no code implementations • 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 • 9 Mar 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 • 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.
no code implementations • 31 Dec 2023 • Yunfeng Fan, Wenchao Xu, Haozhao Wang, Penghui Ruan, Song Guo
Selecting proper clients to participate in the iterative federated learning (FL) rounds is critical to effectively harness a broad range of distributed datasets.
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.
no code implementations • 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.