewards. Our pivotal insight involves treating offline demonstration trajectories as guidance, rather than mere imitation, allowing our method to learn a policy whose distribution of state-action visitation marginally matches that of offline demonstrations. We specifically introduce a novel trajectory distance relying on maximum mean discrepancy (MMD) and cast policy optimization as a distance-constrained optimization problem. We then illustrate that this optimization problem can be streamlined into a policy-gradient algorithm, integrating rewards shaped by insights from offline demonstrations. The proposed algorithm undergoes evaluation across extensive discrete and continuous control tasks with sparse and misleading rewards. The experimental findings demonstrate the significant superiority of our proposed algorithm over baseline methods concerning diverse exploration and the acquisition of an optimal policy.

cs.LG↗

arXiv2024

To Search or to Recommend: Predicting Open-App Motivation with Neural Hawkes Process

Incorporating Search and Recommendation (S&R) services within a singular application is prevalent in online platforms, leading to a new task termed open-app motivation prediction, which aims to predict whether users initiate the application with the specific intent of information searching, or to explore recommended content for entertainment. Studies have shown that predicting users' motivation to open an app can help to improve user engagement and enhance performance in various downstream tasks. However, accurately predicting open-app motivation is not trivial, as it is influenced by user-specific factors, search queries, clicked items, as well as their temporal occurrences. Furthermore, these activities occur sequentially and exhibit intricate temporal dependencies. Inspired by the success of the Neural Hawkes Process (NHP) in modeling temporal dependencies in sequences, this paper proposes a novel neural Hawkes process model to capture the temporal dependencies between historical user browsing and querying actions. The model, referred to as Neural Hawkes Process-based Open-App Motivation prediction model (NHP-OAM), employs a hierarchical transformer and a novel intensity function to encode multiple factors, and open-app motivation prediction layer to integrate time and user-specific information for predicting users' open-app motivations. To demonstrate the superiority of our NHP-OAM model and construct a benchmark for the Open-App Motivation Prediction task, we not only extend the public S&R dataset ZhihuRec but also construct a new real-world Open-App Motivation Dataset (OAMD). Experiments on these two datasets validate NHP-OAM's superiority over baseline models. Further downstream application experiments demonstrate NHP-OAM's effectiveness in predicting users' Open-App Motivation, highlighting the immense application value of NHP-OAM.

cs.IR↗

arXiv2024

Search for GeV gamma-ray emission from the possible TeV-bright red dwarfs with Fermi-LAT

Red dwarfs have been suggested to be among the possible astrophysical species accelerating particles and emitting TeV $γ$-rays. As an effort to search for the GeV $γ$-ray counterparts of the suggested TeV emission from eight red dwarfs, we analyse the 0.2--500 GeV $γ$-ray emission of the regions covering them exploiting the $\sim$13.6 yr Pass 8 data of the Fermi Large Area Telescope. A GeV $γ$-ray emission excess with significance of 3.8$σ$ is detected in the direction of the red dwarf V962 Tau. This emission contains V962 Tau in 1$σ$ error radius and is independent of the catalog source. However, the stellar flare scenario can hardly explain the total energy and lightcurve derived from the $γ$-ray emission in view of the spectral analysis. We also analyse the lightcurves in the positions of the eight red dwarfs and no time bin with significance $>$5$σ$ is found. Therefore, no significant emission from the red dwarfs could be concluded to be detected by Fermi-LAT.

astro-ph.HE↗

arXiv2024

Layer dependent topological phases and transitions in TaRhTe$_4$: From monolayer and bilayer to bulk

The recently synthesized ternary quasi-2D material TaRhTe$_4$ is a bulk Weyl semimetal with an intrinsically layered structure, which poses the question how the topology of its electronic structure depends on layers separations. Experimentally these separations may be changed for instance by intercalation of the bulk, or by exfoliation to reach monolayer or few-layer structures. Here we show that in the monolayer limit a quantum spin Hall insulator (QSHI) state emerges, employing density functional calculations as well as a minimal four-orbital tight-binding model that we develop. Even for weak spin-orbit couplings the QSHI is present, which has an interesting edge state that features Rashba-split bands with quadratic band minima. Further we find that a weak topological insulator (WTI) manifests in the bilayer system due to sizable intralayer hopping, contrary to the common lore that only weak interlayer interactions between stacked QSHIs lead to WTIs. Stacked bilayers give rise to a phase diagram as function of the interlayer separation that comprises a Weyl semimetal, WTI and normal insulator phases. These insights on the evolution of topology with dimension can be transferred to the family of layered ternary transition metal tellurides.

cond-mat.mtrl-sci↗