arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 1,315 records · Page 73Linked to original sources

arXiv2022

MovieMat: Context-aware Movie Recommendation with Matrix Factorization by Matrix Fitting

Movie Recommender System is widely applied in commercial environments such as NetFlix and Tubi. Classic recommender models utilize technologies such as collaborative filtering, learning to rank, matrix factorization and deep learning models to achieve lower marketing expenses and higher revenues. However, audience of movies have different ratings of the same movie in different contexts. Important movie watching contexts include audience mood, location, weather, etc. Tobe able to take advantage of contextual information is of great benefit to recommender builders. However, popular techniques such as tensor factorization consumes an impractical amount of storage, which greatly reduces its feasibility in real world environment. In this paper, we take advantage of the MatMat framework, which factorizes matrices by matrix fitting to build a context-aware movie recommender system that is superior to classic matrix factorization and comparable in the fairness metric.

cs.IR↗

arXiv2022

Extremal GloVe: Theoretically Accurate Distributed Word Embedding by Tail Inference

Distributed word embeddings such as Word2Vec and GloVe have been widely adopted in industrial context settings. Major technical applications of GloVe include recommender systems and natural language processing. The fundamental theory behind GloVe relies on the selection of a weighting function in the weighted least squres formulation that computes the powered ratio of word occurrence count and the maximum word count in the corpus. However, the initial formulation of GloVe is not theoretically sound in two aspects, namely the selection of the weighting function and its power exponent is ad-hoc. In this paper, we utilize the theory of extreme value analysis and propose a theoretically accurate version of GloVe. By reformulating the weighted least squares loss function as the expected loss function and accurately choosing the power exponent, we create a theoretically accurate version of GloVe. We demonstrate the competitiveness of our algorithm and show that the initial formulation of GloVe with the suggested optimal parameter can be viewed as a special case of our paradigm.

cs.CL↗

arXiv2022

RankMat : Matrix Factorization with Calibrated Distributed Embedding and Fairness Enhancement

Matrix Factorization is a widely adopted technique in the field of recommender system. Matrix Factorization techniques range from SVD, LDA, pLSA, SVD++, MatRec, Zipf Matrix Factorization and Item2Vec. In recent years, distributed word embeddings have inspired innovation in the area of recommender systems. Word2vec and GloVe have been especially emphasized in many industrial application scenario such as Xiaomi's recommender system. In this paper, we propose a new matrix factorization inspired by the theory of power law and GloVe. Instead of the exponential nature of GloVe model, we take advantage of Pareto Distribution to model our loss function. Our method is explainable in theory and easy-to-implement in practice. In the experiment section, we prove our approach is superior to vanilla matrix factorization technique and comparable with GloVe-based model in both accuracy and fairness metrics.

cs.IR↗

arXiv2022

KL-Mat : Fair Recommender System via Information Geometry

Recommender system has intrinsic problems such as sparsity and fairness. Although it has been widely adopted for the past decades, research on fairness of recommendation algorithms has been largely neglected until recently. One important paradigm for resolving the issue is regularization. However, researchers have not been able to come up with a consensusly agreed regularization term like regularization framework in other fields such as Lasso or Ridge Regression. In this paper, we borrow concepts from information geometry and propose a new regularization-based fair algorithm called KL-Mat. The algorithmic technique leads to a more robust performance in accuracy performance such as MAE. More importantly, the algorithm produces much fairer results than vanilla matrix factorization approach. KL-Mat is fast, easy-to-implement and explainable.

cs.IR↗

arXiv2022

Self-recoverable Adversarial Examples: A New Effective Protection Mechanism in Social Networks

Malicious intelligent algorithms greatly threaten the security of social users' privacy by detecting and analyzing the uploaded photos to social network platforms. The destruction to DNNs brought by the adversarial attack sparks the potential that adversarial examples serve as a new protection mechanism for privacy security in social networks. However, the existing adversarial example does not have recoverability for serving as an effective protection mechanism. To address this issue, we propose a recoverable generative adversarial network to generate self-recoverable adversarial examples. By modeling the adversarial attack and recovery as a united task, our method can minimize the error of the recovered examples while maximizing the attack ability, resulting in better recoverability of adversarial examples. To further boost the recoverability of these examples, we exploit a dimension reducer to optimize the distribution of adversarial perturbation. The experimental results prove that the adversarial examples generated by the proposed method present superior recoverability, attack ability, and robustness on different datasets and network architectures, which ensure its effectiveness as a protection mechanism in social networks.

cs.CV↗

arXiv2022

Causal Transportability for Visual Recognition

Visual representations underlie object recognition tasks, but they often contain both robust and non-robust features. Our main observation is that image classifiers may perform poorly on out-of-distribution samples because spurious correlations between non-robust features and labels can be changed in a new environment. By analyzing procedures for out-of-distribution generalization with a causal graph, we show that standard classifiers fail because the association between images and labels is not transportable across settings. However, we then show that the causal effect, which severs all sources of confounding, remains invariant across domains. This motivates us to develop an algorithm to estimate the causal effect for image classification, which is transportable (i.e., invariant) across source and target environments. Without observing additional variables, we show that we can derive an estimand for the causal effect under empirical assumptions using representations in deep models as proxies. Theoretical analysis, empirical results, and visualizations show that our approach captures causal invariances and improves overall generalization.

cs.CV↗

arXiv2022

Analyzing the Impact of Undersampling on the Benchmarking and Configuration of Evolutionary Algorithms

The stochastic nature of iterative optimization heuristics leads to inherently noisy performance measurements. Since these measurements are often gathered once and then used repeatedly, the number of collected samples will have a significant impact on the reliability of algorithm comparisons. We show that care should be taken when making decisions based on limited data. Particularly, we show that the number of runs used in many benchmarking studies, e.g., the default value of 15 suggested by the COCO environment, can be insufficient to reliably rank algorithms on well-known numerical optimization benchmarks. Additionally, methods for automated algorithm configuration are sensitive to insufficient sample sizes. This may result in the configurator choosing a `lucky' but poor-performing configuration despite exploring better ones. We show that relying on mean performance values, as many configurators do, can require a large number of runs to provide accurate comparisons between the considered configurations. Common statistical tests can greatly improve the situation in most cases but not always. We show examples of performance losses of more than 20%, even when using statistical races to dynamically adjust the number of runs, as done by irace. Our results underline the importance of appropriately considering the statistical distribution of performance values.

cs.NE↗

arXiv2022

Preference Enhanced Social Influence Modeling for Network-Aware Cascade Prediction

Network-aware cascade size prediction aims to predict the final reposted number of user-generated information via modeling the propagation process in social networks. Estimating the user's reposting probability by social influence, namely state activation plays an important role in the information diffusion process. Therefore, Graph Neural Networks (GNN), which can simulate the information interaction between nodes, has been proved as an effective scheme to handle this prediction task. However, existing studies including GNN-based models usually neglect a vital factor of user's preference which influences the state activation deeply. To that end, we propose a novel framework to promote cascade size prediction by enhancing the user preference modeling according to three stages, i.e., preference topics generation, preference shift modeling, and social influence activation. Our end-to-end method makes the user activating process of information diffusion more adaptive and accurate. Extensive experiments on two large-scale real-world datasets have clearly demonstrated the effectiveness of our proposed model compared to state-of-the-art baselines.

cs.SI↗

arXiv2022

IOHexperimenter: Benchmarking Platform for Iterative Optimization Heuristics

We present IOHexperimenter, the experimentation module of the IOHprofiler project, which aims at providing an easy-to-use and highly customizable toolbox for benchmarking iterative optimization heuristics such as local search, evolutionary and genetic algorithms, Bayesian optimization techniques, etc. IOHexperimenter can be used as a stand-alone tool or as part of a benchmarking pipeline that uses other components of IOHprofiler such as IOHanalyzer, the module for interactive performance analysis and visualization. IOHexperimenter provides an efficient interface between optimization problems and their solvers while allowing for granular logging of the optimization process. These logs are fully compatible with existing tools for interactive data analysis, which significantly speeds up the deployment of a benchmarking pipeline. The main components of IOHexperimenter are the environment to build customized problem suites and the various logging options that allow users to steer the granularity of the data records.

cs.NE↗

arXiv2022

To Split or Not to Split: The Impact of Disparate Treatment in Classification

Disparate treatment occurs when a machine learning model yields different decisions for individuals based on a sensitive attribute (e.g., age, sex). In domains where prediction accuracy is paramount, it could potentially be acceptable to fit a model which exhibits disparate treatment. To evaluate the effect of disparate treatment, we compare the performance of split classifiers (i.e., classifiers trained and deployed separately on each group) with group-blind classifiers (i.e., classifiers which do not use a sensitive attribute). We introduce the benefit-of-splitting for quantifying the performance improvement by splitting classifiers. Computing the benefit-of-splitting directly from its definition could be intractable since it involves solving optimization problems over an infinite-dimensional functional space. Under different performance measures, we (i) prove an equivalent expression for the benefit-of-splitting which can be efficiently computed by solving small-scale convex programs; (ii) provide sharp upper and lower bounds for the benefit-of-splitting which reveal precise conditions where a group-blind classifier will always suffer from a non-trivial performance gap from the split classifiers. In the finite sample regime, splitting is not necessarily beneficial and we provide data-dependent bounds to understand this effect. Finally, we validate our theoretical results through numerical experiments on both synthetic and real-world datasets.

cs.LG↗

arXiv2022

Fairness without Imputation: A Decision Tree Approach for Fair Prediction with Missing Values

We investigate the fairness concerns of training a machine learning model using data with missing values. Even though there are a number of fairness intervention methods in the literature, most of them require a complete training set as input. In practice, data can have missing values, and data missing patterns can depend on group attributes (e.g. gender or race). Simply applying off-the-shelf fair learning algorithms to an imputed dataset may lead to an unfair model. In this paper, we first theoretically analyze different sources of discrimination risks when training with an imputed dataset. Then, we propose an integrated approach based on decision trees that does not require a separate process of imputation and learning. Instead, we train a tree with missing incorporated as attribute (MIA), which does not require explicit imputation, and we optimize a fairness-regularized objective function. We demonstrate that our approach outperforms existing fairness intervention methods applied to an imputed dataset, through several experiments on real-world datasets.

cs.LG↗

arXiv2022

Coverage and Capacity Optimization in STAR-RISs Assisted Networks: A Machine Learning Approach

Coverage and capacity are the important metrics for performance evaluation in wireless networks, while the coverage and capacity have several conflicting relationships, e.g. high transmit power contributes to large coverage but high inter-cell interference reduces the capacity performance. Therefore, in order to strike a balance between the coverage and capacity, a novel model is proposed for the coverage and capacity optimization of simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) assisted networks. To solve the coverage and capacity optimization (CCO) problem, a machine learning-based multi-objective optimization algorithm, i.e., the multi-objective proximal policy optimization (MO-PPO) algorithm, is proposed. In this algorithm, a loss function-based update strategy is the core point, which is able to calculate weights for both loss functions of coverage and capacity by a min-norm solver at each update. The numerical results demonstrate that the investigated update strategy outperforms the fixed weight-based MO algorithms.

cs.IT↗

arXiv2022

Quantum-Inspired Solvers on Mixed-Integer Linear Programming Problem

Mixed-integer linear programming (MILP) plays a crucial role in artificial intelligence, biochemistry, finance, cryptography, etc. Notwithstanding popular for decades, the researches of MILP solvers are still limited by the resource consumption caused by complexity and failure of Moore's Law. Quantum-inspired Ising machines, as a new computing paradigm, can be used to solve integer programming problems by reducing them into Ising models. Therefore, it is necessary to understand the technical evolution of quantum inspired solvers to break the bottleneck. In this paper, the concept and traditional algorithms for MILP are introduced. Then, focused on Ising model, the principle and implementations of annealers and coherent Ising machines are summarized. Finally, the paper discusses the challenges and opportunities of miniaturized solvers in the future.

quant-ph↗

arXiv2022

Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shape

3D Morphable Model (3DMM) fitting has widely benefited face analysis due to its strong 3D priori. However, previous reconstructed 3D faces suffer from degraded visual verisimilitude due to the loss of fine-grained geometry, which is attributed to insufficient ground-truth 3D shapes, unreliable training strategies and limited representation power of 3DMM. To alleviate this issue, this paper proposes a complete solution to capture the personalized shape so that the reconstructed shape looks identical to the corresponding person. Specifically, given a 2D image as the input, we virtually render the image in several calibrated views to normalize pose variations while preserving the original image geometry. A many-to-one hourglass network serves as the encode-decoder to fuse multiview features and generate vertex displacements as the fine-grained geometry. Besides, the neural network is trained by directly optimizing the visual effect, where two 3D shapes are compared by measuring the similarity between the multiview images rendered from the shapes. Finally, we propose to generate the ground-truth 3D shapes by registering RGB-D images followed by pose and shape augmentation, providing sufficient data for network training. Experiments on several challenging protocols demonstrate the superior reconstruction accuracy of our proposal on the face shape.

cs.CV↗

arXiv2022

From PHY to QoE: A Parameterized Framework Design

The rapid development of 5G communication technology has given birth to various real-time broadband communication services, such as augmented reality (AR), virtual reality (VR) and cloud games. Compared with traditional services, consumers tend to focus more on their subjective experience when utilizing these services. In the meantime, the problem of power consumption is particularly prominent in 5G and beyond. The traditional design of physical layer (PHY) receiver is based on maximizing spectrum efficiency or minimizing error, but this will no longer be the best after considering energy efficiency and these new-coming services. Therefore, this paper uses quality of experience (QoE) as the optimization criterion of the PHY algorithm. In order to establish the relationship between PHY and QoE, this paper models the end-to-end transmission from UE perspective and proposes a five-layer framework based on hierarchical analysis method, which includes system-level model, bitstream model, packet model, service quality model and experience quality model. Real data in 5G network is used to train the parameters of the involved models for each type of services, respectively. The results show that the PHY algorithms can be simplified in perspective of QoE.

cs.IT↗

arXiv2022

Federated Learning for Personalized Humor Recognition

Computational understanding of humor is an important topic under creative language understanding and modeling. It can play a key role in complex human-AI interactions. The challenge here is that human perception of humorous content is highly subjective. The same joke may receive different funniness ratings from different readers. This makes it highly challenging for humor recognition models to achieve personalization in practical scenarios. Existing approaches are generally designed based on the assumption that users have a consensus on whether a given text is humorous or not. Thus, they cannot handle diverse humor preferences well. In this paper, we propose the FedHumor approach for the recognition of humorous content in a personalized manner through Federated Learning (FL). Extending a pre-trained language model, FedHumor guides the fine-tuning process by considering diverse distributions of humor preferences from individuals. It incorporates a diversity adaptation strategy into the FL paradigm to train a personalized humor recognition model. To the best of our knowledge, FedHumor is the first text-based personalized humor recognition model through federated learning. Extensive experiments demonstrate the advantage of FedHumor in recognizing humorous texts compared to nine state-of-the-art humor recognition approaches with superior capability for handling the diversity in humor labels produced by users with diverse preferences.

cs.CL↗

arXiv2022

Semi-Supervised Wide-Angle Portraits Correction by Multi-Scale Transformer

We propose a semi-supervised network for wide-angle portraits correction. Wide-angle images often suffer from skew and distortion affected by perspective distortion, especially noticeable at the face regions. Previous deep learning based approaches need the ground-truth correction flow maps for training guidance. However, such labels are expensive, which can only be obtained manually. In this work, we design a semi-supervised scheme and build a high-quality unlabeled dataset with rich scenarios, allowing us to simultaneously use labeled and unlabeled data to improve performance. Specifically, our semi-supervised scheme takes advantage of the consistency mechanism, with several novel components such as direction and range consistency (DRC) and regression consistency (RC). Furthermore, different from the existing methods, we propose the Multi-Scale Swin-Unet (MS-Unet) based on the multi-scale swin transformer block (MSTB), which can simultaneously learn short-distance and long-distance information to avoid artifacts. Extensive experiments demonstrate that the proposed method is superior to the state-of-the-art methods and other representative baselines. The source code and dataset are available at: https://github.com/megvii-research/Portraits_Correction.

cs.CV↗

arXiv2022

Residual-Aided End-to-End Learning of Communication System without Known Channel

Leveraging powerful deep learning techniques, the end-to-end (E2E) learning of communication system is able to outperform the classical communication system. Unfortunately, this communication system cannot be trained by deep learning without known channel. To deal with this problem, a generative adversarial network (GAN) based training scheme has been recently proposed to imitate the real channel. However, the gradient vanishing and overfitting problems of GAN will result in the serious performance degradation of E2E learning of communication system. To mitigate these two problems, we propose a residual aided GAN (RA-GAN) based training scheme in this paper. Particularly, inspired by the idea of residual learning, we propose a residual generator to mitigate the gradient vanishing problem by realizing a more robust gradient backpropagation. Moreover, to cope with the overfitting problem, we reconstruct the loss function for training by adding a regularizer, which limits the representation ability of RA-GAN. Simulation results show that the trained residual generator has better generation performance than the conventional generator, and the proposed RA-GAN based training scheme can achieve the near-optimal block error rate (BLER) performance with a negligible computational complexity increase in both the theoretical channel model and the ray-tracing based channel dataset.

cs.IT↗