papers

Publications (60)

cs.LG2024

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

Yi Fang, Dongzhe Fan, Daochen Zha +1

This work studies self-supervised graph learning for text-attributed graphs (TAGs) where nodes are represented by textual attributes. Unlike traditional graph contrastive methods t…

cs.CL2023

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

Xiao-Yang Liu, Guoxuan Wang, Hongyang Yang +1

Large language models (LLMs) have demonstrated remarkable proficiency in understanding and generating human-like texts, which may potentially revolutionize the finance industry. Ho…

cs.CV2024

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

Junnan Dong, Qinggang Zhang, Huachi Zhou +3

Knowledge-based visual question answering (KVQA) has been extensively studied to answer visual questions with external knowledge, e.g., knowledge graphs (KGs). While several attemp…

cs.AI2021

DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning

Daochen Zha, Jingru Xie, Wenye Ma +4

Games are abstractions of the real world, where artificial agents learn to compete and cooperate with other agents. While significant achievements have been made in various perfect…

cs.LG2020

Meta-AAD: Active Anomaly Detection with Deep Reinforcement Learning

Daochen Zha, Kwei-Herng Lai, Mingyang Wan +1

High false-positive rate is a long-standing challenge for anomaly detection algorithms, especially in high-stake applications. To identify the true anomalies, in practice, analysts…

cs.AI2020

RLCard: A Toolkit for Reinforcement Learning in Card Games

Daochen Zha, Kwei-Herng Lai, Yuanpu Cao +4

RLCard is an open-source toolkit for reinforcement learning research in card games. It supports various card environments with easy-to-use interfaces, including Blackjack, Leduc Ho…

cs.LG2023

Interactive System-wise Anomaly Detection

Guanchu Wang, Ninghao Liu, Daochen Zha +1

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

cs.LG2022

Towards Similarity-Aware Time-Series Classification

Daochen Zha, Kwei-Herng Lai, Kaixiong Zhou +1

We study time-series classification (TSC), a fundamental task of time-series data mining. Prior work has approached TSC from two major directions: (1) similarity-based methods that…

cs.IR2022

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

Qiaoyu Tan, Xin Zhang, Ninghao Liu +5

Graph neural networks (GNNs) have received remarkable success in link prediction (GNNLP) tasks. Existing efforts first predefine the subgraph for the whole dataset and then apply G…

cs.CV2022

BED: A Real-Time Object Detection System for Edge Devices

Guanchu Wang, Zaid Pervaiz Bhat, Zhimeng Jiang +8

Deploying deep neural networks~(DNNs) on edge devices provides efficient and effective solutions for the real-world tasks. Edge devices have been used for collecting a large volume…

cs.LG2026

JourneyFormer: Encoding Airbnb Guest Journey with Sequence Modeling

Daochen Zha, Chun How Tan, Xin Liu +9

Sequence modeling has become increasingly popular in recommendation and ranking algorithms, owing to its capacity to model users' historical behaviors and infer user intentions. De…

cs.LG2024

Denoising-Aware Contrastive Learning for Noisy Time Series

Shuang Zhou, Daochen Zha, Xiao Shen +3

Time series self-supervised learning (SSL) aims to exploit unlabeled data for pre-training to mitigate the reliance on labels. Despite the great success in recent years, there is l…

cs.LG2024

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

Xin Zhang, Daochen Zha, Qiaoyu Tan

This work studies ensemble learning for graph neural networks (GNNs) under the popular semi-supervised setting. Ensemble learning has shown superiority in improving the accuracy an…

cs.LG2024

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

Zirui Liu, Guanchu Wang, Shaochen Zhong +8

With the rapid growth in model size, fine-tuning the large pre-trained language model has become increasingly difficult due to its extensive memory usage. Previous works usually fo…

cs.IR2023

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

Yu-Neng Chuang, Guanchu Wang, Chia-Yuan Chang +8

The exponential growth in scholarly publications necessitates advanced tools for efficient article retrieval, especially in interdisciplinary fields where diverse terminologies are…

cs.SI2019

Multi-Channel Graph Convolutional Networks

Kaixiong Zhou, Qingquan Song, Xiao Huang +3

Graph neural networks (GNN) has been demonstrated to be effective in classifying graph structures. To further improve the graph representation learning ability, hierarchical GNN ha…

cs.LG2023

RSC: Accelerating Graph Neural Networks Training via Randomized Sparse Computations

Zirui Liu, Shengyuan Chen, Kaixiong Zhou +3

The training of graph neural networks (GNNs) is extremely time consuming because sparse graph-based operations are hard to be accelerated by hardware. Prior art explores trading of…

cs.IR2026

An Embarrassingly Simple Graph Heuristic Reveals Shortcut-Solvable Benchmarks for Sequential Recommendation

Haoyu Han, Li Ma, Hanbing Wang +9

Sequential recommendation has increasingly shifted toward generative recommenders that combine sequential patterns with semantic item information. Yet these methods are often evalu…

cs.IR2025

Learning to Comparison-Shop

Jie Tang, Daochen Zha, Xin Liu +4

In online marketplaces like Airbnb, users frequently engage in comparison shopping before making purchase decisions. Despite the prevalence of this behavior, a significant disconne…

cs.CL2025

Large Language Models for Disease Diagnosis: A Scoping Review

Shuang Zhou, Zidu Xu, Mian Zhang +14

Automatic disease diagnosis has become increasingly valuable in clinical practice. The advent of large language models (LLMs) has catalyzed a paradigm shift in artificial intellige…

cs.LG2021

Dirichlet Energy Constrained Learning for Deep Graph Neural Networks

Kaixiong Zhou, Xiao Huang, Daochen Zha +4

Graph neural networks (GNNs) integrate deep architectures and topological structure modeling in an effective way. However, the performance of existing GNNs would decrease significa…

cs.LG2019

Experience Replay Optimization

Daochen Zha, Kwei-Herng Lai, Kaixiong Zhou +1

Experience replay enables reinforcement learning agents to memorize and reuse past experiences, just as humans replay memories for the situation at hand. Contemporary off-policy al…

cs.CV2026

GraphVLM: Benchmarking Vision Language Models for Multimodal Graph Learning

Jiajin Liu, Dongzhe Fan, Chuanhao Ji +2

Vision-Language Models (VLMs) have demonstrated remarkable capabilities in aligning and understanding multimodal signals, yet their potential to reason over structured data, where…

cs.LG2020

Towards Deeper Graph Neural Networks with Differentiable Group Normalization

Kaixiong Zhou, Xiao Huang, Yuening Li +3

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

cs.LG2023

Pre-train and Search: Efficient Embedding Table Sharding with Pre-trained Neural Cost Models

Daochen Zha, Louis Feng, Liang Luo +8

Sharding a large machine learning model across multiple devices to balance the costs is important in distributed training. This is challenging because partitioning is NP-hard, and…

cs.LG2022

DreamShard: Generalizable Embedding Table Placement for Recommender Systems

Daochen Zha, Louis Feng, Qiaoyu Tan +6

We study embedding table placement for distributed recommender systems, which aims to partition and place the tables on multiple hardware devices (e.g., GPUs) to balance the comput…

cs.LG2020

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

Yuening Li, Zhengzhang Chen, Daochen Zha +4

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

cs.LG2020

Dual Policy Distillation

Kwei-Herng Lai, Daochen Zha, Yuening Li +1

Policy distillation, which transfers a teacher policy to a student policy has achieved great success in challenging tasks of deep reinforcement learning. This teacher-student frame…

cs.NI2017

CHAOS: an SDN-based Moving Target Defense System

Juan Wang, Feng Xiao, Jianwei Huang +3

The static nature of current cyber systems has made them easy to be attacked and compromised. By constantly changing a system, Moving Target Defense (MTD) has provided a promising…

cs.DB2025

TODS: An Automated Time Series Outlier Detection System

Kwei-Herng Lai, Daochen Zha, Guanchu Wang +8

We present TODS, an automated Time Series Outlier Detection System for research and industrial applications. TODS is a highly modular system that supports easy pipeline constructio…

cs.LG2023

SurCo: Learning Linear Surrogates For Combinatorial Nonlinear Optimization Problems

Aaron Ferber, Taoan Huang, Daochen Zha +4

Optimization problems with nonlinear cost functions and combinatorial constraints appear in many real-world applications but remain challenging to solve efficiently compared to the…

cs.LG2022

Towards Automated Imbalanced Learning with Deep Hierarchical Reinforcement Learning

Daochen Zha, Kwei-Herng Lai, Qiaoyu Tan +3

Imbalanced learning is a fundamental challenge in data mining, where there is a disproportionate ratio of training samples in each class. Over-sampling is an effective technique to…

cs.LG2020

PyODDS: An End-to-end Outlier Detection System with Automated Machine Learning

Yuening Li, Daochen Zha, Praveen Kumar Venugopal +2

Outlier detection is an important task for various data mining applications. Current outlier detection techniques are often manually designed for specific domains, requiring large…

cs.LG2024

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

Xiao-Yang Liu, Rongyi Zhu, Daochen Zha +4

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 scien…

cs.LG2023

OpenGSL: A Comprehensive Benchmark for Graph Structure Learning

Zhiyao Zhou, Sheng Zhou, Bochao Mao +7

Graph Neural Networks (GNNs) have emerged as the de facto standard for representation learning on graphs, owing to their ability to effectively integrate graph topology and node at…

cs.LG2022

AutoShard: Automated Embedding Table Sharding for Recommender Systems

Daochen Zha, Louis Feng, Bhargav Bhushanam +7

Embedding learning is an important technique in deep recommendation models to map categorical features to dense vectors. However, the embedding tables often demand an extremely lar…

cs.LG2023

Tackling Diverse Minorities in Imbalanced Classification

Kwei-Herng Lai, Daochen Zha, Huiyuan Chen +5

Imbalanced datasets are commonly observed in various real-world applications, presenting significant challenges in training classifiers. When working with large datasets, the imbal…

cs.LG2025

Graph-MLLM: Harnessing Multimodal Large Language Models for Multimodal Graph Learning

Jiajin Liu, Dongzhe Fan, Jiacheng Shen +3

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in representing and understanding diverse modalities. However, they typically focus on modality a…

cs.CE2024

Customized FinGPT Search Agents Using Foundation Models

Felix Tian, Ajay Byadgi, Daniel Kim +4

Current large language models (LLMs) have proven useful for analyzing financial data, but most existing models, such as BloombergGPT and FinGPT, lack customization for specific use…

cs.LG2023

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

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 informat…

cs.AI2023

Fairly Predicting Graft Failure in Liver Transplant for Organ Assigning

Sirui Ding, Ruixiang Tang, Daochen Zha +4

Liver transplant is an essential therapy performed for severe liver diseases. The fact of scarce liver resources makes the organ assigning crucial. Model for End-stage Liver Diseas…

cs.IR2017

Multi-label Dataless Text Classification with Topic Modeling

Daochen Zha, Chenliang Li

Manually labeling documents is tedious and expensive, but it is essential for training a traditional text classifier. In recent years, a few dataless text classification techniques…

cs.LG2023

Data-centric Artificial Intelligence: A Survey

Daochen Zha, Zaid Pervaiz Bhat, Kwei-Herng Lai +4

Artificial Intelligence (AI) is making a profound impact in almost every domain. A vital enabler of its great success is the availability of abundant and high-quality data for buil…

cs.LG2022

Modeling Techniques for Machine Learning Fairness: A Survey

Mingyang Wan, Daochen Zha, Ninghao Liu +1

Machine learning models are becoming pervasive in high-stakes applications. Despite their clear benefits in terms of performance, the models could show discrimination against minor…

cs.LG2026

LTSM-Bundle: A Toolbox and Benchmark on Large Language Models for Time Series Forecasting

Yu-Neng Chuang, Songchen Li, Jiayi Yuan +11

Time Series Forecasting (TSF) has long been a challenge in time series analysis. Inspired by the success of Large Language Models (LLMs), researchers are now developing Large Time…

cs.CV2022

AutoVideo: An Automated Video Action Recognition System

Daochen Zha, Zaid Pervaiz Bhat, Yi-Wei Chen +9

Action recognition is an important task for video understanding with broad applications. However, developing an effective action recognition solution often requires extensive engin…

cs.CE2025

FinLoRA: Benchmarking LoRA Methods for Fine-Tuning LLMs on Financial Datasets

Dannong Wang, Jaisal Patel, Daochen Zha +2

Low-rank adaptation (LoRA) methods show great potential for scaling pre-trained general-purpose Large Language Models (LLMs) to hundreds or thousands of use scenarios. However, the…

cs.AI2023

Data-centric AI: Perspectives and Challenges

Daochen Zha, Zaid Pervaiz Bhat, Kwei-Herng Lai +2

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…

cs.LG2023

Dynamic Datasets and Market Environments for Financial Reinforcement Learning

Xiao-Yang Liu, Ziyi Xia, Hongyang Yang +6

The financial market is a particularly challenging playground for deep reinforcement learning due to its unique feature of dynamic datasets. Building high-quality market environmen…

cs.LG2021

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

Daochen Zha, Wenye Ma, Lei Yuan +2

Exploration under sparse reward is a long-standing challenge of model-free reinforcement learning. The state-of-the-art methods address this challenge by introducing intrinsic rewa…

cs.LG2019

PyODDS: An End-to-End Outlier Detection System

Yuening Li, Daochen Zha, Na Zou +1

PyODDS is an end-to end Python system for outlier detection with database support. PyODDS provides outlier detection algorithms which meet the demands for users in different fields…

cs.LG2020

Policy-GNN: Aggregation Optimization for Graph Neural Networks

Kwei-Herng Lai, Daochen Zha, Kaixiong Zhou +1

Graph data are pervasive in many real-world applications. Recently, increasing attention has been paid on graph neural networks (GNNs), which aim to model the local graph structure…

cs.LG2023

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

Yicheng Wang, Xiaotian Han, Chia-Yuan Chang +3

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

cs.LG2021

Learning Disentangled Representations for Time Series

Yuening Li, Zhengzhang Chen, Daochen Zha +4

Time-series representation learning is a fundamental task for time-series analysis. While significant progress has been made to achieve accurate representations for downstream appl…

cs.LG2024

GraphFM: A Comprehensive Benchmark for Graph Foundation Model

Yuhao Xu, Xinqi Liu, Keyu Duan +4

Foundation Models (FMs) serve as a general class for the development of artificial intelligence systems, offering broad potential for generalization across a spectrum of downstream…

cs.LG2023

Towards Personalized Preprocessing Pipeline Search

Diego Martinez, Daochen Zha, Qiaoyu Tan +1

Feature preprocessing, which transforms raw input features into numerical representations, is a crucial step in automated machine learning (AutoML) systems. However, the existing s…

cs.IR2025

Beyond Pairwise Learning-To-Rank At Airbnb

Malay Haldar, Daochen Zha, Huiji Gao +2

There are three fundamental asks from a ranking algorithm: it should scale to handle a large number of items, sort items accurately by their utility, and impose a total order on th…

cs.LG2021

Simplifying Deep Reinforcement Learning via Self-Supervision

Daochen Zha, Kwei-Herng Lai, Kaixiong Zhou +1

Supervised regression to demonstrations has been demonstrated to be a stable way to train deep policy networks. We are motivated to study how we can take full advantage of supervis…

cs.CL2024

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

Junnan Dong, Qinggang Zhang, Chuang Zhou +3

Knowledge-based question answering (KBQA) is widely used in many scenarios that necessitate domain knowledge. Large language models (LLMs) bring opportunities to KBQA, while their…

cs.CL2024

KnowGPT: Knowledge Graph based Prompting for Large Language Models

Qinggang Zhang, Junnan Dong, Hao Chen +3

Large Language Models (LLMs) have demonstrated remarkable capabilities in many real-world applications. Nonetheless, LLMs are often criticized for their tendency to produce halluci…