Search Results for author: Daochen Zha

Found 50 papers, 31 papers with code

GAugLLM: Improving Graph Contrastive Learning for Text-Attributed Graphs with Large Language Models

1 code implementation17 Jun 2024 Yi Fang, Dongzhe Fan, Daochen Zha, Qiaoyu Tan

This work studies self-supervised graph learning for text-attributed graphs (TAGs) where nodes are represented by textual attributes.

Contrastive Learning Graph Learning +1

GraphFM: A Comprehensive Benchmark for Graph Foundation Model

1 code implementation12 Jun 2024 Yuhao Xu, Xinqi Liu, Keyu Duan, Yi Fang, Yu-Neng Chuang, Daochen Zha, Qiaoyu Tan

To address these questions, we have constructed a rigorous benchmark that thoroughly analyzes and studies the generalization and scalability of self-supervised Graph Neural Network (GNN) models.

Graph Neural Network Link Prediction +3

Denoising-Aware Contrastive Learning for Noisy Time Series

1 code implementation7 Jun 2024 Shuang Zhou, Daochen Zha, Xiao Shen, Xiao Huang, Rui Zhang, Fu-Lai Chung

However, this pre-processing approach may not fully eliminate the effect of noise in SSL for two reasons: (i) the diverse types of noise in time series make it difficult to automatically determine suitable denoising methods; (ii) noise can be amplified after mapping raw data into latent space.

Contrastive Learning Denoising +2

Cost-efficient Knowledge-based Question Answering with Large Language Models

no code implementations27 May 2024 Junnan Dong, Qinggang Zhang, Chuang Zhou, Hao Chen, Daochen Zha, Xiao Huang

We are motivated to combine LLMs and prior small models on knowledge graphs (KGMs) for both inferential accuracy and cost saving.

Knowledge Graphs Model Selection +2

E2GNN: Efficient Graph Neural Network Ensembles for Semi-Supervised Classification

1 code implementation6 May 2024 Xin Zhang, Daochen Zha, Qiaoyu Tan

Next, instead of directly combing their outputs for label inference, we train a simple multi-layer perceptron--MLP model to mimic their predictions on both labeled and unlabeled nodes.

Ensemble Learning Graph Neural Network

Modality-Aware Integration with Large Language Models for Knowledge-based Visual Question Answering

no code implementations20 Feb 2024 Junnan Dong, Qinggang Zhang, Huachi Zhou, Daochen Zha, Pai Zheng, Xiao Huang

Specifically, (i) we propose a two-stage prompting strategy with LLMs to densely embody the image into a scene graph with detailed visual features; (ii) We construct a coupled concept graph by linking the mentioned entities with external facts.

Knowledge Graphs Question Answering +1

Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learning

no code implementations29 Dec 2023 Xiao-Yang Liu, Rongyi Zhu, Daochen Zha, Jiechao Gao, Shan Zhong, Matt White, Meikang Qiu

The surge in interest and application of large language models (LLMs) has sparked a drive to fine-tune these models to suit specific applications, such as finance and medical science.

Federated Learning Language Modelling +1

KnowGPT: Knowledge Graph based Prompting for Large Language Models

no code implementations11 Dec 2023 Qinggang Zhang, Junnan Dong, Hao Chen, Daochen Zha, Zailiang Yu, Xiao Huang

However, most state-of-the-art LLMs are closed-source, making it challenging to develop a prompting framework that can efficiently and effectively integrate KGs into LLMs with hard prompts only.

Knowledge Graphs Prompt Engineering +2

Enhanced Generalization through Prioritization and Diversity in Self-Imitation Reinforcement Learning over Procedural Environments with Sparse Rewards

no code implementations1 Nov 2023 Alain Andres, Daochen Zha, Javier Del Ser

Exploration poses a fundamental challenge in Reinforcement Learning (RL) with sparse rewards, limiting an agent's ability to learn optimal decision-making due to a lack of informative feedback signals.

Diversity Imitation Learning +1

DiscoverPath: A Knowledge Refinement and Retrieval System for Interdisciplinarity on Biomedical Research

1 code implementation4 Sep 2023 Yu-Neng Chuang, Guanchu Wang, Chia-Yuan Chang, Kwei-Herng Lai, Daochen Zha, Ruixiang Tang, Fan Yang, Alfredo Costilla Reyes, Kaixiong Zhou, Xiaoqian Jiang, Xia Hu

The exponential growth in scholarly publications necessitates advanced tools for efficient article retrieval, especially in interdisciplinary fields where diverse terminologies are used to describe similar research.

named-entity-recognition Named Entity Recognition +5

Tackling Diverse Minorities in Imbalanced Classification

no code implementations28 Aug 2023 Kwei-Herng Lai, Daochen Zha, Huiyuan Chen, Mangesh Bendre, Yuzhong Chen, Mahashweta Das, Hao Yang, Xia Hu

Imbalanced datasets are commonly observed in various real-world applications, presenting significant challenges in training classifiers.

Anomaly Detection Classification +2

FinGPT: Democratizing Internet-scale Data for Financial Large Language Models

1 code implementation19 Jul 2023 Xiao-Yang Liu, Guoxuan Wang, Hongyang Yang, Daochen Zha

In light of this, we aim to democratize Internet-scale financial data for LLMs, which is an open challenge due to diverse data sources, low signal-to-noise ratio, and high time-validity.

Algorithmic Trading Sentiment Analysis

OpenGSL: A Comprehensive Benchmark for Graph Structure Learning

1 code implementation NeurIPS 2023 Zhiyao Zhou, Sheng Zhou, Bochao Mao, Xuanyi Zhou, Jiawei Chen, Qiaoyu Tan, Daochen Zha, Yan Feng, Chun Chen, Can Wang

Moreover, we observe that the learned graph structure demonstrates a strong generalization ability across different GNN models, despite the high computational and space consumption.

Graph structure learning Representation Learning

Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model

1 code implementation NeurIPS 2023 Zirui Liu, Guanchu Wang, Shaochen Zhong, Zhaozhuo Xu, Daochen Zha, Ruixiang Tang, Zhimeng Jiang, Kaixiong Zhou, Vipin Chaudhary, Shuai Xu, Xia Hu

While the model parameters do contribute to memory usage, the primary memory bottleneck during training arises from storing feature maps, also known as activations, as they are crucial for gradient calculation.

Language Modelling Stochastic Optimization

Dynamic Datasets and Market Environments for Financial Reinforcement Learning

4 code implementations25 Apr 2023 Xiao-Yang Liu, Ziyi Xia, Hongyang Yang, Jiechao Gao, Daochen Zha, Ming Zhu, Christina Dan Wang, Zhaoran Wang, Jian Guo

The financial market is a particularly challenging playground for deep reinforcement learning due to its unique feature of dynamic datasets.

reinforcement-learning

Interactive System-wise Anomaly Detection

no code implementations21 Apr 2023 Guanchu Wang, Ninghao Liu, Daochen Zha, Xia Hu

Anomaly detection, where data instances are discovered containing feature patterns different from the majority, plays a fundamental role in various applications.

Anomaly Detection Data Poisoning +1

Data-centric Artificial Intelligence: A Survey

10 code implementations17 Mar 2023 Daochen Zha, Zaid Pervaiz Bhat, Kwei-Herng Lai, Fan Yang, Zhimeng Jiang, Shaochen Zhong, Xia Hu

Artificial Intelligence (AI) is making a profound impact in almost every domain.

Towards Personalized Preprocessing Pipeline Search

no code implementations28 Feb 2023 Diego Martinez, Daochen Zha, Qiaoyu Tan, Xia Hu

However, the existing systems often have a very small search space for feature preprocessing with the same preprocessing pipeline applied to all the numerical features.

AutoML Clustering +1

Fairly Predicting Graft Failure in Liver Transplant for Organ Assigning

no code implementations18 Feb 2023 Sirui Ding, Ruixiang Tang, Daochen Zha, Na Zou, Kai Zhang, Xiaoqian Jiang, Xia Hu

To tackle this problem, this work proposes a fair machine learning framework targeting graft failure prediction in liver transplant.

Fairness Knowledge Distillation

Data-centric AI: Perspectives and Challenges

1 code implementation12 Jan 2023 Daochen Zha, Zaid Pervaiz Bhat, Kwei-Herng Lai, Fan Yang, Xia Hu

The role of data in building AI systems has recently been significantly magnified by the emerging concept of data-centric AI (DCAI), which advocates a fundamental shift from model advancements to ensuring data quality and reliability.

Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection

1 code implementation23 Dec 2022 Qiaoyu Tan, Xin Zhang, Ninghao Liu, Daochen Zha, Li Li, Rui Chen, Soo-Hyun Choi, Xia Hu

To bridge the gap, we introduce a Personalized Subgraph Selector (PS2) as a plug-and-play framework to automatically, personally, and inductively identify optimal subgraphs for different edges when performing GNNLP.

Link Prediction

SurCo: Learning Linear Surrogates For Combinatorial Nonlinear Optimization Problems

no code implementations22 Oct 2022 Aaron Ferber, Taoan Huang, Daochen Zha, Martin Schubert, Benoit Steiner, Bistra Dilkina, Yuandong Tian

Optimization problems with nonlinear cost functions and combinatorial constraints appear in many real-world applications but remain challenging to solve efficiently compared to their linear counterparts.

Combinatorial Optimization

RSC: Accelerating Graph Neural Networks Training via Randomized Sparse Computations

no code implementations19 Oct 2022 Zirui Liu, Shengyuan Chen, Kaixiong Zhou, Daochen Zha, Xiao Huang, Xia Hu

To this end, we propose Randomized Sparse Computation, which for the first time demonstrate the potential of training GNNs with approximated operations.

DreamShard: Generalizable Embedding Table Placement for Recommender Systems

1 code implementation5 Oct 2022 Daochen Zha, Louis Feng, Qiaoyu Tan, Zirui Liu, Kwei-Herng Lai, Bhargav Bhushanam, Yuandong Tian, Arun Kejariwal, Xia Hu

Although prior work has explored learning-based approaches for the device placement of computational graphs, embedding table placement remains to be a challenging problem because of 1) the operation fusion of embedding tables, and 2) the generalizability requirement on unseen placement tasks with different numbers of tables and/or devices.

Recommendation Systems Reinforcement Learning (RL)

Towards Automated Imbalanced Learning with Deep Hierarchical Reinforcement Learning

2 code implementations26 Aug 2022 Daochen Zha, Kwei-Herng Lai, Qiaoyu Tan, Sirui Ding, Na Zou, Xia Hu

Motivated by this, we investigate developing a learning-based over-sampling algorithm to optimize the classification performance, which is a challenging task because of the huge and hierarchical decision space.

Hierarchical Reinforcement Learning reinforcement-learning +1

AutoShard: Automated Embedding Table Sharding for Recommender Systems

1 code implementation12 Aug 2022 Daochen Zha, Louis Feng, Bhargav Bhushanam, Dhruv Choudhary, Jade Nie, Yuandong Tian, Jay Chae, Yinbin Ma, Arun Kejariwal, Xia Hu

This is a significant design challenge of distributed systems named embedding table sharding, i. e., how we should partition the embedding tables to balance the costs across devices, which is a non-trivial task because 1) it is hard to efficiently and precisely measure the cost, and 2) the partition problem is known to be NP-hard.

Recommendation Systems

Auto-PINN: Understanding and Optimizing Physics-Informed Neural Architecture

no code implementations27 May 2022 Yicheng Wang, Xiaotian Han, Chia-Yuan Chang, Daochen Zha, Ulisses Braga-Neto, Xia Hu

Physics-informed neural networks (PINNs) are revolutionizing science and engineering practice by bringing together the power of deep learning to bear on scientific computation.

Hyperparameter Optimization Neural Architecture Search

Towards Similarity-Aware Time-Series Classification

1 code implementation5 Jan 2022 Daochen Zha, Kwei-Herng Lai, Kaixiong Zhou, Xia Hu

Prior work has approached TSC from two major directions: (1) similarity-based methods that classify time-series based on the nearest neighbors, and (2) deep learning models that directly learn the representations for classification in a data-driven manner.

Classification Dynamic Time Warping +5

Dirichlet Energy Constrained Learning for Deep Graph Neural Networks

1 code implementation NeurIPS 2021 Kaixiong Zhou, Xiao Huang, Daochen Zha, Rui Chen, Li Li, Soo-Hyun Choi, Xia Hu

To this end, we analyze the bottleneck of deep GNNs by leveraging the Dirichlet energy of node embeddings, and propose a generalizable principle to guide the training of deep GNNs.

DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning

1 code implementation11 Jun 2021 Daochen Zha, Jingru Xie, Wenye Ma, Sheng Zhang, Xiangru Lian, Xia Hu, Ji Liu

Games are abstractions of the real world, where artificial agents learn to compete and cooperate with other agents.

Game of Poker Multi-agent Reinforcement Learning +2

Simplifying Deep Reinforcement Learning via Self-Supervision

1 code implementation10 Jun 2021 Daochen Zha, Kwei-Herng Lai, Kaixiong Zhou, Xia Hu

Supervised regression to demonstrations has been demonstrated to be a stable way to train deep policy networks.

regression reinforcement-learning +1

Learning Disentangled Representations for Time Series

no code implementations17 May 2021 Yuening Li, Zhengzhang Chen, Daochen Zha, Mengnan Du, Denghui Zhang, Haifeng Chen, Xia Hu

Motivated by the success of disentangled representation learning in computer vision, we study the possibility of learning semantic-rich time-series representations, which remains unexplored due to three main challenges: 1) sequential data structure introduces complex temporal correlations and makes the latent representations hard to interpret, 2) sequential models suffer from KL vanishing problem, and 3) interpretable semantic concepts for time-series often rely on multiple factors instead of individuals.

Disentanglement Time Series +1

Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments

3 code implementations ICLR 2021 Daochen Zha, Wenye Ma, Lei Yuan, Xia Hu, Ji Liu

Unfortunately, methods based on intrinsic rewards often fall short in procedurally-generated environments, where a different environment is generated in each episode so that the agent is not likely to visit the same state more than once.

Meta-AAD: Active Anomaly Detection with Deep Reinforcement Learning

1 code implementation16 Sep 2020 Daochen Zha, Kwei-Herng Lai, Mingyang Wan, Xia Hu

Specifically, existing strategies have been focused on making the top instances more likely to be anomalous based on the feedback.

Anomaly Detection reinforcement-learning +2

Policy-GNN: Aggregation Optimization for Graph Neural Networks

1 code implementation26 Jun 2020 Kwei-Herng Lai, Daochen Zha, Kaixiong Zhou, Xia Hu

It is a challenging task to develop an effective aggregation strategy for each node, given complex graphs and sparse features.

Node Classification Reinforcement Learning (RL)

AutoOD: Automated Outlier Detection via Curiosity-guided Search and Self-imitation Learning

no code implementations19 Jun 2020 Yuening Li, Zhengzhang Chen, Daochen Zha, Kaixiong Zhou, Haifeng Jin, Haifeng Chen, Xia Hu

Outlier detection is an important data mining task with numerous practical applications such as intrusion detection, credit card fraud detection, and video surveillance.

Fraud Detection Image Classification +7

Towards Deeper Graph Neural Networks with Differentiable Group Normalization

1 code implementation NeurIPS 2020 Kaixiong Zhou, Xiao Huang, Yuening Li, Daochen Zha, Rui Chen, Xia Hu

Graph neural networks (GNNs), which learn the representation of a node by aggregating its neighbors, have become an effective computational tool in downstream applications.

Dual Policy Distillation

1 code implementation7 Jun 2020 Kwei-Herng Lai, Daochen Zha, Yuening Li, Xia Hu

In this work, we introduce dual policy distillation(DPD), a student-student framework in which two learners operate on the same environment to explore different perspectives of the environment and extract knowledge from each other to enhance their learning.

Continuous Control reinforcement-learning +1

Multi-Channel Graph Convolutional Networks

no code implementations17 Dec 2019 Kaixiong Zhou, Qingquan Song, Xiao Huang, Daochen Zha, Na Zou, Xia Hu

To further improve the graph representation learning ability, hierarchical GNN has been explored.

Clustering Graph Classification +1

RLCard: A Toolkit for Reinforcement Learning in Card Games

8 code implementations10 Oct 2019 Daochen Zha, Kwei-Herng Lai, Yuanpu Cao, Songyi Huang, Ruzhe Wei, Junyu Guo, Xia Hu

The goal of RLCard is to bridge reinforcement learning and imperfect information games, and push forward the research of reinforcement learning in domains with multiple agents, large state and action space, and sparse reward.

Board Games Game of Poker +3

PyODDS: An End-to-End Outlier Detection System

1 code implementation7 Oct 2019 Yuening Li, Daochen Zha, Na Zou, Xia Hu

PyODDS is an end-to end Python system for outlier detection with database support.

BIG-bench Machine Learning Outlier Detection

Experience Replay Optimization

no code implementations19 Jun 2019 Daochen Zha, Kwei-Herng Lai, Kaixiong Zhou, Xia Hu

Experience replay enables reinforcement learning agents to memorize and reuse past experiences, just as humans replay memories for the situation at hand.

Continuous Control reinforcement-learning +1

Multi-label Dataless Text Classification with Topic Modeling

1 code implementation5 Nov 2017 Daochen Zha, Chenliang Li

With a few seed words relevant to each category, SMTM conducts multi-label classification for a collection of documents without any labeled document.

General Classification Multi-Label Classification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.