papers

Publications (28)

cs.CL2022

Continuous Prompt Tuning Based Textual Entailment Model for E-commerce Entity Typing

Yibo Wang, Congying Xia, Guan Wang +1

The explosion of e-commerce has caused the need for processing and analysis of product titles, like entity typing in product titles. However, the rapid activity in e-commerce has l…

cs.LG2026

BTTackler: A Diagnosis-based Framework for Efficient Deep Learning Hyperparameter Optimization

Zhongyi Pei, Zhiyao Cen, Yipeng Huang +4

Hyperparameter optimization (HPO) is known to be costly in deep learning, especially when leveraging automated approaches. Most of the existing automated HPO methods are accuracy-b…

cs.AI2026

FORTIS: Benchmarking Over-Privilege in Agent Skills

Shawn Li, Chenxiao Yu, Han Wang +8

Large language model agents increasingly operate through an intermediate skill layer that mediates between user intent and concrete task execution. This layer is widely treated as…

cs.IR2025

Automating Personalization: Prompt Optimization for Recommendation Reranking

Chen Wang, Mingdai Yang, Zhiwei Liu +4

Modern recommender systems increasingly leverage large language models (LLMs) for reranking to improve personalization. However, existing approaches face two key limitations: (1) h…

cs.CL2021

Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning

Jianguo Zhang, Trung Bui, Seunghyun Yoon +6

In this work, we focus on a more challenging few-shot intent detection scenario where many intents are fine-grained and semantically similar. We present a simple yet effective few-…

cs.IR2026

Personalized Recommendation Tool Learning via Autonomous Language Agents

Mingdai Yang, Zhiwei Liu, Weizhi Zhang +3

Although large language models (LLMs) have recently gained traction in recommender systems due to their strong reasoning capabilities and extensive world knowledge, previous LLM-ba…

cs.LG2024

Motif-aware Riemannian Graph Neural Network with Generative-Contrastive Learning

Li Sun, Zhenhao Huang, Zixi Wang +3

Graphs are typical non-Euclidean data of complex structures. In recent years, Riemannian graph representation learning has emerged as an exciting alternative to Euclidean ones. How…

cs.LG2023

A Counterfactual Fair Model for Longitudinal Electronic Health Records via Deconfounder

Zheng Liu, Xiaohan Li, Philip Yu

The fairness issue of clinical data modeling, especially on Electronic Health Records (EHRs), is of utmost importance due to EHR's complex latent structure and potential selection…

cs.CV2020

Multi-label Zero-shot Classification by Learning to Transfer from External Knowledge

He Huang, Yuanwei Chen, Wei Tang +4

Multi-label zero-shot classification aims to predict multiple unseen class labels for an input image. It is more challenging than its single-label counterpart. On one hand, the unc…

cs.CL2020

Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT

Lichao Sun, Kazuma Hashimoto, Wenpeng Yin +4

There is an increasing amount of literature that claims the brittleness of deep neural networks in dealing with adversarial examples that are created maliciously. It is unclear, ho…

cs.SI2021

Click-Through Rate Prediction with Multi-Modal Hypergraphs

Li He, Hongxu Chen, Dingxian Wang +3

Advertising is critical to many online e-commerce platforms such as e-Bay and Amazon. One of the important signals that these platforms rely upon is the click-through rate (CTR) pr…

cs.LG2021

Learn to Forget: Machine Unlearning via Neuron Masking

Yang Liu, Zhuo Ma, Ximeng Liu +5

Nowadays, machine learning models, especially neural networks, become prevalent in many real-world applications.These models are trained based on a one-way trip from user data: as…

cs.CL2020

CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection

Congying Xia, Chenwei Zhang, Hoang Nguyen +2

In this paper, we formulate a more realistic and difficult problem setup for the intent detection task in natural language understanding, namely Generalized Few-Shot Intent Detecti…

cs.CL2020

MZET: Memory Augmented Zero-Shot Fine-grained Named Entity Typing

Tao Zhang, Congying Xia, Chun-Ta Lu +1

Named entity typing (NET) is a classification task of assigning an entity mention in the context with given semantic types. However, with the growing size and granularity of the en…

cs.SI2015

CENI: a Hybrid Framework for Efficiently Inferring Information Networks

Qingbo Hu, Sihong Xie, Shuyang Lin +2

Nowadays, the message diffusion links among users or websites drive the development of countless innovative applications. However, in reality, it is easier for us to observe the ti…

cs.LG2026

Uncertainty Quantification on Graph Learning: A Survey

Chao Chen, Chenghua Guo, Rui Xu +6

Graphical models have demonstrated their exceptional capabilities across numerous applications. However, their performance, confidence, and trustworthiness are often limited by the…

cs.CL2025

ScaleFormer: Span Representation Cumulation for Long-Context Transformer

Jiangshu Du, Wenpeng Yin, Philip Yu

The quadratic complexity of standard self-attention severely limits the application of Transformer-based models to long-context tasks. While efficient Transformer variants exist, t…

cs.CL2020

Composed Variational Natural Language Generation for Few-shot Intents

Congying Xia, Caiming Xiong, Philip Yu +1

In this paper, we focus on generating training examples for few-shot intents in the realistic imbalanced scenario. To build connections between existing many-shot intents and few-s…

cs.IR2025

Solving the Content Gap in Roblox Game Recommendations: LLM-Based Profile Generation and Reranking

Chen Wang, Xiaokai Wei, Yexi Jiang +7

With the vast and dynamic user-generated content on Roblox, creating effective game recommendations requires a deep understanding of game content. Traditional recommendation models…

cs.LG2024

Beyond the Known: Novel Class Discovery for Open-world Graph Learning

Yucheng Jin, Yun Xiong, Juncheng Fang +5

Node classification on graphs is of great importance in many applications. Due to the limited labeling capability and evolution in real-world open scenarios, novel classes can emer…

cs.CL2021

Pseudo Siamese Network for Few-shot Intent Generation

Congying Xia, Caiming Xiong, Philip Yu

Few-shot intent detection is a challenging task due to the scare annotation problem. In this paper, we propose a Pseudo Siamese Network (PSN) to generate labeled data for few-shot…

cs.CL2021

Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System

Congying Xia, Wenpeng Yin, Yihao Feng +1

Text classification is usually studied by labeling natural language texts with relevant categories from a predefined set. In the real world, new classes might keep challenging the…

cs.LG2026

A Deployment Audit of Release-Side Risk in Conformal Triage under Prevalence Shift

Chengze Li, Xiao Liu, Hanrong Zhang +7

Conformal triage converts predictive scores into deployment actions that either release a case, flag it for urgent attention, or defer it to human review. Under an observed change…

cs.LG2025

RiemannGFM: Learning a Graph Foundation Model from Riemannian Geometry

Li Sun, Zhenhao Huang, Suyang Zhou +3

The foundation model has heralded a new era in artificial intelligence, pretraining a single model to offer cross-domain transferability on different datasets. Graph neural network…

cs.IR2022

Mitigating Frequency Bias in Next-Basket Recommendation via Deconfounders

Xiaohan Li, Zheng Liu, Luyi Ma +4

Recent studies on Next-basket Recommendation (NBR) have achieved much progress by leveraging Personalized Item Frequency (PIF) as one of the main features, which measures the frequ…

cs.LG2022

Mitigating Health Disparities in EHR via Deconfounder

Zheng Liu, Xiaohan Li, Philip Yu

Health disparities, or inequalities between different patient demographics, are becoming crucial in medical decision-making, especially in Electronic Health Record (EHR) predictive…

cs.AI2026

Heterophily-Agnostic Hypergraph Neural Networks with Riemannian Local Exchanger

Li Sun, Ming Zhang, Wenxin Jin +5

Hypergraphs are the natural description of higher-order interactions among objects, widely applied in social network analysis, cross-modal retrieval, etc. Hypergraph Neural Network…

cs.CL2019

Multi-Grained Named Entity Recognition

Congying Xia, Chenwei Zhang, Tao Yang +6

This paper presents a novel framework, MGNER, for Multi-Grained Named Entity Recognition where multiple entities or entity mentions in a sentence could be non-overlapping or totall…