Search Results for author: Pan Li

Found 103 papers, 49 papers with code

Stochastic Gradient Langevin Unlearning

no code implementations25 Mar 2024 Eli Chien, Haoyu Wang, Ziang Chen, Pan Li

Our approach achieves a similar utility under the same privacy constraint while using $2\%$ and $10\%$ of the gradient computations compared with the state-of-the-art gradient-based approximate unlearning methods for mini-batch and full-batch settings, respectively.

Machine Unlearning

Pairwise Alignment Improves Graph Domain Adaptation

1 code implementation2 Mar 2024 Shikun Liu, Deyu Zou, Han Zhao, Pan Li

Graph-based methods, pivotal for label inference over interconnected objects in many real-world applications, often encounter generalization challenges, if the graph used for model training differs significantly from the graph used for testing.

Domain Adaptation Node Classification

Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics

1 code implementation19 Feb 2024 Siqi Miao, Zhiyuan Lu, Mia Liu, Javier Duarte, Pan Li

Our findings highlight the superiority of using locality-sensitive hashing (LSH), especially OR \& AND-construction LSH, in kernel approximation for large-scale point cloud data with local inductive bias.

Inductive Bias

No Need to Look Back: An Efficient and Scalable Approach for Temporal Network Representation Learning

1 code implementation3 Feb 2024 Yuhong Luo, Pan Li

This strategy is implemented using a GPU-executable size-constrained hash table for each node, recording down-sampled recent interactions, which enables rapid response to queries with minimal inference latency.

Graph Representation Learning Link Prediction +1

MEA-Defender: A Robust Watermark against Model Extraction Attack

1 code implementation26 Jan 2024 Peizhuo Lv, Hualong Ma, Kai Chen, Jiachen Zhou, Shengzhi Zhang, Ruigang Liang, Shenchen Zhu, Pan Li, Yingjun Zhang

To protect the Intellectual Property (IP) of the original owners over such DNN models, backdoor-based watermarks have been extensively studied.

Model extraction Self-Supervised Learning

Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning

no code implementations18 Jan 2024 Eli Chien, Haoyu Wang, Ziang Chen, Pan Li

We propose Langevin unlearning, an unlearning framework based on noisy gradient descent with privacy guarantees for approximate unlearning problems.

Machine Unlearning

xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein

no code implementations11 Jan 2024 Bo Chen, Xingyi Cheng, Pan Li, Yangli-ao Geng, Jing Gong, Shen Li, Zhilei Bei, Xu Tan, Boyan Wang, Xin Zeng, Chiming Liu, Aohan Zeng, Yuxiao Dong, Jie Tang, Le Song

We propose a unified protein language model, xTrimoPGLM, to address these two types of tasks simultaneously through an innovative pre-training framework.

Protein Language Model

Learning Scalable Structural Representations for Link Prediction with Bloom Signatures

no code implementations28 Dec 2023 Tianyi Zhang, Haoteng Yin, Rongzhe Wei, Pan Li, Anshumali Shrivastava

We further show that any type of neighborhood overlap-based heuristic can be estimated by a neural network that takes Bloom signatures as input.

Link Prediction

KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph

no code implementations26 Dec 2023 Tiezheng Guo, Qingwen Yang, Chen Wang, Yanyi Liu, Pan Li, Jiawei Tang, Dapeng Li, Yingyou Wen

Large language model (LLM) has achieved outstanding performance on various downstream tasks with its powerful natural language understanding and zero-shot capability, but LLM still suffers from knowledge limitation.

Hallucination Language Modelling +3

High Pileup Particle Tracking with Object Condensation

1 code implementation6 Dec 2023 Kilian Lieret, Gage DeZoort, Devdoot Chatterjee, Jian Park, Siqi Miao, Pan Li

Recent work has demonstrated that graph neural networks (GNNs) can match the performance of traditional algorithms for charged particle tracking while improving scalability to meet the computing challenges posed by the HL-LHC.

Edge Classification Object

On the Inherent Privacy Properties of Discrete Denoising Diffusion Models

no code implementations24 Oct 2023 Rongzhe Wei, Eleonora Kreačić, Haoyu Wang, Haoteng Yin, Eli Chien, Vamsi K. Potluru, Pan Li

Focusing on per-instance differential privacy (pDP), our framework elucidates the potential privacy leakage for each data point in a given training dataset, offering insights into data preprocessing to reduce privacy risks of the synthetic dataset generation via DDMs.

Denoising Privacy Preserving

ABKD: Graph Neural Network Compression with Attention-Based Knowledge Distillation

no code implementations24 Oct 2023 Anshul Ahluwalia, Rohit Das, Payman Behnam, Alind Khare, Pan Li, Alexey Tumanov

To address this shortcoming, we propose a novel KD approach to GNN compression that we call Attention-Based Knowledge Distillation (ABKD).

Drug Discovery Fake News Detection +3

GraphMaker: Can Diffusion Models Generate Large Attributed Graphs?

1 code implementation20 Oct 2023 Mufei Li, Eleonora Kreačić, Vamsi K. Potluru, Pan Li

However, these models face challenges in generating large attributed graphs due to the complex attribute-structure correlations and the large size of these graphs.

Attribute Graph Generation

DIG-MILP: a Deep Instance Generator for Mixed-Integer Linear Programming with Feasibility Guarantee

1 code implementation20 Oct 2023 Haoyu Wang, Jialin Liu, Xiaohan Chen, Xinshang Wang, Pan Li, Wotao Yin

Mixed-integer linear programming (MILP) stands as a notable NP-hard problem pivotal to numerous crucial industrial applications.

Data Augmentation

GDL-DS: A Benchmark for Geometric Deep Learning under Distribution Shifts

1 code implementation12 Oct 2023 Deyu Zou, Shikun Liu, Siqi Miao, Victor Fung, Shiyu Chang, Pan Li

Geometric deep learning (GDL) has gained significant attention in various scientific fields, chiefly for its proficiency in modeling data with intricate geometric structures.

Towards Poisoning Fair Representations

no code implementations28 Sep 2023 Tianci Liu, Haoyu Wang, Feijie Wu, Hengtong Zhang, Pan Li, Lu Su, Jing Gao

Fair machine learning seeks to mitigate model prediction bias against certain demographic subgroups such as elder and female.

Bilevel Optimization Data Poisoning +2

Optimal Resource Allocation for U-Shaped Parallel Split Learning

no code implementations17 Aug 2023 Song Lyu, Zheng Lin, Guanqiao Qu, Xianhao Chen, Xiaoxia Huang, Pan Li

In this paper, we develop a novel parallel U-shaped split learning and devise the optimal resource optimization scheme to improve the performance of edge networks.

Polynomial Width is Sufficient for Set Representation with High-dimensional Features

no code implementations8 Jul 2023 Peihao Wang, Shenghao Yang, Shu Li, Zhangyang Wang, Pan Li

To investigate the minimal value of $L$ that achieves sufficient expressive power, we present two set-element embedding layers: (a) linear + power activation (LP) and (b) linear + exponential activations (LE).

Inductive Bias

Structural Re-weighting Improves Graph Domain Adaptation

1 code implementation5 Jun 2023 Shikun Liu, Tianchun Li, Yongbin Feng, Nhan Tran, Han Zhao, Qiu Qiang, Pan Li

This work examines different impacts of distribution shifts caused by either graph structure or node attributes and identifies a new type of shift, named conditional structure shift (CSS), which current GDA approaches are provably sub-optimal to deal with.

Attribute Domain Adaptation

Prompt Tuning Large Language Models on Personalized Aspect Extraction for Recommendations

no code implementations2 Jun 2023 Pan Li, Yuyan Wang, Ed H. Chi, Minmin Chen

For the aspect-based recommendation component, the extracted aspects are concatenated with the usual user and item features used by the recommendation model.

Aspect Extraction

Hierarchical Reinforcement Learning for Modeling User Novelty-Seeking Intent in Recommender Systems

no code implementations2 Jun 2023 Pan Li, Yuyan Wang, Ed H. Chi, Minmin Chen

Hierarchical structure, on the other hand, exists in a user's novelty-seeking intent, which is manifested as a static and intrinsic user preference for seeking novelty along with a dynamic session-based propensity.

Hierarchical Reinforcement Learning Recommendation Systems +1

GAD-NR: Graph Anomaly Detection via Neighborhood Reconstruction

1 code implementation2 Jun 2023 Amit Roy, Juan Shu, Jia Li, Carl Yang, Olivier Elshocht, Jeroen Smeets, Pan Li

Graph Anomaly Detection (GAD) is a technique used to identify abnormal nodes within graphs, finding applications in network security, fraud detection, social media spam detection, and various other domains.

Fraud Detection Graph Anomaly Detection +1

Improving Graph Neural Networks on Multi-node Tasks with Labeling Tricks

no code implementations20 Apr 2023 Xiyuan Wang, Pan Li, Muhan Zhang

When we want to learn a node-set representation involving multiple nodes, a common practice in previous works is to directly aggregate the single-node representations obtained by a GNN.

Hyperedge Prediction Representation Learning

SUREL+: Moving from Walks to Sets for Scalable Subgraph-based Graph Representation Learning

1 code implementation6 Mar 2023 Haoteng Yin, Muhan Zhang, Jianguo Wang, Pan Li

Subgraph-based graph representation learning (SGRL) has recently emerged as a powerful tool in many prediction tasks on graphs due to its advantages in model expressiveness and generalization ability.

Graph Representation Learning

Unsupervised Learning for Combinatorial Optimization Needs Meta-Learning

1 code implementation8 Jan 2023 Haoyu Wang, Pan Li

With this observation, we propose a new objective of unsupervised learning for CO where the goal of learning is to search for good initialization for future problem instances rather than give direct solutions.

Combinatorial Optimization Meta-Learning

Extensible and Efficient Proxy for Neural Architecture Search

no code implementations ICCV 2023 Yuhong Li, Jiajie Li, Cong Hao, Pan Li, JinJun Xiong, Deming Chen

We further propose a Discrete Proxy Search (DPS) method to find the optimized training settings for Eproxy with only a handful of benchmarked architectures on the target tasks.

Neural Architecture Search

Graph Federated Learning with Hidden Representation Sharing

no code implementations23 Dec 2022 Shuang Wu, Mingxuan Zhang, Yuantong Li, Carl Yang, Pan Li

On the other hand, due to the increasing demands for the protection of clients' data privacy, Federated Learning (FL) has been widely adopted: FL requires models to be trained in a multi-client system and restricts sharing of raw data among clients.

Federated Learning

Interpretable Geometric Deep Learning via Learnable Randomness Injection

1 code implementation30 Oct 2022 Siqi Miao, Yunan Luo, Mia Liu, Pan Li

LRI-induced models, once trained, can detect the points in the point cloud data that carry information indicative of the prediction label.

Federated Graph Representation Learning using Self-Supervision

no code implementations27 Oct 2022 Susheel Suresh, Danny Godbout, Arko Mukherjee, Mayank Shrivastava, Jennifer Neville, Pan Li

1. 7% gains compared to individual client specific self-supervised training and (2) we construct and introduce a new cross-silo dataset called Amazon Co-purchase Networks that have both the characteristics of the motivated problem setting.

Federated Learning Graph Representation Learning

Extensible Proxy for Efficient NAS

1 code implementation17 Oct 2022 Yuhong Li, Jiajie Li, Cong Han, Pan Li, JinJun Xiong, Deming Chen

(2) Efficient proxies are not extensible to multi-modality downstream tasks.

Neural Architecture Search

A Novel Membership Inference Attack against Dynamic Neural Networks by Utilizing Policy Networks Information

no code implementations17 Oct 2022 Pan Li, Peizhuo Lv, Shenchen Zhu, Ruigang Liang, Kai Chen

Although traditional static DNNs are vulnerable to the membership inference attack (MIA) , which aims to infer whether a particular point was used to train the model, little is known about how such an attack performs on the dynamic NNs.

Computational Efficiency Image Classification +2

Spatio-temporal Tendency Reasoning for Human Body Pose and Shape Estimation from Videos

no code implementations7 Oct 2022 Boyang Zhang, Suping Wu, Hu Cao, Kehua Ma, Pan Li, Lei Lin

Different from them, our STR aims to learn accurate and natural motion sequences in an unconstrained environment through temporal and spatial tendency and to fully excavate the spatio-temporal features of existing video data.

3D Human Pose Estimation Temporal Sequences

SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning

1 code implementation8 Sep 2022 Peizhuo Lv, Pan Li, Shenchen Zhu, Shengzhi Zhang, Kai Chen, Ruigang Liang, Chang Yue, Fan Xiang, Yuling Cai, Hualong Ma, Yingjun Zhang, Guozhu Meng

Recent years have witnessed tremendous success in Self-Supervised Learning (SSL), which has been widely utilized to facilitate various downstream tasks in Computer Vision (CV) and Natural Language Processing (NLP) domains.

Self-Supervised Learning

Neighborhood-aware Scalable Temporal Network Representation Learning

2 code implementations2 Sep 2022 Yuhong Luo, Pan Li

Such a dictionary representation records a downsampled set of the neighboring nodes as keys, and allows fast construction of structural features for a joint neighborhood of multiple nodes.

Inductive Link Prediction Representation Learning

Understanding Non-linearity in Graph Neural Networks from the Bayesian-Inference Perspective

1 code implementation22 Jul 2022 Rongzhe Wei, Haoteng Yin, Junteng Jia, Austin R. Benson, Pan Li

Graph neural networks (GNNs) have shown superiority in many prediction tasks over graphs due to their impressive capability of capturing nonlinear relations in graph-structured data.

Bayesian Inference Node Classification

Equivariant Hypergraph Diffusion Neural Operators

1 code implementation14 Jul 2022 Peihao Wang, Shenghao Yang, Yunyu Liu, Zhangyang Wang, Pan Li

Hypergraph neural networks (HNNs) using neural networks to encode hypergraphs provide a promising way to model higher-order relations in data and further solve relevant prediction tasks built upon such higher-order relations.

Computational Efficiency Node Classification

Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxation

1 code implementation13 Jul 2022 Haoyu Wang, Nan Wu, Hang Yang, Cong Hao, Pan Li

Using machine learning to solve combinatorial optimization (CO) problems is challenging, especially when the data is unlabeled.

Combinatorial Optimization

Two-Dimensional Weisfeiler-Lehman Graph Neural Networks for Link Prediction

1 code implementation20 Jun 2022 Yang Hu, Xiyuan Wang, Zhouchen Lin, Pan Li, Muhan Zhang

As pointed out by previous works, this two-step procedure results in low discriminating power, as 1-WL-GNNs by nature learn node-level representations instead of link-level.

Link Prediction Vocal Bursts Valence Prediction

A Framework of Meta Functional Learning for Regularising Knowledge Transfer

no code implementations28 Mar 2022 Pan Li, Yanwei Fu, Shaogang Gong

The MFL computes meta-knowledge on functional regularisation generalisable to different learning tasks by which functional training on limited labelled data promotes more discriminative functions to be learned.

cross-domain few-shot learning Transfer Learning

Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks

1 code implementation ICLR 2022 Haorui Wang, Haoteng Yin, Muhan Zhang, Pan Li

Graph neural networks (GNN) have shown great advantages in many graph-based learning tasks but often fail to predict accurately for a task-based on sets of nodes such as link/motif prediction and so on.

Link Prediction

Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning

3 code implementations28 Feb 2022 Haoteng Yin, Muhan Zhang, Yanbang Wang, Jianguo Wang, Pan Li

Subgraph-based graph representation learning (SGRL) has been recently proposed to deal with some fundamental challenges encountered by canonical graph neural networks (GNNs), and has demonstrated advantages in many important data science applications such as link, relation and motif prediction.

Graph Representation Learning

Graph Auto-Encoder Via Neighborhood Wasserstein Reconstruction

1 code implementation ICLR 2022 Mingyue Tang, Carl Yang, Pan Li

Graph neural networks (GNNs) have drawn significant research attention recently, mostly under the setting of semi-supervised learning.

Graph Mining Graph Reconstruction

Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism

2 code implementations31 Jan 2022 Siqi Miao, Miaoyuan Liu, Pan Li

However, those post-hoc methods often fail to provide stable interpretation and may extract features that are spuriously correlated with the task.

Graph Learning

Applications and Techniques for Fast Machine Learning in Science

no code implementations25 Oct 2021 Allison McCarn Deiana, Nhan Tran, Joshua Agar, Michaela Blott, Giuseppe Di Guglielmo, Javier Duarte, Philip Harris, Scott Hauck, Mia Liu, Mark S. Neubauer, Jennifer Ngadiuba, Seda Ogrenci-Memik, Maurizio Pierini, Thea Aarrestad, Steffen Bahr, Jurgen Becker, Anne-Sophie Berthold, Richard J. Bonventre, Tomas E. Muller Bravo, Markus Diefenthaler, Zhen Dong, Nick Fritzsche, Amir Gholami, Ekaterina Govorkova, Kyle J Hazelwood, Christian Herwig, Babar Khan, Sehoon Kim, Thomas Klijnsma, Yaling Liu, Kin Ho Lo, Tri Nguyen, Gianantonio Pezzullo, Seyedramin Rasoulinezhad, Ryan A. Rivera, Kate Scholberg, Justin Selig, Sougata Sen, Dmitri Strukov, William Tang, Savannah Thais, Kai Lukas Unger, Ricardo Vilalta, Belinavon Krosigk, Thomas K. Warburton, Maria Acosta Flechas, Anthony Aportela, Thomas Calvet, Leonardo Cristella, Daniel Diaz, Caterina Doglioni, Maria Domenica Galati, Elham E Khoda, Farah Fahim, Davide Giri, Benjamin Hawks, Duc Hoang, Burt Holzman, Shih-Chieh Hsu, Sergo Jindariani, Iris Johnson, Raghav Kansal, Ryan Kastner, Erik Katsavounidis, Jeffrey Krupa, Pan Li, Sandeep Madireddy, Ethan Marx, Patrick McCormack, Andres Meza, Jovan Mitrevski, Mohammed Attia Mohammed, Farouk Mokhtar, Eric Moreno, Srishti Nagu, Rohin Narayan, Noah Palladino, Zhiqiang Que, Sang Eon Park, Subramanian Ramamoorthy, Dylan Rankin, Simon Rothman, ASHISH SHARMA, Sioni Summers, Pietro Vischia, Jean-Roch Vlimant, Olivia Weng

In this community review report, we discuss applications and techniques for fast machine learning (ML) in science -- the concept of integrating power ML methods into the real-time experimental data processing loop to accelerate scientific discovery.

BIG-bench Machine Learning

FEATURE-AUGMENTED HYPERGRAPH NEURAL NETWORKS

no code implementations29 Sep 2021 Xueqi Ma, Pan Li, Qiong Cao, James Bailey, Yue Gao

In FAHGNN, we explore the influence of node features for the expressive power of GNNs and augment features by introducing common features and personal features to model information.

Node Classification Representation Learning

Semi-supervised Graph Neural Network for Particle-level Noise Removal

no code implementations NeurIPS Workshop AI4Scien 2021 Tianchun Li, Shikun Liu, Yongbin Feng, Nhan Tran, Miaoyuan Liu, Pan Li

The graph neural network is trained on charged particles with well-known labels, which can be obtained from simulation truth information or measurements from data, and inferred on neutral particles of which such labeling is missing.

Program-to-Circuit: Exploiting GNNs for Program Representation and Circuit Translation

no code implementations13 Sep 2021 Nan Wu, Huake He, Yuan Xie, Pan Li, Cong Hao

Pioneering in this direction, we expect more GNN endeavors to revolutionize this high-demand Program-to-Circuit problem and to enrich the expressiveness of GNNs on programs.

Transfer Learning Translation

A Web Scale Entity Extraction System

no code implementations Findings (EMNLP) 2021 Xuanting Cai, Quanbin Ma, Pan Li, Jianyu Liu, Qi Zeng, Zhengkan Yang, Pushkar Tripathi

Understanding the semantic meaning of content on the web through the lens of entities and concepts has many practical advantages.

Generic Neural Architecture Search via Regression

2 code implementations NeurIPS 2021 Yuhong Li, Cong Hao, Pan Li, JinJun Xiong, Deming Chen

Such a self-supervised regression task can effectively evaluate the intrinsic power of an architecture to capture and transform the input signal patterns, and allow more sufficient usage of training samples.

 Ranked #1 on Neural Architecture Search on NAS-Bench-101 (Spearman Correlation metric)

Image Classification Neural Architecture Search +1

On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs

2 code implementations3 Jul 2021 Hejie Cui, Zijie Lu, Pan Li, Carl Yang

Graph neural networks (GNNs) have been widely used in various graph-related problems such as node classification and graph classification, where superior performance is mainly established when natural node features are available.

Graph Classification Node Classification

Neural Predicting Higher-order Patterns in Temporal Networks

2 code implementations10 Jun 2021 Yunyu Liu, Jianzhu Ma, Pan Li

HIT extracts the structural representation of a node triplet of interest on the temporal hypergraph and uses it to tell what type of, when, and why the interaction expansion could happen in this triplet.

Adversarial Graph Augmentation to Improve Graph Contrastive Learning

1 code implementation NeurIPS 2021 Susheel Suresh, Pan Li, Cong Hao, Jennifer Neville

Self-supervised learning of graph neural networks (GNN) is in great need because of the widespread label scarcity issue in real-world graph/network data.

Contrastive Learning Self-Supervised Learning

Principled Hyperedge Prediction with Structural Spectral Features and Neural Networks

no code implementations8 Jun 2021 Changlin Wan, Muhan Zhang, Wei Hao, Sha Cao, Pan Li, Chi Zhang

SNALS captures the joint interactions of a hyperedge by its local environment, which is retrieved by collecting the spectrum information of their connections.

Hyperedge Prediction

Dual Attentive Sequential Learning for Cross-Domain Click-Through Rate Prediction

1 code implementation5 Jun 2021 Pan Li, Zhichao Jiang, Maofei Que, Yao Hu, Alexander Tuzhilin

While several cross domain sequential recommendation models have been proposed to leverage information from a source domain to improve CTR predictions in a target domain, they did not take into account bidirectional latent relations of user preferences across source-target domain pairs.

Click-Through Rate Prediction Sequential Recommendation

PURS: Personalized Unexpected Recommender System for Improving User Satisfaction

1 code implementation5 Jun 2021 Pan Li, Maofei Que, Zhichao Jiang, Yao Hu, Alexander Tuzhilin

Classical recommender system methods typically face the filter bubble problem when users only receive recommendations of their familiar items, making them bored and dissatisfied.

Recommendation Systems

Dual Metric Learning for Effective and Efficient Cross-Domain Recommendations

1 code implementation17 Apr 2021 Pan Li, Alexander Tuzhilin

Furthermore, we combine the dual learning method with the metric learning approach, which allows us to significantly reduce the required common user overlap across the two domains and leads to even better cross-domain recommendation performance.

Metric Learning Recommendation Systems

HufuNet: Embedding the Left Piece as Watermark and Keeping the Right Piece for Ownership Verification in Deep Neural Networks

no code implementations25 Mar 2021 Peizhuo Lv, Pan Li, Shengzhi Zhang, Kai Chen, Ruigang Liang, Yue Zhao, Yingjiu Li

Most existing solutions embed backdoors in DNN model training such that DNN ownership can be verified by triggering distinguishable model behaviors with a set of secret inputs.

The Curse of Correlations for Robust Fingerprinting of Relational Databases

no code implementations11 Mar 2021 Tianxi Ji, Emre Yilmaz, Erman Ayday, Pan Li

Database fingerprinting have been widely adopted to prevent unauthorized sharing of data and identify the source of data leakages.

Cryptography and Security Databases

Local Hyper-Flow Diffusion

1 code implementation NeurIPS 2021 Kimon Fountoulakis, Pan Li, Shenghao Yang

Recently, hypergraphs have attracted a lot of attention due to their ability to capture complex relations among entities.

Clustering Community Detection +1

Handling many conversions per click in modeling delayed feedback

no code implementations6 Jan 2021 Ashwinkumar Badanidiyuru, Andrew Evdokimov, Vinodh Krishnan, Pan Li, Wynn Vonnegut, Jayden Wang

Predicting the expected value or number of post-click conversions (purchases or other events) is a key task in performance-based digital advertising.

A Simple Feature Augmentation for Domain Generalization

no code implementations ICCV 2021 Pan Li, Da Li, Wei Li, Shaogang Gong, Yanwei Fu, Timothy M. Hospedales

The topical domain generalization (DG) problem asks trained models to perform well on an unseen target domain with different data statistics from the source training domains.

Data Augmentation Domain Generalization

Striking a Balance Between Stability and Plasticity for Class-Incremental Learning

no code implementations ICCV 2021 Guile Wu, Shaogang Gong, Pan Li

With the reformulated baseline, we present two new approaches to CIL by learning class-independent knowledge and multi-perspective knowledge, respectively.

Class Incremental Learning Incremental Learning

F-FADE: Frequency Factorization for Anomaly Detection in Edge Streams

1 code implementation9 Nov 2020 Yen-Yu Chang, Pan Li, Rok Sosic, M. H. Afifi, Marco Schweighauser, Jure Leskovec

Edge streams are commonly used to capture interactions in dynamic networks, such as email, social, or computer networks.

Anomaly Detection Anomaly Detection in Edge Streams

Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning

2 code implementations NeurIPS 2021 Muhan Zhang, Pan Li, Yinglong Xia, Kai Wang, Long Jin

In this paper, we provide a theory of using graph neural networks (GNNs) for multi-node representation learning (where we are interested in learning a representation for a set of more than one node, such as link).

General Classification Graph Classification +4

Graph Information Bottleneck

1 code implementation NeurIPS 2020 Tailin Wu, Hongyu Ren, Pan Li, Jure Leskovec

We design two sampling algorithms for structural regularization and instantiate the GIB principle with two new models: GIB-Cat and GIB-Bern, and demonstrate the benefits by evaluating the resilience to adversarial attacks.

Representation Learning

MSTREAM: Fast Anomaly Detection in Multi-Aspect Streams

1 code implementation17 Sep 2020 Siddharth Bhatia, Arjit Jain, Pan Li, Ritesh Kumar, Bryan Hooi

Given a stream of entries in a multi-aspect data setting i. e., entries having multiple dimensions, how can we detect anomalous activities in an unsupervised manner?

Group Anomaly Detection Intrusion Detection

Latent Unexpected Recommendations

no code implementations27 Jul 2020 Pan Li, Alexander Tuzhilin

Unexpected recommender system constitutes an important tool to tackle the problem of filter bubbles and user boredom, which aims at providing unexpected and satisfying recommendations to target users at the same time.

Recommendation Systems

Adaptive Universal Generalized PageRank Graph Neural Network

1 code implementation ICLR 2021 Eli Chien, Jianhao Peng, Pan Li, Olgica Milenkovic

We address these issues by introducing a new Generalized PageRank (GPR) GNN architecture that adaptively learns the GPR weights so as to jointly optimize node feature and topological information extraction, regardless of the extent to which the node labels are homophilic or heterophilic.

GPR Node Classification on Non-Homophilic (Heterophilic) Graphs +1

Landing Probabilities of Random Walks for Seed-Set Expansion in Hypergraphs

no code implementations20 Oct 2019 Eli Chien, Pan Li, Olgica Milenkovic

We describe the first known mean-field study of landing probabilities for random walks on hypergraphs.

DDTCDR: Deep Dual Transfer Cross Domain Recommendation

no code implementations11 Oct 2019 Pan Li, Alexander Tuzhilin

Cross domain recommender systems have been increasingly valuable for helping consumers identify the most satisfying items from different categories.

Recommendation Systems Transfer Learning

Towards Controllable and Personalized Review Generation

no code implementations IJCNLP 2019 Pan Li, Alexander Tuzhilin

In this paper, we propose a novel model RevGAN that automatically generates controllable and personalized user reviews based on the arbitrarily given sentimental and stylistic information.

Review Generation Sentence

Meta-Graph Based HIN Spectral Embedding: Methods, Analyses, and Insights

no code implementations29 Sep 2019 Carl Yang, Yichen Feng, Pan Li, Yu Shi, Jiawei Han

In this work, we propose to study the utility of different meta-graphs, as well as how to simultaneously leverage multiple meta-graphs for HIN embedding in an unsupervised manner.

Subspace Determination through Local Intrinsic Dimensional Decomposition: Theory and Experimentation

no code implementations15 Jul 2019 Ruben Becker, Imane Hafnaoui, Michael E. Houle, Pan Li, Arthur Zimek

For each point, the recently-proposed Local Intrinsic Dimension (LID) model is used in identifying the axis directions along which features have the greatest local discriminability, or equivalently, the fewest number of components of LID that capture the local complexity of the data.

Clustering

Latent Multi-Criteria Ratings for Recommendations

no code implementations26 Jun 2019 Pan Li, Alexander Tuzhilin

Multi-criteria recommender systems have been increasingly valuable for helping consumers identify the most relevant items based on different dimensions of user experiences.

Recommendation Systems

Latent Unexpected and Useful Recommendation

1 code implementation4 May 2019 Pan Li, Alexander Tuzhilin

Providing unexpected recommendations is an important task for recommender systems.

Recommendation Systems

A tractable ellipsoidal approximation for voltage regulation problems

no code implementations9 Mar 2019 Pan Li, Baihong Jin, Ruoxuan Xiong, Dai Wang, Alberto Sangiovanni-Vincentelli, Baosen Zhang

We present a machine learning approach to the solution of chance constrained optimizations in the context of voltage regulation problems in power system operation.

BIG-bench Machine Learning

Quadratic Decomposable Submodular Function Minimization: Theory and Practice (Computation and Analysis of PageRank over Hypergraphs)

no code implementations26 Feb 2019 Pan Li, Niao He, Olgica Milenkovic

We introduce a new convex optimization problem, termed quadratic decomposable submodular function minimization (QDSFM), which allows to model a number of learning tasks on graphs and hypergraphs.

hypergraph partitioning

$HS^2$: Active Learning over Hypergraphs

no code implementations25 Nov 2018 I Chien, Huozhi Zhou, Pan Li

We propose a hypergraph-based active learning scheme which we term $HS^2$, $HS^2$ generalizes the previously reported algorithm $S^2$ originally proposed for graph-based active learning with pointwise queries [Dasarathy et al., COLT 2015].

Active Learning

Motif and Hypergraph Correlation Clustering

no code implementations5 Nov 2018 Pan Li, Gregory J. Puleo, Olgica Milenkovic

Our contributions are as follows: We first introduce several variants of motif correlation clustering and then show that these clustering problems are NP-hard.

Clustering

Person-Job Fit: Adapting the Right Talent for the Right Job with Joint Representation Learning

no code implementations8 Oct 2018 Chen Zhu, HengShu Zhu, Hui Xiong, Chao Ma, Fang Xie, Pengliang Ding, Pan Li

To this end, in this paper, we propose a novel end-to-end data-driven model based on Convolutional Neural Network (CNN), namely Person-Job Fit Neural Network (PJFNN), for matching a talent qualification to the requirements of a job.

Data Visualization Representation Learning

Quadratic Decomposable Submodular Function Minimization

1 code implementation NeurIPS 2018 Pan Li, Niao He, Olgica Milenkovic

The problem is closely related to decomposable submodular function minimization and arises in many learning on graphs and hypergraphs settings, such as graph-based semi-supervised learning and PageRank.

BEBP: An Poisoning Method Against Machine Learning Based IDSs

no code implementations11 Mar 2018 Pan Li, Qiang Liu, Wentao Zhao, Dongxu Wang, Siqi Wang

In this paper, we adopt the Edge Pattern Detection (EPD) algorithm to design a novel poisoning method that attack against several machine learning algorithms used in IDSs.

BIG-bench Machine Learning Intrusion Detection

Revisiting Decomposable Submodular Function Minimization with Incidence Relations

1 code implementation NeurIPS 2018 Pan Li, Olgica Milenkovic

We introduce a new approach to decomposable submodular function minimization (DSFM) that exploits incidence relations.

Submodular Hypergraphs: p-Laplacians, Cheeger Inequalities and Spectral Clustering

1 code implementation ICML 2018 Pan Li, Olgica Milenkovic

We introduce submodular hypergraphs, a family of hypergraphs that have different submodular weights associated with different cuts of hyperedges.

Clustering

Bayesian Renewables Scenario Generation via Deep Generative Networks

1 code implementation2 Feb 2018 Yize Chen, Pan Li, Baosen Zhang

We present a method to generate renewable scenarios using Bayesian probabilities by implementing the Bayesian generative adversarial network~(Bayesian GAN), which is a variant of generative adversarial networks based on two interconnected deep neural networks.

Generative Adversarial Network

Inhomogeneous Hypergraph Clustering with Applications

1 code implementation NeurIPS 2017 Pan Li, Olgica Milenkovic

Hypergraph partitioning is an important problem in machine learning, computer vision and network analytics.

Clustering hypergraph partitioning

Distribution System Voltage Control under Uncertainties using Tractable Chance Constraints

no code implementations28 Apr 2017 Pan Li, Baihong Jin, Dai Wang, Baosen Zhang

We also show that this optimization problem is convex for a wide variety of probabilistic distributions.

Multiclass MinMax Rank Aggregation

no code implementations28 Jan 2017 Pan Li, Olgica Milenkovic

We introduce a new family of minmax rank aggregation problems under two distance measures, the Kendall {\tau} and the Spearman footrule.

Efficient Rank Aggregation via Lehmer Codes

no code implementations28 Jan 2017 Pan Li, Arya Mazumdar, Olgica Milenkovic

We propose a novel rank aggregation method based on converting permutations into their corresponding Lehmer codes or other subdiagonal images.

An Optimal Treatment Assignment Strategy to Evaluate Demand Response Effect

no code implementations2 Oct 2016 Pan Li, Baosen Zhang

The accurate estimation of impact of demand response signals to customers' consumption is central to any successful program.

Experimental Design

A Sparse Linear Model and Significance Test for Individual Consumption Prediction

no code implementations5 Nov 2015 Pan Li, Baosen Zhang, Yang Weng, Ram Rajagopal

Accurate prediction of user consumption is a key part not only in understanding consumer flexibility and behavior patterns, but in the design of robust and efficient energy saving programs as well.

Two-sample testing

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