Searcharxiv⌕ Search

arXiv subjects

Haipeng Zhang

Publications and source records attributed to Haipeng Zhang.

53 records · Page 3Linked to original sources
arXiv2024

For the Misgendered Chinese in Gender Bias Research: Multi-Task Learning with Knowledge Distillation for Pinyin Name-Gender Prediction

Achieving gender equality is a pivotal factor in realizing the UN's Global Goals for Sustainable Development. Gender bias studies work towards this and rely on name-based gender inference tools to assign individual gender labels when gender information is unavailable. However, these tools often inaccurately predict gender for Chinese Pinyin names, leading to potential bias in such studies. With the growing participation of Chinese in international activities, this situation is becoming more severe. Specifically, current tools focus on pronunciation (Pinyin) information, neglecting the fact that the latent connections between Pinyin and Chinese characters (Hanzi) behind convey critical information. As a first effort, we formulate the Pinyin name-gender guessing problem and design a Multi-Task Learning Network assisted by Knowledge Distillation that enables the Pinyin embeddings in the model to possess semantic features of Chinese characters and to learn gender information from Chinese character names. Our open-sourced method surpasses commercial name-gender guessing tools by 9.70\% to 20.08\% relatively, and also outperforms the state-of-the-art algorithms.

cs.CL↗
arXiv2024

Decision-Oriented Learning for Future Power System Decision-Making under Uncertainty

Better forecasts may not lead to better decision-making. To address this challenge, decision-oriented learning (DOL) has been proposed as a new branch of machine learning that replaces traditional statistical loss with a decision loss to form an end-to-end model. Applications of DOL in power systems have been developed in recent years. For renewable-rich power systems, uncertainties propagate through sequential tasks, where traditional statistical-based approaches focus on minimizing statistical errors at intermediate stages but may fail to provide optimal decisions at the final stage. This paper first elaborates on the mismatch between more accurate forecasts and more optimal decisions in the power system caused by statistical-based learning (SBL) and explains how DOL resolves this problem. Secondly, this paper extensively reviews DOL techniques and their applications in power systems while highlighting their pros and cons in relation to SBL. Finally, this paper identifies the challenges to adopt DOL in the energy sector and presents future research directions.

eess.SY↗
arXiv2023

Adaptive Decision-Objective Loss for Forecast-then-Optimize in Power Systems

Forecast-then-optimize is a widely-used framework for decision-making problems in power systems. Traditionally, statistical losses have been employed to train forecasting models, but recent research demonstrated that improved decision utility in downstream optimization tasks can be achieved by using decision loss as an alternative. However, the implementation of decision loss in power systems faces challenges in 1) accommodating multi-stage decision-making problems where upstream optimality cannot guarantee final optimality; 2) adapting to dynamic environments such as changing parameters and nature of the problem like continuous or discrete optimization tasks. To this end, this paper proposes a novel adaptive decision-objective loss (ADOL) to address the above challenges. Specifically, ADOL first redefines the decision loss as objective utilities rather than objective loss to eliminate the need to manually set the optimal decision, thus ensuring the globally optimal decision. ADOL enables one-off training in a dynamic environment by introducing additional variables. The differentiability and convexity of ADOL provide useful gradients for forecasting model training in conjunction with continuous and discrete optimization tasks. Experiments are conducted for both linear programming-based and mixed integer linear programming-based power system two-stage dispatching cases with changing costs, and the results show that the proposed ADOL is capable of achieving globally optimal decision-making and adaptability to dynamic environments. The method can be extended to other multi-stage tasks in complex systems.

eess.SY↗
arXiv2023

Multiple Instance Learning for Uplift Modeling

Uplift modeling is widely used in performance marketing to estimate effects of promotion campaigns (e.g., increase of customer retention rate). Since it is impossible to observe outcomes of a recipient in treatment (e.g., receiving a certain promotion) and control (e.g., without promotion) groups simultaneously (i.e., counter-factual), uplift models are mainly trained on instances of treatment and control groups separately to form two models respectively, and uplifts are predicted by the difference of predictions from these two models (i.e., two-model method). When responses are noisy and the treatment effect is fractional, induced individual uplift predictions will be inaccurate, resulting in targeting undesirable customers. Though it is impossible to obtain the ideal ground-truth individual uplifts, known as Individual Treatment Effects (ITEs), alternatively, an average uplift of a group of users, called Average Treatment Effect (ATE), can be observed from experimental deliveries. Upon this, similar to Multiple Instance Learning (MIL) in which each training sample is a bag of instances, our framework sums up individual user uplift predictions for each bag of users as its bag-wise ATE prediction, and regularizes it to its ATE label, thus learning more accurate individual uplifts. Additionally, to amplify the fractional treatment effect, bags are composed of instances with adjacent individual uplift predictions, instead of random instances. Experiments conducted on two datasets show the effectiveness and universality of the proposed framework.

cs.LG↗
arXiv2023

Where Did the President Visit Last Week? Detecting Celebrity Trips from News Articles

Celebrities' whereabouts are of pervasive importance. For instance, where politicians go, how often they visit, and who they meet, come with profound geopolitical and economic implications. Although news articles contain travel information of celebrities, it is not possible to perform large-scale and network-wise analysis due to the lack of automatic itinerary detection tools. To design such tools, we have to overcome difficulties from the heterogeneity among news articles: 1)One single article can be noisy, with irrelevant people and locations, especially when the articles are long. 2)Though it may be helpful if we consider multiple articles together to determine a particular trip, the key semantics are still scattered across different articles intertwined with various noises, making it hard to aggregate them effectively. 3)Over 20% of the articles refer to the celebrities' trips indirectly, instead of using the exact celebrity names or location names, leading to large portions of trips escaping regular detecting algorithms. We model text content across articles related to each candidate location as a graph to better associate essential information and cancel out the noises. Besides, we design a special pooling layer based on attention mechanism and node similarity, reducing irrelevant information from longer articles. To make up the missing information resulted from indirect mentions, we construct knowledge sub-graphs for named entities (person, organization, facility, etc.). Specifically, we dynamically update embeddings of event entities like the G7 summit from news descriptions since the properties (date and location) of the event change each time, which is not captured by the pre-trained event representations. The proposed CeleTrip jointly trains these modules, which outperforms all baseline models and achieves 82.53% in the F1 metric.

cs.AI↗
arXiv2023

Risk-Aware Objective-Based Forecasting in Inertia Management

The objective-based forecasting considers the asymmetric and non-linear impacts of forecasting errors on decision objectives, thus improving the effectiveness of its downstream decision-making process. However, existing objective-based forecasting methods are risk-neutral and not suitable for tasks like power system inertia management and unit commitment, of which decision-makers are usually biased toward risk aversion in practice. To tackle this problem, this paper proposes a generic risk-aware objective-based forecasting method. It enables decision-makers to customize their forecasting with different risk preferences. The equivalence between the proposed method and optimization under uncertainty (stochastic/robust optimization) is established for the first time. Case studies are carried out on a Great Britain 2030 power system with system operational data from National Grid. The results show that the proposed model with deterministic optimization can approximate the performance of stochastic programming or robust optimization at only a fraction of their computational cost.

eess.SY↗
arXiv2023

For the Underrepresented in Gender Bias Research: Chinese Name Gender Prediction with Heterogeneous Graph Attention Network

Achieving gender equality is an important pillar for humankind's sustainable future. Pioneering data-driven gender bias research is based on large-scale public records such as scientific papers, patents, and company registrations, covering female researchers, inventors and entrepreneurs, and so on. Since gender information is often missing in relevant datasets, studies rely on tools to infer genders from names. However, available open-sourced Chinese gender-guessing tools are not yet suitable for scientific purposes, which may be partially responsible for female Chinese being underrepresented in mainstream gender bias research and affect their universality. Specifically, these tools focus on character-level information while overlooking the fact that the combinations of Chinese characters in multi-character names, as well as the components and pronunciations of characters, convey important messages. As a first effort, we design a Chinese Heterogeneous Graph Attention (CHGAT) model to capture the heterogeneity in component relationships and incorporate the pronunciations of characters. Our model largely surpasses current tools and also outperforms the state-of-the-art algorithm. Last but not least, the most popular Chinese name-gender dataset is single-character based with far less female coverage from an unreliable source, naturally hindering relevant studies. We open-source a more balanced multi-character dataset from an official source together with our code, hoping to help future research promoting gender equality.

cs.AI↗
arXiv2022

Sill-Net: Feature Augmentation with Separated Illumination Representation

For visual object recognition tasks, the illumination variations can cause distinct changes in object appearance and thus confuse the deep neural network based recognition models. Especially for some rare illumination conditions, collecting sufficient training samples could be time-consuming and expensive. To solve this problem, in this paper we propose a novel neural network architecture called Separating-Illumination Network (Sill-Net). Sill-Net learns to separate illumination features from images, and then during training we augment training samples with these separated illumination features in the feature space. Experimental results demonstrate that our approach outperforms current state-of-the-art methods in several object classification benchmarks.

cs.CV↗
arXiv2022

RISeer: Inspecting the Status and Dynamics of Regional Industrial Structure via Visual Analytics

Restructuring the regional industrial structure (RIS) has the potential to halt economic recession and achieve revitalization. Understanding the current status and dynamics of RIS will greatly assist in studying and evaluating the current industrial structure. Previous studies have focused on qualitative and quantitative research to rationalize RIS from a macroscopic perspective. Although recent studies have traced information at the industrial enterprise level to complement existing research from a micro perspective, the ambiguity of the underlying variables contributing to the industrial sector and its composition, the dynamic nature, and the large number of multivariant features of RIS records have obscured a deep and fine-grained understanding of RIS. To this end, we propose an interactive visualization system, RISeer, which is based on interpretable machine learning models and enhanced visualizations designed to identify the evolutionary patterns of the RIS and facilitate inter-regional inspection and comparison. Two case studies confirm the effectiveness of our approach, and feedback from experts indicates that RISeer helps them to gain a fine-grained understanding of the dynamics and evolution of the RIS.

cs.HC↗
arXiv2022

Domain Generalization using Pretrained Models without Fine-tuning

Fine-tuning pretrained models is a common practice in domain generalization (DG) tasks. However, fine-tuning is usually computationally expensive due to the ever-growing size of pretrained models. More importantly, it may cause over-fitting on source domain and compromise their generalization ability as shown in recent works. Generally, pretrained models possess some level of generalization ability and can achieve decent performance regarding specific domains and samples. However, the generalization performance of pretrained models could vary significantly over different test domains even samples, which raises challenges for us to best leverage pretrained models in DG tasks. In this paper, we propose a novel domain generalization paradigm to better leverage various pretrained models, named specialized ensemble learning for domain generalization (SEDGE). It first trains a linear label space adapter upon fixed pretrained models, which transforms the outputs of the pretrained model to the label space of the target domain. Then, an ensemble network aware of model specialty is proposed to dynamically dispatch proper pretrained models to predict each test sample. Experimental studies on several benchmarks show that SEDGE achieves significant performance improvements comparing to strong baselines including state-of-the-art method in DG tasks and reduces the trainable parameters by ~99% and the training time by ~99.5%.

cs.CV↗
arXiv2021

Knowledge Graph Enhanced Event Extraction in Financial Documents

Event extraction is a classic task in natural language processing with wide use in handling large amount of yet rapidly growing financial, legal, medical, and government documents which often contain multiple events with their elements scattered and mixed across the documents, making the problem much more difficult. Though the underlying relations between event elements to be extracted provide helpful contextual information, they are somehow overlooked in prior studies. We showcase the enhancement to this task brought by utilizing the knowledge graph that captures entity relations and their attributes. We propose a first event extraction framework that embeds a knowledge graph through a Graph Neural Network and integrates the embedding with regular features, all at document-level. Specifically, for extracting events from Chinese financial announcements, our method outperforms the state-of-the-art method by 5.3% in F1-score.

cs.CL↗
arXiv2021

DMotion: Robotic Visuomotor Control with Unsupervised Forward Model Learned from Videos

Learning an accurate model of the environment is essential for model-based control tasks. Existing methods in robotic visuomotor control usually learn from data with heavily labelled actions, object entities or locations, which can be demanding in many cases. To cope with this limitation, we propose a method, dubbed DMotion, that trains a forward model from video data only, via disentangling the motion of controllable agent to model the transition dynamics. An object extractor and an interaction learner are trained in an end-to-end manner without supervision. The agent's motions are explicitly represented using spatial transformation matrices containing physical meanings. In the experiments, DMotion achieves superior performance on learning an accurate forward model in a Grid World environment, as well as a more realistic robot control environment in simulation. With the accurate learned forward models, we further demonstrate their usage in model predictive control as an effective approach for robotic manipulations.

cs.RO↗
arXiv2021

Graph Neural Network Based VC Investment Success Prediction

Predicting the start-ups that will eventually succeed is essentially important for the venture capital business and worldwide policy makers, especially at an early stage such that rewards can possibly be exponential. Though various empirical studies and data-driven modeling work have been done, the predictive power of the complex networks of stakeholders including venture capital investors, start-ups, and start-ups' managing members has not been thoroughly explored. We design an incremental representation learning mechanism and a sequential learning model, utilizing the network structure together with the rich attributes of the nodes. In general, our method achieves the state-of-the-art prediction performance on a comprehensive dataset of global venture capital investments and surpasses human investors by large margins. Specifically, it excels at predicting the outcomes for start-ups in industries such as healthcare and IT. Meanwhile, we shed light on impacts on start-up success from observable factors including gender, education, and networking, which can be of value for practitioners as well as policy makers when they screen ventures of high growth potentials.

cs.SI↗
arXiv2014

Key parameters generation of the navigation data of GPS Simulator

The development of the GPS (Global Positioning System) signal simulator involving to a number of key technologies, in which the generation of navigation message has important significance. Based on analysis of the structure of GPS navigation data, the paper researches the production of telemetry word and handover word, parity check code, time parameters and star clock. Using disturbing force equation and Lagrange planetary motion equation extrapolate ephemeris parameters whose feasibility is verified through the Matlab software finally.

cs.IT↗
arXiv2014

Design of an Encryption-Decryption Module Oriented for Internet Information Security SOC Design

In order to protect the security of network data, a high speed chip module for encrypting and decrypting of network data packet is designed. The chip module is oriented for internet information security SOC (System on Chip) design. During the design process, AES (Advanced Encryption Standard) and 3DES (Data Encryption Standard) encryption algorithm are adopted to protect the security of network data. The following points are focused: (1) The SOC (System on Chip) design methodology based on IP (Intellectual Property) core is used. AES (Advanced Encryption Standard) and 3DES (Data Encryption Standard) IP (Intellectual Property) cores are embedded in the chip module, peripheral control sub-modules are designed to control the encryption-decryption module, which is capable of shortening the design period of the chip module. (2) The implementation of encryption-decryption with hardware was presented, which improves the safety of data through the encryption-decryption chip and reduce the load of CPU. (3) In our hardware solution, two AES (Advanced Encryption Standard) cores are used to work in parallel, which improves the speed of the encryption module. Moreover, the key length of AES (Advanced Encryption Standard) encryption algorithm is designed with three optional configurations at 128 bits, 256 bits and 192 bits respectively and six optional encryption algorithm modes: CBC (Cipher Block Chaining) mode, ECB (Electronic Code Book) mode, GCM (Galois/Counter Mode) mode, XTS(cipherteXT Stealing) mode, CTR (CounTeR) mode and 3DES respectively, which adds the flexibility to its applications.

cs.AR↗
arXiv2014

Design of a High Speed XAUI Based on Dynamic Reconfigurable Transceiver IP Core

By using the dynamic reconfigurable transceiver in high speed interface design, designer can solve critical technology problems such as ensuring signal integrity conveniently, with lower error binary rate. In this paper, we designed a high speed XAUI (10Gbps Ethernet Attachment Unit Interface) to transparently extend the physical reach of the XGMII. The following points are focused: (1) IP (Intellectual Property) core usage. Altera Co. offers two transceiver IP cores in Quartus II MegaWizard Plug-In Manager for XAUI design which is featured of dynamic reconfiguration performance, that is, ALTGX_RECO?FIG instance and ALTGX instance, we can get various groups by changing settings of the devices without power off. These two blocks can accomplish function of PCS (Physical Coding Sub-layer) and PMA (Physical Medium Attachment), however, with higher efficiency and reliability. (2) 1+1 protection. In our design, two ALTGX IP cores are used to work in parallel, which named XAUI0 and XAUI1. The former works as the main channel while the latter redundant channel. When XAUI0 is out of service for some reasons, XAUI1 will start to work to keep the business. (3) RTL (Register Transfer Level) coding with Verilog HDL and simulation. Create the ALTGX_RECO?FIG instance and ALTGX instance, enable dynamic reconfiguration in the ALTGXB Megafunction, then connect the ALTGX_RECO?FIG with the ALTGX instances. After RTL coding, the design was simulated on VCS simulator. The validated result indicates that the packets are transferred efficiently. FPGA makes high-speed optical communication system design simplified.

cs.AR↗