Arrow Research search

Author name cluster

Guihai Chen

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

32 papers
2 author rows

Possible papers

32

AAAI Conference 2026 Conference Paper

AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization

  • Qiyang Li
  • Rui Kong
  • Yuchen Li
  • Hengyi Cai
  • Shuaiqiang Wang
  • Linghe Kong
  • Guihai Chen
  • Dawei Yin

The integration of dynamic, sparse structures like Mixture-of-Experts (MoE) with parameter-efficient adapters (e.g., LoRA) is a powerful technique for enhancing Large Language Models (LLMs). However, this architectural enhancement comes at a steep cost: despite minimal increases in computational load, the inference latency often skyrockets, leading to decoding speeds slowing by over 2.5 times. Through a fine-grained performance analysis, we pinpoint the primary bottleneck not in the computation itself, but in the severe overhead from fragmented, sequential CUDA kernel launches required for conventional dynamic routing. To address this challenge, we introduce AdaFuse, a framework built on a tight co-design between the algorithm and the underlying hardware system to enable efficient dynamic adapter execution. Departing from conventional layer-wise or block-wise routing, AdaFuse employs a token-level pre-gating strategy, which makes a single, global routing decision for all adapter layers before a token is processed. This ``decide-once, apply-everywhere'' approach effectively staticizes the execution path for each token, creating an opportunity for holistic optimization. We capitalize on this by developing a custom CUDA kernel that performs a fused switching operation, merging the parameters of all selected LoRA adapters into the backbone model in a single, efficient pass. Experimental results on popular open-source LLMs show that AdaFuse achieves accuracy on par with state-of-the-art dynamic adapters while drastically cutting decoding latency by a factor of over 2.4x, thereby bridging the gap between model capability and inference efficiency.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Channel-masked Asymmetric Distribution Matching for Cross-Domain Generalized Dataset Distillation

  • Qi Liu
  • Chenghao Xu
  • Jiexi Yan
  • guangtao lyu
  • Erkun Yang
  • Guihai Chen
  • Yanhua Yang

Dataset distillation has achieved remarkable progress as an effective approach for data compression. However, real-world data often comes from diverse domains, leading to potential mismatches between the domains of synthesized images and those of the evaluation set. Existing methods primarily assume domain alignment between them, which limits their generalization ability in the above cross-domain scenarios. In this paper, we aim to ensure that images synthesized from known domains maintain robust performance on unseen domains and propose a novel framework called Channel-masked Asymmetric Distribution Matching (CADM). During asymmetric distribution matching, domain-sensitive channels of real data are selectively masked at different layers to extract domain-invariant features that guide synthetic data optimization. To further improve synthetic data representation, we introduce a class-focused domain-agnostic regularization to capture class-relevant knowledge while ignoring domain-specific information. Experiments show that our method produces domain-robust synthetic data and substantially improves generalization performance on unseen domains.

PDF Details DOI

AAAI Conference 2026 Conference Paper

ProCAST: A Projection Framework for Coupled Aggregation Constrained Multivariate Time Series Forecasting

  • Jiaqi Xue
  • Hongji Dong
  • Yucen Gao
  • Xiaofeng Gao
  • Guihai Chen

Aggregated time series are widely used in business and economics, where top-level sequences (e.g., category sales) aggregated from underlying sequences (e.g., individual items) often exhibit clearer trends and are therefore typically the primary focus of forecasting tasks. However, treating top-level sequences as ordinary multivariate time series is inappropriate in the presence of coupled aggregation constraints. The core challenge arises in coupled aggregation structures, where a single underlying sequence contributes to multiple top-level sequences, as simple nonnegativity constraints of underlying sequences induce highly complex constraints among top-level sequences. Existing methods fail to achieve high accuracy while satisfying these constraints. To address this, we propose ProCAST, a projection-based framework that adjusts forecasts from any multivariate base model to satisfy coupled aggregation constraints. By introducing virtual underlying sequences and leveraging orthogonal and oblique projection, our method ensures that the top-level forecasts are feasible without explicitly deriving complex constraints. Theoretically, we prove that the proposed method guarantees improved accuracy under distance-based loss functions. Experiments on real-world datasets show that our method completely eliminates constraint violations while achieving higher accuracy than current state-of-the-art approaches.

PDF Details DOI

TAAS Journal 2025 Journal Article

ACORN+: Adaptive Compression-Reconstruction for Device-Cloud Collaboration Video Services

  • Jiale Lei
  • Peihao Yang
  • Linghe Kong
  • Yehan Ma
  • Deyu Lin
  • Guihai Chen
  • E. Zhao

With the improvement of edge-based autonomous systems such as mobile Industrial IoT (IIoT) networks, edge devices can capture and upload videos with increasing bitrates. Massive edge-computing end nodes are eager for adequate multimedia data to satisfy the requirements of real-time video services. However, existing encoding standards for video services in Web 2.0 are specifically designed for something other than IoT video streaming. We have improved our Adaptive Compression-Reconstruction (ACORN) framework to obtain ACORN+, based on compressed sensing and recent advances in deep learning. At end nodes, we compress multiple sequential video frames into a single frame to reduce video volume. Given that multiple kinds of intelligent tasks are expected to be finished on the device side, we also designed a device-cloud collaboration scheme where deep learning-based algorithms can be executed on both the device and server sides. Experiments reveal that video analytics can be conducted on compressed frames. Taking action recognition as a device-cloud collaboration use case, we find ACORN \(+\) obtains more than 3 \(\times\) speedup on compressed frames. The reconstruction algorithm in ACORN \(+\) is with 1– 4 dB improvements. Moreover, the encoding time cost and the encoded video volume are reduced by more than 4 \(\times\) under the ACORN \(+\) framework. 1

Details DOI

TCS Journal 2025 Journal Article

Algorithms for Shortest Path Tour Problem

  • Yucen Gao
  • Zhuoran Li
  • Jingyu He
  • Jun Fang
  • Hui Gao
  • Xiaofeng Gao
  • Guihai Chen

Carpooling route planning becomes an important problem with the growth of low-carbon traffic systems. When each passenger has multiple potential pick-up/drop-off locations, the problem will be more challenging. In the paper, we discussed a simplified carpooling route planning problem, namely the Shortest Path Tour Problem (SPTP), whose aim is to find a single-origin single-destination shortest path through an ordered sequence of disjoint node subsets. We propose Stage Dijkstra and Global Dijkstra algorithms to find the optimal shortest path, with the time complexity of O ( l ( n + m ) log ⁡ n ) and O ( l ( n + m ) log ⁡ ( l n ) ) respectively, where l represents the number of node subsets. To the best of our knowledge, O ( l ( n + m ) log ⁡ n ) is the best time complexity of the exact algorithms for SPTP. Besides, the Stage Dijkstra and Global Dijkstra algorithms both have the linear space complexity, which is highly suitable for resource-constrained environments. Experiments conducted on large-scale road networks and synthetic datasets demonstrate the effectiveness and efficiency of our proposed algorithms in terms of running time and memory consumption.

Details DOI

NeurIPS Conference 2025 Conference Paper

Bi-Level Decision-Focused Causal Learning for Large-Scale Marketing Optimization: Bridging Observational and Experimental Data

  • Shuli Zhang
  • Hao Zhou
  • Jiaqi Zheng
  • Guibin Jiang
  • Cheng Bing
  • Wei Lin
  • Guihai Chen

Online Internet platforms require sophisticated marketing strategies to optimize user retention and platform revenue — a classical resource allocation problem. Traditional solutions adopt a two-stage pipeline: machine learning (ML) for predicting individual treatment effects to marketing actions, followed by operations research (OR) optimization for decision-making. This paradigm presents two fundamental technical challenges. First, the prediction-decision misalignment: Conventional ML methods focus solely on prediction accuracy without considering downstream optimization objectives, leading to improved predictive metrics that fail to translate to better decisions. Second, the bias-variance dilemma: Observational data suffers from multiple biases (e. g. , selection bias, position bias), while experimental data (e. g. , randomized controlled trials), though unbiased, is typically scarce and costly --- resulting in high-variance estimates. We propose Bi -level D ecision- F ocused C ausal L earning ( Bi-DFCL ) that systematically addresses these challenges. First, we develop an unbiased estimator of OR decision quality using experimental data, which guides ML model training through surrogate loss functions that bridge discrete optimization gradients. Second, we establish a bi-level optimization framework that jointly leverages observational and experimental data, solved via implicit differentiation. This novel formulation enables our unbiased OR estimator to correct learning directions from biased observational data, achieving optimal bias-variance tradeoff. Extensive evaluations on public benchmarks, industrial marketing datasets, and large-scale online A/B tests demonstrate the effectiveness of Bi-DFCL, showing statistically significant improvements over state-of-the-art. Currently, Bi-DFCL has been deployed across several marketing scenarios at Meituan, one of the largest online food delivery platforms in the world.

PDF Details

NeurIPS Conference 2025 Conference Paper

CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs

  • Gucongcong Fan
  • Chaoyue Niu
  • Chengfei Lyu
  • Fan Wu
  • Guihai Chen

Mobile agents rely on Large Language Models (LLMs) to plan and execute tasks on smartphone user interfaces (UIs). While cloud-based LLMs achieve high task accuracy, they require uploading the full UI state at every step, exposing unnecessary and often irrelevant information. In contrast, local LLMs avoid UI uploads but suffer from limited capacity, resulting in lower task success rates. We propose $\textbf{CORE}$, a $\textbf{CO}$llaborative framework that combines the strengths of cloud and local LLMs to $\textbf{R}$educe UI $\textbf{E}$xposure, while maintaining task accuracy for mobile agents. CORE comprises three key components: (1) $\textbf{Layout-aware block partitioning}$, which groups semantically related UI elements based on the XML screen hierarchy; (2) $\textbf{Co-planning}$, where local and cloud LLMs collaboratively identify the current sub-task; and (3) $\textbf{Co-decision-making}$, where the local LLM ranks relevant UI blocks, and the cloud LLM selects specific UI elements within the top-ranked block. CORE further introduces a multi-round accumulation mechanism to mitigate local misjudgment or limited context. Experiments across diverse mobile apps and tasks show that CORE reduces UI exposure by up to 55. 6\% while maintaining task success rates slightly below cloud-only agents, effectively mitigating unnecessary privacy exposure to the cloud. The code is available at https: //github. com/Entropy-Fighter/CORE.

PDF Details

AAAI Conference 2025 Conference Paper

CSR:Achieving 1 Bit Key-Value Cache via Sparse Representation

  • Hongxuan Zhang
  • Yao Zhao
  • Jiaqi Zheng
  • Chenyi Zhuang
  • Jinjie Gu
  • Guihai Chen

The emergence of long-context text applications utilizing large language models (LLMs) has presented significant scalability challenges, particularly in memory footprint. The linear growth of the Key-Value (KV) cache, which stores attention keys and values to reduce redundant computations, can significantly increase memory usage and may prevent models from functioning properly in memory-constrained environments. To address this issue, we propose a novel approach called Cache Sparse Representation (CSR), which converts the KV cache by transforming the dense Key-Value cache tensor into sparse indexes and weights, offering a more memory-efficient representation during LLM inference. Furthermore, we introduce NeuralDict, a novel neural network-based method to automatically generate the dictionary used in our sparse representation. Our extensive experiments demonstrate that CSR matches the performance of state-of-the-art KV cache quantization algorithms while ensuring robust functionality in memory-constrained environments.

PDF Details DOI

TCS Journal 2025 Journal Article

Online multi-dimensional generalized assignment problem with predictions

  • Yimeng Xu
  • Jiaqi Zheng
  • Guihai Chen
  • Xia Zhu
  • Zhen Yao

The Online Multi-Dimensional Generalized Assignment Problem (online MDGAP) can model a large number of applications such as parallel machine scheduling, vehicle routing, telecommunication network design, etc. , where a set of jobs have to be assigned to a set of capacitated agents in an online manner such that multi-dimensional capacity constraints can be respected. In this paper, we initiate the study of online MDGAP with predictions — the decision parameters such as coefficients of service (switching) costs and resource consumption can be accurately predicted or error-bounded, with the objective of minimizing the sum of service costs and switching costs in the long run. Furthermore, we design a two-stage online algorithm with performance guarantees. Rigorous theoretical analysis in terms of competitive ratio and regret demonstrates that our algorithm can produce an integer solution in polynomial time with bounded dimension constraints violation, robust to the coefficient variations and resource consumption uncertainty. Finally, trace-driven simulations show that our algorithm can achieve near optimal, high utilization, low constraint violation, and strong robustness.

Details DOI

NeurIPS Conference 2025 Conference Paper

RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models

  • Jiarui Zhang
  • Xiangyu Liu
  • Yong Hu
  • Chaoyue Niu
  • Fan Wu
  • Guihai Chen

Retrieval-Augmented Generation (RAG) significantly improves the performance of Large Language Models (LLMs) on knowledge-intensive tasks. However, varying response quality across LLMs under RAG necessitates intelligent routing mechanisms, which select the most suitable model for each query from multiple retrieval-augmented LLMs via a dedicated router model. We observe that external documents dynamically affect LLMs' ability to answer queries, while existing routing methods, which rely on static parametric knowledge representations, exhibit suboptimal performance in RAG scenarios. To address this, we formally define the new retrieval-augmented LLM routing problem, incorporating the influence of retrieved documents into the routing framework. We propose RAGRouter, a RAG-aware routing design, which leverages document embeddings and RAG capability embeddings with contrastive learning to capture knowledge representation shifts and enable informed routing decisions. Extensive experiments on diverse knowledge-intensive tasks and retrieval settings, covering open and closed-source LLMs, show that RAGRouter outperforms the best individual LLM and existing routing methods. With an extended score-threshold-based mechanism, it also achieves strong performance-efficiency trade-offs under low-latency constraints. The code and data are available at https: //github. com/OwwO99/RAGRouter.

PDF Details

ECAI Conference 2025 Conference Paper

VariGen: Controllable Image Generation Via Personalized Diffusion Framework

  • Mingxin Cai
  • Zexu Huang
  • Yuchen Li 0006
  • Linghe Kong
  • Guihai Chen

Diffusion models have achieved remarkable progress in text-to-image generation, enabling the rise of personalized models. A key challenge in personalized generation is to provide users with precise control while ensuring high fidelity to the content. To address this, we introduce VariGen: a framework that empowers users to achieve fine-grained, layout-controllable personalized image generation. VariGen employs the Variational Detail-Aware Feature Extractor to capture intricate details from reference subjects and the Dual Layout Control Mechanism to integrate layout specifications seamlessly into the generation process. We demonstrate that VariGen achieves superior performance through extensive experimentation, offering unparalleled creative freedom and fidelity. To our knowledge, this is the first work to enable users to “create anything, anywhere” with such precision and flexibility.

Details

NeurIPS Conference 2024 Conference Paper

2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution

  • Kai Liu
  • Haotong Qin
  • Yong Guo
  • Xin Yuan
  • Linghe Kong
  • Guihai Chen
  • Yulun Zhang

Low-bit quantization has become widespread for compressing image super-resolution (SR) models for edge deployment, which allows advanced SR models to enjoy compact low-bit parameters and efficient integer/bitwise constructions for storage compression and inference acceleration, respectively. However, it is notorious that low-bit quantization degrades the accuracy of SR models compared to their full-precision (FP) counterparts. Despite several efforts to alleviate the degradation, the transformer-based SR model still suffers severe degradation due to its distinctive activation distribution. In this work, we present a dual-stage low-bit post-training quantization (PTQ) method for image super-resolution, namely 2DQuant, which achieves efficient and accurate SR under low-bit quantization. The proposed method first investigates the weight and activation and finds that the distribution is characterized by coexisting symmetry and asymmetry, long tails. Specifically, we propose Distribution-Oriented Bound Initialization (DOBI), using different searching strategies to search a coarse bound for quantizers. To obtain refined quantizer parameters, we further propose Distillation Quantization Calibration (DQC), which employs a distillation approach to make the quantized model learn from its FP counterpart. Through extensive experiments on different bits and scaling factors, the performance of DOBI can reach the state-of-the-art (SOTA) while after stage two, our method surpasses existing PTQ in both metrics and visual effects. 2DQuant gains an increase in PSNR as high as 4. 52dB on Set5 (x2) compared with SOTA when quantized to 2-bit and enjoys a 3. 60x compression ratio and 5. 08x speedup ratio. The code and models are available at https: //github. com/Kai-Liu001/2DQuant.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

GS2P: A Generative Pre-trained Learning to Rank Model with Over-parameterization for Web-Scale Search (Extended Abstract)

  • Yuchen Li
  • Haoyi Xiong
  • Linghe Kong
  • Jiang Bian
  • Shuaiqiang Wang
  • Guihai Chen
  • Dawei Yin

While Learning to Rank (LTR) is widely employed in web searches to prioritize pertinent webpages from the retrieved contents based on input queries, traditional LTR models stumble over two principal stumbling blocks leading to subpar performance: 1) the lack of well-annotated query-webpage pairs with ranking scores to cover search queries of various popularity, debilitating their coverage of search queries across the popularity spectrum, and 2) ill-trained models that are incapable of inducing generalized representations for LTR, culminating in overfitting. To tackle above challenges, we proposed a Generative Semi-supervised Pre-trained (GS2P) LTR model. Specifically, GS2P first generates pseudo-labels for the unlabeled samples using tree-based LTR models after a series of co-training procedures, then learns the representations of query-webpage pairs with self-attentive transformers via both discriminative and generative losses. Finally, GS2P boosts the performance of LTR through incorporating Random Fourier Features to over-parameterize the models into "interpolating regime", so as to enjoy the further descent of generalization errors with learned representations. We conduct extensive offline experiments on a publicly available dataset and a real-world dataset collected from a large-scale search engine. The results show that GS2P can achieve the best performance on both datasets, compared to baselines. We also deploy GS2P at a large-scale web search engine with realistic traffic, where we can still observe significant improvement in real-world applications.

PDF Details DOI

TCS Journal 2023 Journal Article

Optimizing incremental SDN upgrades for load balancing in ISP networks

  • Yunlong Cheng
  • Hao Zhou
  • Xiaofeng Gao
  • Jiaqi Zheng
  • Guihai Chen

Software defined network (SDN) can dynamically and timely reply to the changes of network states, thus enabling advance traffic engineering mechanisms. To enhance the management ability of the network, Internet Service Providers (ISPs) are upgrading traditional network devices to SDN devices incrementally. In this paper, we study the k-LB problem, i. e. , upgrading at most k legacy switches to SDN switches to achieve load balance. We prove that k-LB problem is NP-hard and there is no polynomial time ( N + M ) 1 − ϵ -approximation algorithm for any constant ϵ > 0 unless P = NP, where N (M) is the number of switches (links) in the network. Nevertheless, we propose an effective greedy algorithm and prove that it reaches an approximation guarantee of c a v g c m i n M, where c a v g ( c m i n ) is the average (minimum) link capacity. Furthermore, we show that the greedy algorithm touches the tight lower bound of approximation ratio by extending the inapproximability result. The simulation results from large-scale ISP network topologies illustrate the effectiveness of our algorithm and show that the maximum link utilization can be decreased by 30% on average compared with the SOTA.

Details DOI

IJCAI Conference 2023 Conference Paper

Truthful Auctions for Automated Bidding in Online Advertising

  • Yidan Xing
  • Zhilin Zhang
  • Zhenzhe Zheng
  • Chuan Yu
  • Jian Xu
  • Fan Wu
  • Guihai Chen

Automated bidding, an emerging intelligent decision-making paradigm powered by machine learning, has become popular in online advertising. Advertisers in automated bidding evaluate the cumulative utilities and have private financial constraints over multiple ad auctions in a long-term period. Based on these distinct features, we consider a new ad auction model for automated bidding: the values of advertisers are public while the financial constraints, such as budget and return on investment (ROI) rate, are private types. We derive the truthfulness conditions with respect to private constraints for this multi-dimensional setting, and demonstrate any feasible allocation rule could be equivalently reduced to a series of non-decreasing functions on budget. However, the resulted allocation mapped from these non-decreasing functions generally follows an irregular shape, making it difficult to obtain a closed-form expression for the auction objective. To overcome this design difficulty, we propose a family of truthful automated bidding auction with personalized rank scores, similar to the Generalized Second-Price (GSP) auction. The intuition behind our design is to leverage personalized rank scores as the criteria to allocate items, and compute a critical ROI to transforms the constraints on budget to the same dimension as ROI. The experimental results demonstrate that the proposed auction mechanism outperforms the widely used ad auctions, such as first-price auction and second-price auction, in various automated bidding environments.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Cross-Task Knowledge Distillation in Multi-Task Recommendation

  • Chenxiao Yang
  • Junwei Pan
  • Xiaofeng Gao
  • Tingyu Jiang
  • Dapeng Liu
  • Guihai Chen

Multi-task learning (MTL) has been widely used in recommender systems, wherein predicting each type of user feedback on items (e. g, click, purchase) are treated as individual tasks and jointly trained with a unified model. Our key observation is that the prediction results of each task may contain task-specific knowledge about user’s fine-grained preference towards items. While such knowledge could be transferred to benefit other tasks, it is being overlooked under the current MTL paradigm. This paper, instead, proposes a Cross-Task Knowledge Distillation framework that attempts to leverage prediction results of one task as supervised signals to teach another task. However, integrating MTL and KD in a proper manner is non-trivial due to several challenges including task conflicts, inconsistent magnitude and requirement of synchronous optimization. As countermeasures, we 1) introduce auxiliary tasks with quadruplet loss functions to capture cross-task fine-grained ranking information and avoid task conflicts, 2) design a calibrated distillation approach to align and distill knowledge from auxiliary tasks, and 3) propose a novel error correction mechanism to enable and facilitate synchronous training of teacher and student models. Comprehensive experiments are conducted to verify the effectiveness of our framework in real-world datasets.

PDF Details

NeurIPS Conference 2022 Conference Paper

Federated Submodel Optimization for Hot and Cold Data Features

  • Yucheng Ding
  • Chaoyue Niu
  • Fan Wu
  • Shaojie Tang
  • Chengfei Lyu
  • Yanghe Feng
  • Guihai Chen

We focus on federated learning in practical recommender systems and natural language processing scenarios. The global model for federated optimization typically contains a large and sparse embedding layer, while each client’s local data tend to interact with part of features, updating only a small submodel with the feature-related embedding vectors. We identify a new and important issue that distinct data features normally involve different numbers of clients, generating the differentiation of hot and cold features. We further reveal that the classical federated averaging algorithm (FedAvg) or its variants, which randomly selects clients to participate and uniformly averages their submodel updates, will be severely slowed down, because different parameters of the global model are optimized at different speeds. More specifically, the model parameters related to hot (resp. , cold) features will be updated quickly (resp. , slowly). We thus propose federated submodel averaging (FedSubAvg), which introduces the number of feature-related clients as the metric of feature heat to correct the aggregation of submodel updates. We prove that due to the dispersion of feature heat, the global objective is ill-conditioned, and FedSubAvg works as a suitable diagonal preconditioner. We also rigorously analyze FedSubAvg’s convergence rate to stationary points. We finally evaluate FedSubAvg over several public and industrial datasets. The evaluation results demonstrate that FedSubAvg significantly outperforms FedAvg and its variants.

PDF Details

IJCAI Conference 2022 Conference Paper

Trading Hard Negatives and True Negatives: A Debiased Contrastive Collaborative Filtering Approach

  • Chenxiao Yang
  • Qitian Wu
  • Jipeng Jin
  • Xiaofeng Gao
  • Junwei Pan
  • Guihai Chen

Collaborative filtering (CF), as a standard method for recommendation with implicit feedback, tackles a semi-supervised learning problem where most interaction data are unobserved. Such a nature makes existing approaches highly rely on mining negatives for providing correct training signals. However, mining proper negatives is not a free lunch, encountering with a tricky trade-off between mining informative hard negatives and avoiding false ones. We devise a new approach named as Hardness-Aware Debiased Contrastive Collaborative Filtering (HDCCF) to resolve the dilemma. It could sufficiently explore hard negatives from two-fold aspects: 1) adaptively sharpening the gradients of harder instances through a set-wise objective, and 2) implicitly leveraging item/user frequency information with a new sampling strategy. To circumvent false negatives, we develop a principled approach to improve the reliability of negative instances and prove that the objective is an unbiased estimation of sampling from the true negative distribution. Extensive experiments demonstrate the superiority of the proposed model over existing CF models and hard negative mining methods.

PDF Details DOI

TCS Journal 2021 Journal Article

A unified task recommendation strategy for realistic mobile crowdsourcing system

  • Zhiyao Li
  • Bosen Cheng
  • Xiaofeng Gao
  • Huai Chen
  • Guihai Chen

A well-designed task recommendation framework aims to protect the data quality as well as increase the task execution results. However, current crowdsourcing systems ignore the fact that there are few duplicate task expectations because of the budget limitation in realistic conditions. Besides, a practical crowdsourcing system needs to recommend new tasks without previous knowledge about the concrete task content due to short task lifespan. Thus, most of the existing studies are not applicable due to the idealized assumptions. In this paper, we formally define the problem and prove it is NP-Hard. For the problem, we design a unified task recommendation system for realistic conditions to address the mentioned problems, Pioneer-Assisted Task RecommendatiON (PATRON) framework. The framework first selects a set of pioneer workers to collect initial knowledge of the new tasks. Then it adopts the k-medoids clustering algorithm to split the workers into subsets based on the worker similarity. Cluster selection and worker pruning provides accurate and efficient recommendations that satisfy the valid recommendation requirements from requesters. Finally, we conducted our experiments based on real datasets from a famous Chinese crowdsourcing platform, Tencent SOHO. The experimental results show the efficiency and accuracy of PATRON compared with three baseline methods from several perspectives, such as recommendation success rate and recommended worker quality.

Details DOI

AAAI Conference 2021 Conference Paper

Toward Understanding the Influence of Individual Clients in Federated Learning

  • Yihao Xue
  • Chaoyue Niu
  • Zhenzhe Zheng
  • Shaojie Tang
  • Chengfei Lyu
  • Fan Wu
  • Guihai Chen

Federated learning allows mobile clients to jointly train a global model without sending their private data to a central server. Extensive works have studied the performance guarantee of the global model, however, it is still unclear how each individual client influences the collaborative training process. In this work, we defined a new notion, called Fed- Influence, to quantify this influence over the model parameters, and proposed an effective and efficient algorithm to estimate this metric. In particular, our design satisfies several desirable properties: (1) it requires neither retraining nor retracing, adding only linear computational overhead to clients and the server; (2) it strictly maintains the tenets of federated learning, without revealing any client’s local private data; and (3) it works well on both convex and non-convex loss functions, and does not require the final model to be optimal. Empirical results on a synthetic dataset and the FEMNIST dataset demonstrate that our estimation method can approximate Fed-Influence with small bias. Further, we show an application of Fed-Influence in model debugging.

PDF Details

TCS Journal 2020 Journal Article

Hardness of and approximate mechanism design for the bike rebalancing problem

  • Hongtao Lv
  • Fan Wu
  • Tie Luo
  • Xiaofeng Gao
  • Guihai Chen

Recently arose in the flourishing sharing economy, the bike rebalancing problem is a new challenge that concerns how to incentivize users to park bikes at system-desired locations that better meet bike demands. It can also be generalized to other location-based vehicle or tool sharing problems such as car, truck, drone, and trolley sharing. In this paper, we address this problem using an auction model under a crowdsourcing framework, where users report their original destinations and the bike sharing platform assigns proper relocation tasks to them in order to better balance the bike supply and demand. We first prove two impossibility results: (1) finding an optimal solution to the bike rebalancing problem is NP-hard, and (2) there is no approximate mechanism with bounded approximation ratio that is both truthful and budget-feasible. To overcome this barrier, we introduce two practical constraints and design a two-stage approximate mechanism that satisfies location truthfulness, budget feasibility, individual rationality, and achieves constant approximation ratio. To the best of our knowledge, we are the first to address two dimensional location truthfulness in the regime of mechanism design. In addition, our extensive experiments based on real-world dataset demonstrate that our proposed mechanism can effectively redress the imbalance of bike distribution.

Details DOI

AAAI Conference 2020 Conference Paper

Mechanism Design with Predicted Task Revenue for Bike Sharing Systems

  • Hongtao Lv
  • Chaoli Zhang
  • Zhenzhe Zheng
  • Tie Luo
  • Fan Wu
  • Guihai Chen

Bike sharing systems have been widely deployed around the world in recent years. A core problem in such systems is to reposition the bikes so that the distribution of bike supply is reshaped to better match the dynamic bike demand. When the bike-sharing company or platform is able to predict the revenue of each reposition task based on historic data, an additional constraint is to cap the payment for each task below its predicted revenue. In this paper, we propose an incentive mechanism called TruPreTar to incentivize users to park bicycles at locations desired by the platform toward rebalancing supply and demand. TruPreTar possesses four important economic and computational properties such as truthfulness and budget feasibility. Furthermore, we prove that even when the payment budget is tight, the total revenue still exceeds or equals the budget. Otherwise, TruPre- Tar achieves 2-approximation as compared to the optimal (revenue-maximizing) solution, which is close to the lower bound of at least √ 2 that we also prove. Using an industrial dataset obtained from a large bike-sharing company, our experiments show that TruPreTar is effective in rebalancing bike supply and demand and, as a result, generates high revenue that outperforms several benchmark mechanisms.

PDF Details

TCS Journal 2020 Journal Article

Pricing and allocation algorithm designs in dynamic ridesharing system

  • Chaoli Zhang
  • Jiapeng Xie
  • Fan Wu
  • Xiaofeng Gao
  • Guihai Chen

Traffic congestion and car pollution are becoming serious plagues nowadays. High travel cost brings a great burden to people and society. A ridesharing system mitigates traffic congestion and car pollution by allowing passengers to share their travel costs with others. Traditional ridesharing platforms usually require passengers to submit their plans in advance and then design schedules for the drivers who would like to offer a ride. Nowadays, with the development of the smartphone technology, dynamic ridesharing systems enable passengers request a car anytime and anywhere. This paper mainly considers the problems of how to allocate passengers to drivers, how to charge the passengers and how to design feasible schedules for the driver in such online environment. The allocation problem is modeled as an online weighted matching problem with the graph changing over time. Firstly, we give a fair pricing method which is easy to be understood and accepted by the passengers. We develop a greedy algorithm called LiqMax_Gre for the purpose of maximizing liquidity and an algorithm called UtiMax for the purpose of maximizing utility. LiqMax_Gre achieves a competitive ratio of 1 λ + 1, where λ is the maximal number of passengers a car can take. In general, we prove that no online algorithm can have a good guarantee for the design goal of maximizing utility. Innovatively, UtiMax considers not only the current maximal utility, but also the opportunity cost, which is the utility contributed by occupying a seat. It reflects the utility in the future and thus can be used to handle the difficulty in online design. We prove that, our algorithm has a competitive ratio of 1/3 in a special case. The schedule problem is NP-hard and we design a heuristic nearest neighbor algorithm to solve it.

Details DOI

TCS Journal 2019 Journal Article

Accelerate the classification statistics in RFID systems

  • Jiapeng Huang
  • Zhenzao Wen
  • Linghe Kong
  • Li Ge
  • Min-You Wu
  • Guihai Chen

Radio Frequency Identification (RFID) technology has been widely used in many applications such as logistics, warehouse management and animal identification. However, the dilemma of short time requirement and massive tags makes traditional one-by-one identification methods impractical. Meanwhile, existing off-the-shelf methods cannot count and classify RFID tags at the same time. In this paper, RFID classification statistics problem is defined as classifying the tags into distinct groups and counting the quantity of tags in each group by the reader. The issue of time efficiency is significant in classification statistics, especially when the number of tags is large. To address this problem, we propose a novel Twins Accelerating Gears (TAG) approach. One gear shortens the classification process in frequency domain through subcarrier allocation, when another gear accelerates the statistics process in time domain through geometric distribution based quantity estimation. TAG can handle classification and quantity estimation during one process while existing methods need to handle it separately. We give elaborate proof of the running time and quantity estimation value of the process in theory. Typically, the total time of TAG is O ( log ⁡ N ) and TAG outperforms existing identification solutions about 99. 8% time reduction on 1000 tags classified statistics.

Details DOI

IJCAI Conference 2019 Conference Paper

Feature Evolution Based Multi-Task Learning for Collaborative Filtering with Social Trust

  • Qitian Wu
  • Lei Jiang
  • Xiaofeng Gao
  • Xiaochun Yang
  • Guihai Chen

Social recommendation could address the data sparsity and cold-start problems for collaborative filtering by leveraging user trust relationships as auxiliary information for recommendation. However, most existing methods tend to consider the trust relationship as preference similarity in a static way and model the representations for user preference and social trust via a common feature space. In this paper, we propose TrustEV and take the view of multi-task learning to unite collaborative filtering for recommendation and network embedding for user trust. We design a special feature evolution unit that enables the embedding vectors for two tasks to exchange their features in a probabilistic manner, and further harness a meta-controller to globally explore proper settings for the feature evolution units. The training process contains two nested loops, where in the outer loop, we optimize the meta-controller by Bayesian optimization, and in the inner loop, we train the feedforward model with given feature evolution units. Experiment results show that TrustEV could make better use of social information and greatly improve recommendation MAE over state-of-the-art approaches.

PDF Details

NeurIPS Conference 2019 Conference Paper

Learning Latent Process from High-Dimensional Event Sequences via Efficient Sampling

  • Qitian Wu
  • Zixuan Zhang
  • Xiaofeng Gao
  • Junchi Yan
  • Guihai Chen

We target modeling latent dynamics in high-dimension marked event sequences without any prior knowledge about marker relations. Such problem has been rarely studied by previous works which would have fundamental difficulty to handle the arisen challenges: 1) the high-dimensional markers and unknown relation network among them pose intractable obstacles for modeling the latent dynamic process; 2) one observed event sequence may concurrently contain several different chains of interdependent events; 3) it is hard to well define the distance between two high-dimension event sequences. To these ends, in this paper, we propose a seminal adversarial imitation learning framework for high-dimension event sequence generation which could be decomposed into: 1) a latent structural intensity model that estimates the adjacent nodes without explicit networks and learns to capture the temporal dynamics in the latent space of markers over observed sequence; 2) an efficient random walk based generation model that aims at imitating the generation process of high-dimension event sequences from a bottom-up view; 3) a discriminator specified as a seq2seq network optimizing the rewards to help the generator output event sequences as real as possible. Experimental results on both synthetic and real-world datasets demonstrate that the proposed method could effectively detect the hidden network among markers and make decent prediction for future marked events, even when the number of markers scales to million level.

PDF Details

AAMAS Conference 2018 Conference Paper

On Designing Optimal Data Purchasing Strategies for Online Ad Auctions

  • Zun Li
  • Zhenzhe Zheng
  • Fan Wu
  • Guihai Chen

In online advertising, advertisers can purchase consumer relevant data from data marketplaces with a certain expenditure, and exploit the purchased data to guide the bidding process in ad auctions. One of the pressing problem faced by advertisers is to design the optimal data purchasing strategy (how much data to purchase to be competitive in bidding process) in online ad auctions. In this paper, we model the data purchasing strategy design as a convex optimization problem, jointly considering the expenditure paid during data purchasing and the benefits obtained from ad auctions. Using the techniques from Baysian game theory and convex analysis, we derive the optimal purchasing strategies for advertisers in different market scenarios. We also theoretically prove that the resulting strategy profile is the unique one that achieves Nash Equilibrium. Our analysis shows that the proposed data purchasing strategy can handle diverse ad auctions and valuation learning models. Our numerical results empirically reveal how the equilibrium state changes with variation of the strategic environment.

PDF

IJCAI Conference 2018 Conference Paper

Online Pricing for Revenue Maximization with Unknown Time Discounting Valuations

  • Weichao Mao
  • Zhenzhe Zheng
  • Fan Wu
  • Guihai Chen

Online pricing mechanisms have been widely applied to resource allocation in multi-agent systems. However, most of the existing online pricing mechanisms assume buyers have fixed valuations over the time horizon, which cannot capture the dynamic nature of valuation in emerging applications. In this paper, we study the problem of revenue maximization in online auctions with unknown time discounting valuations, and model it as non-stationary multi-armed bandit optimization. We design an online pricing mechanism, namely Biased-UCB, based on unique features of the discounting valuations. We use competitive analysis to theoretically evaluate the performance guarantee of our pricing mechanism, and derive the competitive ratio. Numerical results show that our design achieves good performance in terms of revenue maximization on a real-world bidding dataset.

PDF Details

TCS Journal 2018 Journal Article

Reachability for airline networks: fast algorithm for shortest path problem with time windows

  • Xiaofeng Gao
  • Yueyang Xianzang
  • Xiaotian You
  • Yaru Dang
  • Guihai Chen
  • Xinglong Wang

Airline network, including airports as network nodes and flight routes as directed network edges, has a lot of special features such as departure and arrival times, air ticket budget, flight capacity, transportation cost, etc. Thus, analyzing network behavior and service performance for such a network is much more difficult than that for many other networks. In this paper, taking China domestic airline network as a representative, we try to discuss the reachability issue for each airport respectively, which could reflect its regional connectivity level and service quality of civil aviation. More specifically, we evaluate reachability through many features including node degree, betweenness, closeness, etc. To get the values of some features, we design a fast Dijkstra-based all-pair shortest path algorithm with both time and budget requirements, then use Fenwick Tree to further improve the time efficiency. Actually, it is a shortest path problem with time windows and other constraints. Furthermore, we propose a faster solution by reducing the edges in the duplicated graph as a simplification and then provide the time complexity proof. Finally, we implement Analytic Hierarchy Process (AHP) to convert the reachability feature into numerical values for all airports to measure their service qualities precisely. Our results for China domestic airline network with 210 airports and 69, 160 flight routes will definitely become a guide to airline companies and civil aviation administration for their further development and management.

Details DOI

AAMAS Conference 2016 Conference Paper

Strategy-Proof Data Auctions with Negative Externalities (Extended Abstract)

  • Xiang Wang
  • Zhenzhe Zheng
  • Fan Wu
  • Xiaoju Dong
  • Shaojie Tang
  • Guihai Chen

Data has appeared to be a new kind of commodity with distinctive characteristics, which make it fundamentally different from physical goods as well as traditional digital goods. Therefore, new trading mechanisms for data need to be designed. In this paper, we model the data market as an auction with negative externalities, and design practical mechanisms for data trading. Specifically, we propose a family of Data auctIons in CompetiTive mArkets, namely DIC- TA. DICTA contains two mechanisms, including DICTA- FUL and DICTA-PAR. DICTA-FUL is a direct revelation auction mechanism in full competition markets, achieving strategy-proofness and optimal social welfare. In the partial competition markets, we show that the allocation problem is NP-hard. Therefore, we present an approximation algorithm for winner determination. By carefully integrating this approximation allocation algorithm and a charging scheme, DICTA-PAR achieves both strategy-proofness and d-approximation, where d is the maximum degree of the underlying undirected graph of the competition graph. General Terms Algorithms, Theory, Economics

PDF

TCS Journal 2015 Journal Article

A better approximation for constructing virtual backbone in 3D wireless ad-hoc networks

  • Xiaofeng Gao
  • Jun Li
  • Guihai Chen

Wireless ad hoc networks have been widely used in many areas. In order to improve network performance, we often select a connected dominating set (CDS) as its virtual backbone to deal with routing-related tasks. The problem of finding a minimum CDS (MCDS) for 2-dimensional networks has been widely studied, whereas finding an MCDS in 3-dimensional networks draws more attention recently, because it can formulate the network environment more precisely. Since MCDS problem is proved to be NP-complete, lots of approximations were proposed in literature. Among those, the best approximation for MCDS in 3D network is 14. 937 in [1]. However, their projection method during the approximation deduction process is incorrect, which overthrows its final bound completely. As a consequence, in this paper we will first propose a new projection method to overcome their problem, illustrate the cardinality upper bound of independent points in a graph (which will be used to analyze the approximation ratio), and then optimize the algorithms to select MCDS with prune techniques. The major technique we use is an adaptive jitter scheme, which solves the open question in this area.

Details DOI

AAAI Conference 2014 Conference Paper

A Strategy-Proof Online Auction with Time Discounting Values

  • Fan Wu
  • Junming Liu
  • Zhenzhe Zheng
  • Guihai Chen

Online mechanism design has been widely applied to various practical applications. However, designing a strategy-proof online mechanism is much more challenging than that in a static scenario due to short of knowledge of future information. In this paper, we investigate online auctions with time discounting values, in contrast to the flat values studied in most of existing work. We present a strategy-proof 2-competitive online auction mechanism despite of time discounting values. We also implement our design and compare it with offline optimal solution. Our numerical results show that our design achieves good performance in terms of social welfare, revenue, average winning delay, and average valuation loss.

PDF Details
v2026.09.13