Arrow Research search

Author name cluster

Zhiyuan Wu

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.

7 papers
2 author rows

Possible papers

7

AAAI Conference 2026 Conference Paper

Re-architecting Personalized Federated Learning for Demanding Edge Environments

  • Quyang Pan
  • Sheng Sun
  • Tingting Wi
  • Zhiyuan Wu
  • Yuwei Wang
  • Min Liu
  • Bo Gao
  • Jingyuan Wang

Federated Edge Learning (FEL) has emerged as a promising approach for enabling edge devices to collaboratively train machine learning models while preserving data privacy. Despite its advantages, practical FEL deployment faces significant challenges related to device constraints and device-server interactions, necessitating heterogeneous, user-adaptive model training with limited and uncertain communication. While knowledge cache-driven federated learning offers a promising FEL solution for demanding edge environments, its logits-based interaction design provides poor richness of exchanged information for on-device model optimization. To tackle this issue, we introduce DistilCacheFL, a novel personalized FEL architecture that enhances the exchange of optimization insights while delivering state-of-the-art performance with efficient communication. DistilCacheFL incorporates the benefits of both dataset distillation and knowledge cache-driven federated learning by storing and organizing distilled data as knowledge in the server-side knowledge cache, allowing devices to periodically download and utilize personalized knowledge for local model optimization. Moreover, a device-centric cache sampling strategy is introduced to tailor transferred knowledge for individual devices within controlled communication bandwidth. Extensive experiments on five datasets covering image recognition, audio understanding, and mobile sensor data mining tasks demonstrate that (1) DistilCacheFL significantly outperforms state-of-the-art methods regardless of model structures, data distributions, and modalities. (2) DistilCacheFL can train splendid personalized on-device models with at least 28.6 improvement in communication efficiency.

PDF Details DOI

ICLR Conference 2025 Conference Paper

Addressing Label Shift in Distributed Learning via Entropy Regularization​

  • Zhiyuan Wu
  • Changkyu Choi
  • Xiangcheng Cao
  • Volkan Cevher
  • Ali Ramezani-Kebrya

We address the challenge of minimizing "true risk" in multi-node distributed learning.\footnote{We use the term node to refer to a client, FPGA, APU, CPU, GPU, or worker.} These systems are frequently exposed to both inter-node and intra-node "label shifts", which present a critical obstacle to effectively optimizing model performance while ensuring that data remains confined to each node. To tackle this, we propose the Versatile Robust Label Shift (VRLS) method, which enhances the maximum likelihood estimation of the test-to-train label importance ratio. VRLS incorporates Shannon entropy-based regularization and adjusts the importance ratio during training to better handle label shifts at the test time. In multi-node learning environments, VRLS further extends its capabilities by learning and adapting importance ratios across nodes, effectively mitigating label shifts and improving overall model performance. Experiments conducted on MNIST, Fashion MNIST, and CIFAR-10 demonstrate the effectiveness of VRLS, outperforming baselines by up to 20\% in imbalanced settings. These results highlight the significant improvements VRLS offers in addressing label shifts. Our theoretical analysis further supports this by establishing high-probability bounds on estimation errors.

Details

IROS Conference 2025 Conference Paper

ConViTac: Aligning Visual-Tactile Fusion with Contrastive Representations

  • Zhiyuan Wu
  • Yongqiang Zhao
  • Shan Luo 0001

Vision and touch are two fundamental sensory modalities for robots, offering complementary information that enhances perception and manipulation tasks. Previous research has attempted to jointly learn visual-tactile representations to extract more meaningful information. However, these approaches often rely on direct combination, such as feature addition and concatenation, for modality fusion, which tend to result in poor feature integration. In this paper, we propose ConViTac, a visual-tactile representation learning network designed to enhance the alignment of features during fusion using contrastive representations. Our key contribution is a Contrastive Embedding Conditioning (CEC) mechanism that leverages a contrastive encoder pretrained through self-supervised contrastive learning to project visual and tactile inputs into unified latent embeddings. These embeddings are used to couple visual-tactile feature fusion through cross-modal attention, aiming at aligning the unified representations and enhancing performance on downstream tasks. We conduct extensive experiments to demonstrate the superiority of ConViTac in real world over current state-of-the-art methods and the effectiveness of our proposed CEC mechanism, which improves accuracy by up to 12. 0% in material classification and grasping prediction tasks. More details are on our project website.

Details

NeurIPS Conference 2025 Conference Paper

Transcending Cost-Quality Tradeoff in Agent Serving via Session-Awareness

  • Yanyu Ren
  • Li Chen
  • Dan Li
  • Xizheng Wang
  • Zhiyuan Wu
  • Yukai Miao
  • Yu Bai

Large Language Model (LLM) agents are capable of task execution across various domains by autonomously interacting with environments and refining LLM responses based on feedback. However, existing model serving systems are not optimized for the unique demands of serving agents. Compared to classic model serving, agent serving has different characteristics: predictable request pattern, increasing quality requirement, and unique prompt formatting. We identify a key problem for agent serving: LLM serving systems lack session-awareness. They neither perform effective KV cache management nor precisely select the cheapest yet competent model in each round. This leads to a cost-quality tradeoff, and we identify an opportunity to surpass it in an agent serving system. To this end, we introduce AgServe for AGile AGent SERVing. AgServe features a session-aware server that boosts KV cache reuse via Estimated-Time-of-Arrival-based eviction and in-place positional embedding calibration, a quality-aware client that performs session-aware model cascading through real-time quality assessment, and a dynamic resource scheduler that maximizes GPU utilization. With AgServe, we allow agents to select and upgrade models during the session lifetime, and to achieve similar quality at much lower costs, effectively transcending the tradeoff. Extensive experiments on real testbeds demonstrate that AgServe (1) achieves comparable response quality to GPT-4o at a 16. 5\% cost. (2) delivers 1. 8$\times$ improvement in quality relative to the tradeoff curve.

PDF Details

TIST Journal 2024 Journal Article

Exploring the Distributed Knowledge Congruence in Proxy-data-free Federated Distillation

  • Zhiyuan Wu
  • Sheng Sun
  • Yuwei Wang
  • Min Liu
  • Quyang Pan
  • Junbo Zhang
  • Zeju Li
  • Qingxiang Liu

Federated learning (FL) is a privacy-preserving machine learning paradigm in which the server periodically aggregates local model parameters from cli ents without assembling their private data. Constrained communication and personalization requirements pose severe challenges to FL. Federated distillation (FD) is proposed to simultaneously address the above two problems, which exchanges knowledge between the server and clients, supporting heterogeneous local models while significantly reducing communication overhead. However, most existing FD methods require a proxy dataset, which is often unavailable in reality. A few recent proxy-data-free FD approaches can eliminate the need for additional public data, but suffer from remarkable discrepancy among local knowledge due to client-side model heterogeneity, leading to ambiguous representation on the server and inevitable accuracy degradation. To tackle this issue, we propose a proxy-data-free FD algorithm based on distributed knowledge congruence (FedDKC). FedDKC leverages well-designed refinement strategies to narrow local knowledge differences into an acceptable upper bound, so as to mitigate the negative effects of knowledge incongruence. Specifically, from perspectives of peak probability and Shannon entropy of local knowledge, we design kernel-based knowledge refinement (KKR) and searching-based knowledge refinement (SKR) respectively, and theoretically guarantee that the refined-local knowledge can satisfy an approximately-similar distribution and be regarded as congruent. Extensive experiments conducted on three common datasets demonstrate that our proposed FedDKC significantly outperforms the state-of-the-art on various heterogeneous settings while evidently improving the convergence speed.

Details DOI

ICRA Conference 2024 Conference Paper

SG-RoadSeg: End-to-End Collision-Free Space Detection Sharing Encoder Representations Jointly Learned via Unsupervised Deep Stereo

  • Zhiyuan Wu
  • Jiaqi Li
  • Yi Feng
  • Chengju Liu
  • Wei Ye 0001
  • Qijun Chen
  • Rui Fan 0001

Collision-free space detection is of utmost importance for autonomous robot perception and navigation. State-of-the-art (SoTA) approaches generally extract features from RGB images and an additional source or modality of 3-D information, such as depth or disparity images, using a pair of independent encoders. The extracted features are subsequently fused and decoded to yield semantic predictions of collision-free spaces. Such feature-fusion approaches become infeasible in scenarios, where the sensor for 3-D information acquisition is unavailable, or just when multi-sensor calibration falls short of the necessary precision. To overcome these limitations, this paper introduces a novel end-to-end collision-free space detection network, referred to as SG-RoadSeg, built upon our previous work SNE-RoadSeg. A key contribution of this paper is a strategy for sharing encoder representations that are co-learned through both semantic segmentation and unsupervised stereo matching tasks, enabling the features extracted from RGB images to contain both semantic and spatial geometric information. The unsupervised deep stereo serves as an auxiliary functionality, capable of generating accurate disparity maps that can be used by other perception tasks that require depth-related data. Comprehensive experimental results on the KITTI road and semantics datasets validate the effectiveness of our proposed architecture and encoder representation sharing strategy. SG-RoadSeg also demonstrates superior performance than other SoTA collision-free space detection approaches. Our source code, demo video, and supplement are publicly available at mias. group/SG-RoadSeg.

Details

ICRA Conference 2023 Conference Paper

Transparent Objects: A Corner Case in Stereo Matching

  • Zhiyuan Wu
  • Shuai Su
  • Qijun Chen
  • Rui Fan 0001

Stereo matching is a common technique used in 3D perception, but transparent objects such as reflective and penetrable glass pose a challenge as their disparities are often estimated inaccurately. In this paper, we propose transparency-aware stereo (TA-Stereo), an effective solution to tackle this issue. TA-Stereo first utilizes a semantic segmentation or salient object detection network to identify transparent objects, and then homogenizes them to enable stereo matching algorithms to handle them as non-transparent objects. To validate the effectiveness of our proposed TA-Stereo strategy, we collect 260 images containing transparent objects from the KITTI Stereo 2012 and 2015 datasets and manually label pixel-level ground truth. We evaluate our strategy with six deep stereo networks and two types of transparent object detection methods. Our experiments demonstrate that TA-Stereo significantly improves the disparity accuracy of transparent objects. Our project webpage can be accessed at mias. group/TA-Stereo.

Details
v2026.09.13