no code implementations • 15 Jan 2025 • Yichen Li, Yuying Wang, Jiahua Dong, Haozhao Wang, Yining Qi, Rui Zhang, Ruixuan Li
We revisit this problem with a large-scale benchmark and analyze the performance of state-of-the-art FCL approaches under different resource-constrained settings.
no code implementations • 6 Jan 2025 • Jiaze Li, Haoran Xu, Shiding Zhu, Junwei He, Haozhao Wang
We propose a Prompt Semantic Supervision Module using text encoder of CLIP to ensure semantic consistency between videos and conditional prompts.
no code implementations • 24 Dec 2024 • Tianzhe Xiao, Yichen Li, Yining Qi, Haozhao Wang, Ruixuan Li
Recent studies have shown that Federated learning (FL) is vulnerable to Gradient Inversion Attacks (GIA), which can recover private training data from shared gradients.
no code implementations • 23 Dec 2024 • Yuying Wang, Yichen Li, Haozhao Wang, Lei Zhao, Xiaofang Zhang
In this paper, we study the privacy-preserving cross-project defect prediction with data heterogeneity under the federated learning framework.
no code implementations • 18 Dec 2024 • Wenchao Xu, Jinyu Chen, Peirong Zheng, Xiaoquan Yi, Tianyi Tian, Wenhui Zhu, Quan Wan, Haozhao Wang, Yunfeng Fan, Qinliang Su, Xuemin Shen
Foundation model (FM) powered agent services are regarded as a promising solution to develop intelligent and personalized applications for advancing toward Artificial General Intelligence (AGI).
no code implementations • 18 Dec 2024 • Yichen Li, Yuying Wang, Tianzhe Xiao, Haozhao Wang, Yining Qi, Ruixuan Li
Specifically, we first apply traditional regularization techniques to CFL and observe that existing regularization techniques, especially synaptic intelligence, can achieve promising results under homogeneous data distribution but fail when the data is heterogeneous.
no code implementations • 18 Dec 2024 • Yichen Li, Haozhao Wang, Wenchao Xu, Tianzhe Xiao, Hong Liu, Minzhu Tu, Yuying Wang, Xin Yang, Rui Zhang, Shui Yu, Song Guo, Ruixuan Li
To achieve high reliability and scalability in deploying this paradigm in distributed systems, it is essential to conquer challenges stemming from both spatial and temporal dimensions, manifesting as distribution shifts, catastrophic forgetting, heterogeneity, and privacy issues.
no code implementations • 25 Nov 2024 • Xingshuo Han, Xuanye Zhang, Xiang Lan, Haozhao Wang, Shengmin Xu, Shen Ren, Jason Zeng, Ming Wu, Michael Heinrich, Tianwei Zhang
Federated learning (FL) enables the training of deep learning models on distributed clients to preserve data privacy.
1 code implementation • 8 Oct 2024 • Wei Liu, Zhiying Deng, Zhongyu Niu, Jun Wang, Haozhao Wang, Yuankai Zhang, Ruixuan Li
In the optimization objectives of these methods, spurious features are still distinguished from plain noise, which hinders the discovery of causal rationales.
1 code implementation • 30 Sep 2024 • Shiwei Li, Zhuoqi Hu, Xing Tang, Haozhao Wang, Shijie Xu, Weihong Luo, Yuhua Li, Xiuqiang He, Ruixuan Li
Specifically, to reduce the size of the search space, we first group features by frequency and then search precision for each feature group.
no code implementations • 20 Aug 2024 • Yuankai Zhang, Lingxiao Kong, Haozhao Wang, Ruixuan Li, Jun Wang, Yuhua Li, Wei Liu
Based on this, we make a series of recommendations for improving rationalization models in terms of explanation.
1 code implementation • 6 Aug 2024 • Shiwei Li, Wenchao Xu, Haozhao Wang, Xing Tang, Yining Qi, Shijie Xu, Weihong Luo, Yuhua Li, Xiuqiang He, Ruixuan Li
To this end, we propose Federated Binarization-Aware Training (FedBAT), a novel framework that directly learns binary model updates during the local training process, thus inherently reducing the approximation errors.
1 code implementation • 6 Aug 2024 • Shiwei Li, Yingyi Cheng, Haozhao Wang, Xing Tang, Shijie Xu, Weihong Luo, Yuhua Li, Dugang Liu, Xiuqiang He, Ruixuan Li
For this purpose, we propose Federated Masked Random Noise (FedMRN), a novel framework that enables clients to learn a 1-bit mask for each model parameter and apply masked random noise (i. e., the Hadamard product of random noise and masks) to represent model updates.
1 code implementation • 4 Aug 2024 • Fushuo Huo, Wenchao Xu, Zhong Zhang, Haozhao Wang, Zhicheng Chen, Peilin Zhao
While Large Vision-Language Models (LVLMs) have rapidly advanced in recent years, the prevalent issue known as the `hallucination' problem has emerged as a significant bottleneck, hindering their real-world deployments.
1 code implementation • 28 Jul 2024 • Yunfeng Fan, Wenchao Xu, Haozhao Wang, Junhong Liu, Song Guo
Recently, Multimodal Learning (MML) has gained significant interest as it compensates for single-modality limitations through comprehensive complementary information within multimodal data.
no code implementations • 6 Jul 2024 • Yichen Li, Wenchao Xu, Haozhao Wang, Ruixuan Li, Yining Qi, Jingcai Guo
Then, the client can choose to adopt a new initial model or a previous model with similar knowledge to train the new task and simultaneously migrate knowledge from previous tasks based on these correlations.
1 code implementation • 25 Apr 2024 • Zhijie Rao, Jingcai Guo, Xiaocheng Lu, Jingming Liang, Jie Zhang, Haozhao Wang, Kang Wei, Xiaofeng Cao
Zero-shot learning has consistently yielded remarkable progress via modeling nuanced one-to-one visual-attribute correlation.
no code implementations • CVPR 2024 • Yichen Li, Qunwei Li, Haozhao Wang, Ruixuan Li, Wenliang Zhong, Guannan Zhang
Then, the client trains the local model with both the cached samples and the samples from the new task.
no code implementations • 4 Jan 2024 • Yuxuan Liu, Haozhao Wang, Shuang Wang, Zhiming He, Wenchao Xu, Jialiang Zhu, Fan Yang
Estimating causal effects among different events is of great importance to critical fields such as drug development.
no code implementations • CVPR 2024 • Fushuo Huo, Wenchao Xu, Jingcai Guo, Haozhao Wang, Song Guo
We empirically reveal that the modality gap i. e. modality imbalance and soft label misalignment incurs the ineffectiveness of traditional KD in CMKD.
no code implementations • 31 Dec 2023 • Yunfeng Fan, Wenchao Xu, Haozhao Wang, Jiaqi Zhu, Song Guo
Federated learning (FL) underpins advancements in privacy-preserving distributed computing by collaboratively training neural networks without exposing clients' raw data.
1 code implementation • 31 Dec 2023 • Yunfeng Fan, Wenchao Xu, Haozhao Wang, Fushuo Huo, Jinyu Chen, Song Guo
On the other hand, we propose the modality selection aiming to select subsets of local modalities with great diversity and achieving global modal balance simultaneously.
no code implementations • 21 Dec 2023 • Jie Han, Yixiong Zou, Haozhao Wang, Jun Wang, Wei Liu, Yao Wu, Tao Zhang, Ruixuan Li
Therefore, current works first train a model on source domains with sufficiently labeled data, and then transfer the model to target domains where only rarely labeled data is available.
1 code implementation • 7 Dec 2023 • Wei Liu, Haozhao Wang, Jun Wang, Zhiying Deng, Yuankai Zhang, Cheng Wang, Ruixuan Li
Rationalization empowers deep learning models with self-explaining capabilities through a cooperative game, where a generator selects a semantically consistent subset of the input as a rationale, and a subsequent predictor makes predictions based on the selected rationale.
1 code implementation • NeurIPS 2023 • Jiashuo Wang, Haozhao Wang, Shichao Sun, Wenjie Li
For this alignment, current popular methods leverage a reinforcement learning (RL) approach with a reward model trained on feedback from humans.
1 code implementation • NeurIPS 2023 • Wei Liu, Jun Wang, Haozhao Wang, Ruixuan Li, Zhiying Deng, Yuankai Zhang, Yang Qiu
Instead of attempting to rectify the issues of the MMI criterion, we propose a novel criterion to uncover the causal rationale, termed the Minimum Conditional Dependence (MCD) criterion, which is grounded on our finding that the non-causal features and the target label are \emph{d-separated} by the causal rationale.
1 code implementation • 23 May 2023 • Wei Liu, Jun Wang, Haozhao Wang, Ruixuan Li, Yang Qiu, Yuankai Zhang, Jie Han, Yixiong Zou
However, such a cooperative game may incur the degeneration problem where the predictor overfits to the uninformative pieces generated by a not yet well-trained generator and in turn, leads the generator to converge to a sub-optimal model that tends to select senseless pieces.
1 code implementation • 8 May 2023 • Wei Liu, Haozhao Wang, Jun Wang, Ruixuan Li, Xinyang Li, Yuankai Zhang, Yang Qiu
Rationalization is to employ a generator and a predictor to construct a self-explaining NLP model in which the generator selects a subset of human-intelligible pieces of the input text to the following predictor.
no code implementations • 6 May 2023 • Daizong Liu, Xiaoye Qu, Jianfeng Dong, Pan Zhou, Zichuan Xu, Haozhao Wang, Xing Di, Weining Lu, Yu Cheng
This paper addresses the temporal sentence grounding (TSG).
no code implementations • 20 Mar 2023 • Fushuo Huo, Wenchao Xu, Jingcai Guo, Haozhao Wang, Yunfeng Fan, Song Guo
In this paper, we propose a novel Dual-prototype Self-augment and Refinement method (DSR) for NO-CL problem, which consists of two strategies: 1) Dual class prototypes: vanilla and high-dimensional prototypes are exploited to utilize the pre-trained information and obtain robust quasi-orthogonal representations rather than example buffers for both privacy preservation and memory reduction.
no code implementations • 14 Mar 2023 • Yunfeng Fan, Wenchao Xu, Haozhao Wang, Jiaqi Zhu, Junxiao Wang, Song Guo
Unfortunately, OCI learning can suffer from catastrophic forgetting (CF) as the decision boundaries for old classes can become inaccurate when perturbated by new ones.
no code implementations • CVPR 2023 • Haozhao Wang, Yichen Li, Wenchao Xu, Ruixuan Li, Yufeng Zhan, Zhigang Zeng
In this paper, we propose a new perspective that treats the local data in each client as a specific domain and design a novel domain knowledge aware federated distillation method, dubbed DaFKD, that can discern the importance of each model to the distillation sample, and thus is able to optimize the ensemble of soft predictions from diverse models.
no code implementations • 19 Nov 2022 • Fushuo Huo, Wenchao Xu, Song Guo, Jingcai Guo, Haozhao Wang, Ziming Liu, Xiaocheng Lu
Open-World Compositional Zero-shot Learning (OW-CZSL) aims to recognize novel compositions of state and object primitives in images with no priors on the compositional space, which induces a tremendously large output space containing all possible state-object compositions.
no code implementations • 15 Nov 2022 • Jinyu Chen, Wenchao Xu, Song Guo, Junxiao Wang, Jie Zhang, Haozhao Wang
Federated Learning (FL) is an emerging paradigm that enables distributed users to collaboratively and iteratively train machine learning models without sharing their private data.
no code implementations • CVPR 2023 • Yunfeng Fan, Wenchao Xu, Haozhao Wang, Junxiao Wang, Song Guo
Multimodal learning (MML) aims to jointly exploit the common priors of different modalities to compensate for their inherent limitations.
1 code implementation • 17 Sep 2022 • Wei Liu, Haozhao Wang, Jun Wang, Ruixuan Li, Chao Yue, Yuankai Zhang
Conventional works generally employ a two-phase model in which a generator selects the most important pieces, followed by a predictor that makes predictions based on the selected pieces.
no code implementations • 14 Apr 2022 • Feijie Wu, Shiqi He, Song Guo, Zhihao Qu, Haozhao Wang, Weihua Zhuang, Jie Zhang
Traditional one-bit compressed stochastic gradient descent can not be directly employed in multi-hop all-reduce, a widely adopted distributed training paradigm in network-intensive high-performance computing systems such as public clouds.
1 code implementation • 17 Dec 2021 • Feijie Wu, Song Guo, Haozhao Wang, Zhihao Qu, Haobo Zhang, Jie Zhang, Ziming Liu
In the setting of federated optimization, where a global model is aggregated periodically, step asynchronism occurs when participants conduct model training by efficiently utilizing their computational resources.
1 code implementation • NeurIPS 2021 • Jie Zhang, Song Guo, Xiaosong Ma, Haozhao Wang, Wencao Xu, Feijie Wu
To deal with such model constraints, we exploit the potentials of heterogeneous model settings and propose a novel training framework to employ personalized models for different clients.
no code implementations • 22 Jan 2020 • Haozhao Wang, Zhihao Qu, Song Guo, Xin Gao, Ruixuan Li, Baoliu Ye
A major bottleneck on the performance of distributed Stochastic Gradient Descent (SGD) algorithm for large-scale Federated Learning is the communication overhead on pushing local gradients and pulling global model.
no code implementations • 21 Feb 2019 • Chengjie Li, Ruixuan Li, Haozhao Wang, Yuhua Li, Pan Zhou, Song Guo, Keqin Li
Distributed asynchronous offline training has received widespread attention in recent years because of its high performance on large-scale data and complex models.