1 code implementation • 24 Mar 2024 • Ziwen Zhao, Yuhua Li, Yixiong Zou, Ruixuan Li, Rui Zhang
Graph self-supervised learning is now a go-to method for pre-training graph foundation models, including graph neural networks, graph transformers, and more recent large language model (LLM)-based graph models.
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 • 1 Mar 2024 • Yixiong Zou, Yicong Liu, Yiman Hu, Yuhua Li, Ruixuan Li
To enhance the transferability and facilitate fine-tuning, we introduce a simple yet effective approach to achieve long-range flattening of the minima in the loss landscape.
1 code implementation • 6 Feb 2024 • Ziwen Zhao, Yuhua Li, Yixiong Zou, Jiliang Tang, Ruixuan Li
Inspired by these understandings, we explore non-discrete edge masks, which are sampled from a continuous and dispersive probability distribution instead of the discrete Bernoulli distribution.
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 • 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.
1 code implementation • 8 May 2023 • Han Chen, Ziwen Zhao, Yuhua Li, Yixiong Zou, Ruixuan Li, Rui Zhang
Graph Contrastive Learning (GCL) is an effective way to learn generalized graph representations in a self-supervised manner, and has grown rapidly in recent years.
no code implementations • 26 Apr 2023 • Meixuan Qiao, Jun Wang, Junfu Xiang, Qiyu Hou, Ruixuan Li
Accurately extracting structured data from structure diagrams in financial announcements is of great practical importance for building financial knowledge graphs and further improving the efficiency of various financial applications.
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 • 12 Dec 2022 • Shiwei Li, Huifeng Guo, Lu Hou, Wei zhang, Xing Tang, Ruiming Tang, Rui Zhang, Ruixuan Li
To this end, we formulate a novel quantization training paradigm to compress the embeddings from the training stage, termed low-precision training (LPT).
1 code implementation • 10 Oct 2022 • Yixiong Zou, Shanghang Zhang, Yuhua Li, Ruixuan Li
Few-shot class-incremental learning (FSCIL) is designed to incrementally recognize novel classes with only few training samples after the (pre-)training on base classes with sufficient samples, which focuses on both base-class performance and novel-class generalization.
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 • 31 Aug 2022 • Xiang Fang, Daizong Liu, Pan Zhou, Zichuan Xu, Ruixuan Li
To address this issue, in this paper, we propose a novel Hierarchical Local-Global Transformer (HLGT) to leverage this hierarchy information and model the interactions between different levels of granularity and different modalities for learning more fine-grained multi-modal representations.
no code implementations • 8 Dec 2021 • Wenbo Gou, Wen Shi, Jian Lou, Lijie Huang, Pan Zhou, Ruixuan Li
Natural language video localization (NLVL) is an important task in the vision-language understanding area, which calls for an in-depth understanding of not only computer vision and natural language side alone, but more importantly the interplay between both sides.
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.
no code implementations • 21 Jan 2019 • Jinrong Guo, Wantao Liu, Wang Wang, Qu Lu, Songlin Hu, Jizhong Han, Ruixuan Li
Typically, Ultra-deep neural network(UDNN) tends to yield high-quality model, but its training process is usually resource intensive and time-consuming.