arXiv subjects

Chen Ma

Publications and source records attributed to Chen Ma.

At least 127 records · Page 7Linked to original sources

arXiv2023

Gray-body factor and absorption of the Dirac field in ESTGB gravity

The gray-body factor and the absorption cross section of the 4D ESTGB gravity with a mode of nonlinear electrodynamics for the massless Dirac field are studied in this paper. The magnetic charge value varies between $-2^{(\frac{5}{3})}/3$ and $0$ as well as the ADM mass is set to $1$, which corresponds to a non-extreme black hole. The gray-body factor is obtained using the semi-analytic WKB method after solving the massless Dirac equation. When the absolute value of magnetic charge is increasing, the gray-body factor $γ(ω)$ is decreasing. In addition, the partial absorption cross section and the total absorption cross section are calculated by using the partial wave method. We find that the maximum value of partial absorption cross section decreases as $κ$ increases. And the existence of magnetic charge causes the diminishing of the total absorption cross section. Finally, we find that the absorption cross section of the Dirac field is more sensitive to electric charge than magnetic charge by comparing the absorption cross section of the Reissner-Nordstr$\rm\ddot{o}$m and ESTGB-NLED black holes.

gr-qc↗

arXiv2023

Shadow, absorption and Hawking radiation of a Schwarzschild black hole surrounded by a cloud of strings in Rastall gravity

This paper studies the black hole shadow, absorption cross section, and Hawking radiation of a massless scalar field in the background of a static spherically symmetric black hole spacetime that is surrounded by a cloud of strings in Rastall gravity. Specifically, the effects of the parameters $a$ and $β$ on the photon sphere and shadow radii are investigated. The results show that as the negative parameter $β$ decreases, the photon sphere and shadow radii change in an N-shape. In addition, the absorption cross section obtained after solving the massless Klein-Gordon equation is calculated using the sinc approximation and the partial waves method. We compare the absorption cross section obtained by the sinc approximation and the partial waves method, and find it to be exceptionally consistent in the mid-to-high frequency region. Furthermore, the effects of parameters $a$ and $β$ on absorption are examined in detail. Finally, we study in detail the effects of the parameters $a$, $β$ and $l$ on the Hawking radiation power emission spectrum of the considered black hole. It turns out that the string parameter $a$ always suppresses the power emission spectrum, indicating that such black holes live longer when the string parameter $a$ is increased while other parameters are fixed.

gr-qc↗

arXiv2023

Mutually Guided Few-shot Learning for Relational Triple Extraction

Knowledge graphs (KGs), containing many entity-relation-entity triples, provide rich information for downstream applications. Although extracting triples from unstructured texts has been widely explored, most of them require a large number of labeled instances. The performance will drop dramatically when only few labeled data are available. To tackle this problem, we propose the Mutually Guided Few-shot learning framework for Relational Triple Extraction (MG-FTE). Specifically, our method consists of an entity-guided relation proto-decoder to classify the relations firstly and a relation-guided entity proto-decoder to extract entities based on the classified relations. To draw the connection between entity and relation, we design a proto-level fusion module to boost the performance of both entity extraction and relation classification. Moreover, a new cross-domain few-shot triple extraction task is introduced. Extensive experiments show that our method outperforms many state-of-the-art methods by 12.6 F1 score on FewRel 1.0 (single-domain) and 20.5 F1 score on FewRel 2.0 (cross-domain).

cs.CL↗

arXiv2023

WSFE: Wasserstein Sub-graph Feature Encoder for Effective User Segmentation in Collaborative Filtering

Maximizing the user-item engagement based on vectorized embeddings is a standard procedure of recent recommender models. Despite the superior performance for item recommendations, these methods however implicitly deprioritize the modeling of user-wise similarity in the embedding space; consequently, identifying similar users is underperforming, and additional processing schemes are usually required otherwise. To avoid thorough model re-training, we propose WSFE, a model-agnostic and training-free representation encoder, to be flexibly employed on the fly for effective user segmentation. Underpinned by the optimal transport theory, the encoded representations from WSFE present a matched user-wise similarity/distance measurement between the realistic and embedding space. We incorporate WSFE into six state-of-the-art recommender models and conduct extensive experiments on six real-world datasets. The empirical analyses well demonstrate the superiority and generality of WSFE to fuel multiple downstream tasks with diverse underlying targets in recommendation.

cs.IR↗

arXiv2023

A string-theoretical analog of non-maximal chaos in some Sachdev-Ye-Kitaev-like models

Very recently two of the present authors have studied the chaos exponent of some Sachdev-Ye-Kitaev (SYK)-like models for arbitrary interaction strength [1]. These models carry supersymmetric (SUSY) or SUSY-like structures. Namely, bosons and Majorana fermions are both present and each of them interacts with $(q-1)$ particles, but the model is not necessarily supersymmetric. It was found that the chaos exponents in different models, no matter whether they carry SUSY(-like) structures or not, all follow a universal single-parameter scaling law for large $q$, and by tuning that parameter continuously a flow from maximally chaotic to completely regular motion results. Here we report a string-theoretical analog of this chaotic phenomenon. Specifically, we consider closed string scattering near the two-sided AdS black hole, whose amplitude grows exponentially in the Schwarzschild time, with a rate determined by the Regge spin of the Pomeron exchanged during string scattering. We calculate the Pomeron Regge spin for strings of different types, including the bosonic string, the type II superstring and the heterotic superstring. We find that the Pomeron Regge spin also displays a single-parameter scaling behavior independent of string types, with the parameter depending on the string length and the length scale characterizing the spacetime curvature; moreover, the scaling function has the same limiting behaviors as that for the chaos exponent of SYK-like models. Remarkably, the flow from maximally chaotic to completely regular motion in SYK-like models corresponds to the flow of the Pomeron Regge spin from $2$ to $1$.

hep-th↗

arXiv2023

Sim2Rec: A Simulator-based Decision-making Approach to Optimize Real-World Long-term User Engagement in Sequential Recommender Systems

Long-term user engagement (LTE) optimization in sequential recommender systems (SRS) is shown to be suited by reinforcement learning (RL) which finds a policy to maximize long-term rewards. Meanwhile, RL has its shortcomings, particularly requiring a large number of online samples for exploration, which is risky in real-world applications. One of the appealing ways to avoid the risk is to build a simulator and learn the optimal recommendation policy in the simulator. In LTE optimization, the simulator is to simulate multiple users' daily feedback for given recommendations. However, building a user simulator with no reality-gap, i.e., can predict user's feedback exactly, is unrealistic because the users' reaction patterns are complex and historical logs for each user are limited, which might mislead the simulator-based recommendation policy. In this paper, we present a practical simulator-based recommender policy training approach, Simulation-to-Recommendation (Sim2Rec) to handle the reality-gap problem for LTE optimization. Specifically, Sim2Rec introduces a simulator set to generate various possibilities of user behavior patterns, then trains an environment-parameter extractor to recognize users' behavior patterns in the simulators. Finally, a context-aware policy is trained to make the optimal decisions on all of the variants of the users based on the inferred environment-parameters. The policy is transferable to unseen environments (e.g., the real world) directly as it has learned to recognize all various user behavior patterns and to make the correct decisions based on the inferred environment-parameters. Experiments are conducted in synthetic environments and a real-world large-scale ride-hailing platform, DidiChuxing. The results show that Sim2Rec achieves significant performance improvement, and produces robust recommendations in unseen environments.

cs.IR↗

arXiv2023

Structure Aware Incremental Learning with Personalized Imitation Weights for Recommender Systems

Recommender systems now consume large-scale data and play a significant role in improving user experience. Graph Neural Networks (GNNs) have emerged as one of the most effective recommender system models because they model the rich relational information. The ever-growing volume of data can make training GNNs prohibitively expensive. To address this, previous attempts propose to train the GNN models incrementally as new data blocks arrive. Feature and structure knowledge distillation techniques have been explored to allow the GNN model to train in a fast incremental fashion while alleviating the catastrophic forgetting problem. However, preserving the same amount of the historical information for all users is sub-optimal since it fails to take into account the dynamics of each user's change of preferences. For the users whose interests shift substantially, retaining too much of the old knowledge can overly constrain the model, preventing it from quickly adapting to the users' novel interests. In contrast, for users who have static preferences, model performance can benefit greatly from preserving as much of the user's long-term preferences as possible. In this work, we propose a novel training strategy that adaptively learns personalized imitation weights for each user to balance the contribution from the recent data and the amount of knowledge to be distilled from previous time periods. We demonstrate the effectiveness of learning imitation weights via a comparison on five diverse datasets for three state-of-art structure distillation based recommender systems. The performance shows consistent improvement over competitive incremental learning techninques.

cs.IR↗

arXiv2023

Dynamically Expandable Graph Convolution for Streaming Recommendation

Personalized recommender systems have been widely studied and deployed to reduce information overload and satisfy users' diverse needs. However, conventional recommendation models solely conduct a one-time training-test fashion and can hardly adapt to evolving demands, considering user preference shifts and ever-increasing users and items in the real world. To tackle such challenges, the streaming recommendation is proposed and has attracted great attention recently. Among these, continual graph learning is widely regarded as a promising approach for the streaming recommendation by academia and industry. However, existing methods either rely on the historical data replay which is often not practical under increasingly strict data regulations, or can seldom solve the \textit{over-stability} issue. To overcome these difficulties, we propose a novel \textbf{D}ynamically \textbf{E}xpandable \textbf{G}raph \textbf{C}onvolution (DEGC) algorithm from a \textit{model isolation} perspective for the streaming recommendation which is orthogonal to previous methods. Based on the motivation of disentangling outdated short-term preferences from useful long-term preferences, we design a sequence of operations including graph convolution pruning, refining, and expanding to only preserve beneficial long-term preference-related parameters and extract fresh short-term preferences. Moreover, we model the temporal user preference, which is utilized as user embedding initialization, for better capturing the individual-level preference shifts. Extensive experiments on the three most representative GCN-based recommendation models and four industrial datasets demonstrate the effectiveness and robustness of our method.

cs.IR↗

arXiv2023

Feature Representation Learning for Click-through Rate Prediction: A Review and New Perspectives

Representation learning has been a critical topic in machine learning. In Click-through Rate Prediction, most features are represented as embedding vectors and learned simultaneously with other parameters in the model. With the development of CTR models, feature representation learning has become a trending topic and has been extensively studied by both industrial and academic researchers in recent years. This survey aims at summarizing the feature representation learning in a broader picture and pave the way for future research. To achieve such a goal, we first present a taxonomy of current research methods on feature representation learning following two main issues: (i) which feature to represent and (ii) how to represent these features. Then we give a detailed description of each method regarding these two issues. Finally, the review concludes with a discussion on the future directions of this field.

cs.IR↗

arXiv2022

Hyperspherical Quantization: Toward Smaller and More Accurate Models

Model quantization enables the deployment of deep neural networks under resource-constrained devices. Vector quantization aims at reducing the model size by indexing model weights with full-precision embeddings, i.e., codewords, while the index needs to be restored to 32-bit during computation. Binary and other low-precision quantization methods can reduce the model size up to 32$\times$, however, at the cost of a considerable accuracy drop. In this paper, we propose an efficient framework for ternary quantization to produce smaller and more accurate compressed models. By integrating hyperspherical learning, pruning and reinitialization, our proposed Hyperspherical Quantization (HQ) method reduces the cosine distance between the full-precision and ternary weights, thus reducing the bias of the straight-through gradient estimator during ternary quantization. Compared with existing work at similar compression levels ($\sim$30$\times$, $\sim$40$\times$), our method significantly improves the test accuracy and reduces the model size.

cs.CV↗

arXiv2022

Adapting Triplet Importance of Implicit Feedback for Personalized Recommendation

Implicit feedback is frequently used for developing personalized recommendation services due to its ubiquity and accessibility in real-world systems. In order to effectively utilize such information, most research adopts the pairwise ranking method on constructed training triplets (user, positive item, negative item) and aims to distinguish between positive items and negative items for each user. However, most of these methods treat all the training triplets equally, which ignores the subtle difference between different positive or negative items. On the other hand, even though some other works make use of the auxiliary information (e.g., dwell time) of user behaviors to capture this subtle difference, such auxiliary information is hard to obtain. To mitigate the aforementioned problems, we propose a novel training framework named Triplet Importance Learning (TIL), which adaptively learns the importance score of training triplets. We devise two strategies for the importance score generation and formulate the whole procedure as a bilevel optimization, which does not require any rule-based design. We integrate the proposed training procedure with several Matrix Factorization (MF)- and Graph Neural Network (GNN)-based recommendation models, demonstrating the compatibility of our framework. Via a comparison using three real-world datasets with many state-of-the-art methods, we show that our proposed method outperforms the best existing models by 3-21\% in terms of Recall@k for the top-k recommendation.

cs.IR↗

arXiv2022

Artificial Intelligence Security Competition (AISC)

The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems. To accelerate the research on AI security, the Artificial Intelligence Security Competition (AISC) was organized by the Zhongguancun Laboratory, China Industrial Control Systems Cyber Emergency Response Team, Institute for Artificial Intelligence, Tsinghua University, and RealAI as part of the Zhongguancun International Frontier Technology Innovation Competition (https://www.zgc-aisc.com/en). The competition consists of three tracks, including Deepfake Security Competition, Autonomous Driving Security Competition, and Face Recognition Security Competition. This report will introduce the competition rules of these three tracks and the solutions of top-ranking teams in each track.

cs.CR↗

arXiv2022

A route from maximal chaoticity to integrability

We study the chaos exponent of some variants of the Sachdev-Ye-Kitaev (SYK) model, namely, the $\Ns=1$ supersymmetry (SUSY)-SYK model and its sibling, the $(N|M)$-SYK model which is not supersymmetric in general, for arbitrary interaction strength. We find that for large $q$ the chaos exponent of these variants, as well as the SYK and the $\Ns=2$ SUSY-SYK model, all follow a single-parameter scaling law. By quantitative arguments we further make a conjecture, i.e. that the found scaling law might hold for general one-dimensional (1D) SYK-like models with large $q$. This points out a universal route from maximal chaos towards completely regular or integrable motion in the SYK model and its 1D variants.

cond-mat.str-el↗

arXiv2022

Intent-aware Multi-source Contrastive Alignment for Tag-enhanced Recommendation

To offer accurate and diverse recommendation services, recent methods use auxiliary information to foster the learning process of user and item representations. Many SOTA methods fuse different sources of information (user, item, knowledge graph, tags, etc.) into a graph and use Graph Neural Networks to introduce the auxiliary information through the message passing paradigm. In this work, we seek an alternative framework that is light and effective through self-supervised learning across different sources of information, particularly for the commonly accessible item tag information. We use a self-supervision signal to pair users with the auxiliary information associated with the items they have interacted with before. To achieve the pairing, we create a proxy training task. For a given item, the model predicts the correct pairing between the representations obtained from the users that have interacted with this item and the assigned tags. This design provides an efficient solution, using the auxiliary information directly to enhance the quality of user and item embeddings. User behavior in recommendation systems is driven by the complex interactions of many factors behind the decision-making processes. To make the pairing process more fine-grained and avoid embedding collapse, we propose an intent-aware self-supervised pairing process where we split the user embeddings into multiple sub-embedding vectors. Each sub-embedding vector captures a specific user intent via self-supervised alignment with a particular cluster of tags. We integrate our designed framework with various recommendation models, demonstrating its flexibility and compatibility. Through comparison with numerous SOTA methods on seven real-world datasets, we show that our method can achieve better performance while requiring less training time. This indicates the potential of applying our approach on web-scale datasets.

cs.IR↗

arXiv2022

Multi-FR: A Multi-objective Optimization Framework for Multi-stakeholder Fairness-aware Recommendation

Nowadays, most online services are hosted on multi-stakeholder marketplaces, where consumers and producers may have different objectives. Conventional recommendation systems, however, mainly focus on maximizing consumers' satisfaction by recommending the most relevant items to each individual. This may result in unfair exposure of items, thus jeopardizing producer benefits. Additionally, they do not care whether consumers from diverse demographic groups are equally satisfied. To address these limitations, we propose a multi-objective optimization framework for fairness-aware recommendation, Multi-FR, that adaptively balances accuracy and fairness for various stakeholders with Pareto optimality guarantee. We first propose four fairness constraints on consumers and producers. In order to train the whole framework in an end-to-end way, we utilize the smooth rank and stochastic ranking policy to make these fairness criteria differentiable and friendly to back-propagation. Then, we adopt the multiple gradient descent algorithm to generate a Pareto set of solutions, from which the most appropriate one is selected by the Least Misery Strategy. The experimental results demonstrate that Multi-FR largely improves recommendation fairness on multiple stakeholders over the state-of-the-art approaches while maintaining almost the same recommendation accuracy. The training efficiency study confirms our model's ability to simultaneously optimize different fairness constraints for many stakeholders efficiently.

cs.IR↗

arXiv2022

Translucency and negative temperature-dependence for the slip length of water on graphene

Carbonous materials, such as graphene and carbon nanotube, have attracted tremendous attention in the fields of nanofluidics due to the slip at the interface between solid and liquid. The dependence of slip length for water on the types of supporting substrates and thickness of carbonous layer, which is critical for applications such as sustainable cooling of electronic devices, remains unknown. In this paper, using colloidal probe atomic force microscope, we measured the slip length of water on graphene ls supported by hydrophilic and hydrophobic substrates, i.e., SiO2 and octadecyltrimethoxysilane (OTS). The ls on single-layer graphene supported by SiO2 is found to be 1.6~1.9 nm, and by OTS is 8.5~0.9 nm. With the thickness of few-layer graphene increases to 3~4 layers, both ls gradually converge to the value of graphite (4.3~3.5 nm). Such thickness dependence is termed slip length translucency. Further, ls is found to decrease by about 70% with the temperature increases from 300 K to 350 K for 2-layer graphene supported by SiO2. These observations are explained by analysis based on Green-Kubo relation and McLachlan theory. Our results provide the first set of reference values for the slip length of water on supported few-layer graphene. They can not only serve as a direct experimental reference for solid-liquid interaction, but also provide guideline for the design of nanofluidics-based devices, for example the thermo-mechanical nanofluidic devices.

physics.flu-dyn↗

arXiv2022

Learning Binarized Graph Representations with Multi-faceted Quantization Reinforcement for Top-K Recommendation

Learning vectorized embeddings is at the core of various recommender systems for user-item matching. To perform efficient online inference, representation quantization, aiming to embed the latent features by a compact sequence of discrete numbers, recently shows the promising potentiality in optimizing both memory and computation overheads. However, existing work merely focuses on numerical quantization whilst ignoring the concomitant information loss issue, which, consequently, leads to conspicuous performance degradation. In this paper, we propose a novel quantization framework to learn Binarized Graph Representations for Top-K Recommendation (BiGeaR). BiGeaR introduces multi-faceted quantization reinforcement at the pre-, mid-, and post-stage of binarized representation learning, which substantially retains the representation informativeness against embedding binarization. In addition to saving the memory footprint, BiGeaR further develops solid online inference acceleration with bitwise operations, providing alternative flexibility for the realistic deployment. The empirical results over five large real-world benchmarks show that BiGeaR achieves about 22%~40% performance improvement over the state-of-the-art quantization-based recommender system, and recovers about 95%~102% of the performance capability of the best full-precision counterpart with over 8x time and space reduction.

cs.IR↗

arXiv2022

Unbiased Implicit Feedback via Bi-level Optimization

Implicit feedback is widely leveraged in recommender systems since it is easy to collect and provides weak supervision signals. Recent works reveal a huge gap between the implicit feedback and user-item relevance due to the fact that implicit feedback is also closely related to the item exposure. To bridge this gap, existing approaches explicitly model the exposure and propose unbiased estimators to improve the relevance. Unfortunately, these unbiased estimators suffer from the high gradient variance, especially for long-tail items, leading to inaccurate gradient updates and degraded model performance. To tackle this challenge, we propose a low-variance unbiased estimator from a probabilistic perspective, which effectively bounds the variance of the gradient. Unlike previous works which either estimate the exposure via heuristic-based strategies or use a large biased training set, we propose to estimate the exposure via an unbiased small-scale validation set. Specifically, we first parameterize the user-item exposure by incorporating both user and item information, and then construct an unbiased validation set from the biased training set. By leveraging the unbiased validation set, we adopt bi-level optimization to automatically update exposure-related parameters along with recommendation model parameters during the learning. Experiments on two real-world datasets and two semi-synthetic datasets verify the effectiveness of our method.

cs.IR↗