Search Results for author:
Found 103 papers, 49 papers with code
Stochastic Gradient Langevin Unlearning
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.
Pairwise Alignment Improves Graph Domain Adaptation
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.
Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics
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.
No Need to Look Back: An Efficient and Scalable Approach for Temporal Network Representation Learning
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.
MEA-Defender: A Robust Watermark against Model Extraction Attack
To protect the Intellectual Property (IP) of the original owners over such DNN models, backdoor-based watermarks have been extensively studied.
Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
We propose Langevin unlearning, an unlearning framework based on noisy gradient descent with privacy guarantees for approximate unlearning problems.
xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein
We propose a unified protein language model, xTrimoPGLM, to address these two types of tasks simultaneously through an innovative pre-training framework.
Learning Scalable Structural Representations for Link Prediction with Bloom Signatures
We further show that any type of neighborhood overlap-based heuristic can be estimated by a neural network that takes Bloom signatures as input.
KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph
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.
High Pileup Particle Tracking with Object Condensation
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.
On the Inherent Privacy Properties of Discrete Denoising Diffusion Models
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.
ABKD: Graph Neural Network Compression with Attention-Based Knowledge Distillation
To address this shortcoming, we propose a novel KD approach to GNN compression that we call Attention-Based Knowledge Distillation (ABKD).
DIG-MILP: a Deep Instance Generator for Mixed-Integer Linear Programming with Feasibility Guarantee
Mixed-integer linear programming (MILP) stands as a notable NP-hard problem pivotal to numerous crucial industrial applications.
GraphMaker: Can Diffusion Models Generate Large Attributed Graphs?
However, these models face challenges in generating large attributed graphs due to the complex attribute-structure correlations and the large size of these graphs.
GDL-DS: A Benchmark for Geometric Deep Learning under Distribution Shifts
Geometric deep learning (GDL) has gained significant attention in various scientific fields, chiefly for its proficiency in modeling data with intricate geometric structures.
On the Stability of Expressive Positional Encodings for Graphs
Despite many attempts to address non-uniqueness, most methods overlook stability, leading to poor generalization on unseen graph structures.
Molecular Property Prediction
Out-of-Distribution Generalization
+1
Towards Poisoning Fair Representations
Fair machine learning seeks to mitigate model prediction bias against certain demographic subgroups such as elder and female.
Optimal Resource Allocation for U-Shaped Parallel Split Learning
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
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).
Structural Re-weighting Improves Graph Domain Adaptation
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.
Prompt Tuning Large Language Models on Personalized Aspect Extraction for Recommendations
For the aspect-based recommendation component, the extracted aspects are concatenated with the usual user and item features used by the recommendation model.
Hierarchical Reinforcement Learning for Modeling User Novelty-Seeking Intent in Recommender Systems
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
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.
Improving Graph Neural Networks on Multi-node Tasks with Labeling Tricks
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.
SUREL+: Moving from Walks to Sets for Scalable Subgraph-based Graph Representation Learning
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.
Ranked #1 on
Link Property Prediction
on ogbl-ppa
Unsupervised Learning for Combinatorial Optimization Needs Meta-Learning
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.
Extensible and Efficient Proxy for Neural Architecture Search
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.
Graph Federated Learning with Hidden Representation Sharing
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.
Interpretable Geometric Deep Learning via Learnable Randomness Injection
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
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.
Extensible Proxy for Efficient NAS
(2) Efficient proxies are not extensible to multi-modality downstream tasks.
A Novel Membership Inference Attack against Dynamic Neural Networks by Utilizing Policy Networks Information
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.
Spatio-temporal Tendency Reasoning for Human Body Pose and Shape Estimation from Videos
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.
Ranked #55 on
3D Human Pose Estimation
on MPI-INF-3DHP
SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning
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.
Neighborhood-aware Scalable Temporal Network Representation Learning
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.
Understanding Non-linearity in Graph Neural Networks from the Bayesian-Inference Perspective
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.
Equivariant Hypergraph Diffusion Neural Operators
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.
Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxation
Using machine learning to solve combinatorial optimization (CO) problems is challenging, especially when the data is unlabeled.
Two-Dimensional Weisfeiler-Lehman Graph Neural Networks for Link Prediction
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.
A Framework of Meta Functional Learning for Regularising Knowledge Transfer
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.
Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks
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.
Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning
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.
Ranked #1 on
Link Property Prediction
on ogbl-citation2
Graph Auto-Encoder Via Neighborhood Wasserstein Reconstruction
Graph neural networks (GNNs) have drawn significant research attention recently, mostly under the setting of semi-supervised learning.
Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism
However, those post-hoc methods often fail to provide stable interpretation and may extract features that are spuriously correlated with the task.
Ranked #11 on
Graph Property Prediction
on ogbg-molhiv
High-Level Synthesis Performance Prediction using GNNs: Benchmarking, Modeling, and Advancing
The contribution of this work is three-fold.
Better Trigger Inversion Optimization in Backdoor Scanning
A popular trigger inversion method is by optimization.
Ranking Distance Calibration for Cross-Domain Few-Shot Learning
The calibrated distance in this target-aware non-linear subspace is complementary to that in the pre-trained representation.
Applications and Techniques for Fast Machine Learning in Science
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.
Nested Graph Neural Networks
The key is to make each node representation encode a subgraph around it more than a subtree.
Ranked #9 on
Graph Property Prediction
on ogbg-molpcba
FEATURE-AUGMENTED HYPERGRAPH NEURAL NETWORKS
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.
Semi-supervised Graph Neural Network for Particle-level Noise Removal
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
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.
A Web Scale Entity Extraction System
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
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)
On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs
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.
Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns
We find that the prediction performance of a wide range of GNN models is highly correlated with the node level assortativity.
Graph Learning
Node Classification on Non-Homophilic (Heterophilic) Graphs
Neural Predicting Higher-order Patterns in Temporal Networks
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
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.
Principled Hyperedge Prediction with Structural Spectral Features and Neural Networks
SNALS captures the joint interactions of a hyperedge by its local environment, which is retrieved by collecting the spectrum information of their connections.
Dual Attentive Sequential Learning for Cross-Domain Click-Through Rate Prediction
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.
PURS: Personalized Unexpected Recommender System for Improving User Satisfaction
Classical recommender system methods typically face the filter bubble problem when users only receive recommendations of their familiar items, making them bored and dissatisfied.
Dual Metric Learning for Effective and Efficient Cross-Domain Recommendations
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.
HufuNet: Embedding the Left Piece as Watermark and Keeping the Right Piece for Ownership Verification in Deep Neural Networks
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
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
Recently, hypergraphs have attracted a lot of attention due to their ability to capture complex relations among entities.
Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks
Temporal networks serve as abstractions of many real-world dynamic systems.
Handling many conversions per click in modeling delayed feedback
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
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.
Striking a Balance Between Stability and Plasticity for Class-Incremental Learning
With the reformulated baseline, we present two new approaches to CIL by learning class-independent knowledge and multi-perspective knowledge, respectively.
Revisiting graph neural networks and distance encoding from a practical view
We want to explain how DE makes GNNs fit for node classification and link prediction.
F-FADE: Frequency Factorization for Anomaly Detection in Edge Streams
Edge streams are commonly used to capture interactions in dynamic networks, such as email, social, or computer networks.
Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning
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).
Ranked #1 on
Link Property Prediction
on ogbl-citation2
Graph Information Bottleneck
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.
Revisiting Graph Neural Networks for Link Prediction
Graph neural networks (GNNs) have achieved great success in recent years.
MSTREAM: Fast Anomaly Detection in Multi-Aspect Streams
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?
Ranked #1 on
Intrusion Detection
on CIC-DDoS
Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning
DE captures the distance between the node set whose representation is to be learned and each node in the graph.
Latent Unexpected Recommendations
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.
Adaptive Universal Generalized PageRank Graph Neural Network
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
Conditional Structure Generation through Graph Variational Generative Adversarial Nets
Graph embedding has been intensively studied recently, due to the advance of various neural network models.
Landing Probabilities of Random Walks for Seed-Set Expansion in Hypergraphs
We describe the first known mean-field study of landing probabilities for random walks on hypergraphs.
DDTCDR: Deep Dual Transfer Cross Domain Recommendation
Cross domain recommender systems have been increasingly valuable for helping consumers identify the most satisfying items from different categories.
Towards Controllable and Personalized Review Generation
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.
Meta-Graph Based HIN Spectral Embedding: Methods, Analyses, and Insights
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
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.
Latent Multi-Criteria Ratings for Recommendations
Multi-criteria recommender systems have been increasingly valuable for helping consumers identify the most relevant items based on different dimensions of user experiences.
Optimizing Generalized PageRank Methods for Seed-Expansion Community Detection
Landing probabilities (LP) of random walks (RW) over graphs encode rich information regarding graph topology.
Latent Unexpected and Useful Recommendation
Providing unexpected recommendations is an important task for recommender systems.
A tractable ellipsoidal approximation for voltage regulation problems
We present a machine learning approach to the solution of chance constrained optimizations in the context of voltage regulation problems in power system operation.
Quadratic Decomposable Submodular Function Minimization: Theory and Practice (Computation and Analysis of PageRank over Hypergraphs)
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.
$HS^2$: Active Learning over Hypergraphs
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].
Motif and Hypergraph Correlation Clustering
Our contributions are as follows: We first introduce several variants of motif correlation clustering and then show that these clustering problems are NP-hard.
Person-Job Fit: Adapting the Right Talent for the Right Job with Joint Representation Learning
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.
Quadratic Decomposable Submodular Function Minimization
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
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.
Revisiting Decomposable Submodular Function Minimization with Incidence Relations
We introduce a new approach to decomposable submodular function minimization (DSFM) that exploits incidence relations.
Submodular Hypergraphs: p-Laplacians, Cheeger Inequalities and Spectral Clustering
We introduce submodular hypergraphs, a family of hypergraphs that have different submodular weights associated with different cuts of hyperedges.
Bayesian Renewables Scenario Generation via Deep Generative Networks
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.
Inhomogeneous Hypergraph Clustering with Applications
Hypergraph partitioning is an important problem in machine learning, computer vision and network analytics.
Distribution System Voltage Control under Uncertainties using Tractable Chance Constraints
We also show that this optimization problem is convex for a wide variety of probabilistic distributions.
Efficient Rank Aggregation via Lehmer Codes
We propose a novel rank aggregation method based on converting permutations into their corresponding Lehmer codes or other subdiagonal images.
Multiclass MinMax Rank Aggregation
We introduce a new family of minmax rank aggregation problems under two distance measures, the Kendall {\tau} and the Spearman footrule.
An Optimal Treatment Assignment Strategy to Evaluate Demand Response Effect
The accurate estimation of impact of demand response signals to customers' consumption is central to any successful program.
A Sparse Linear Model and Significance Test for Individual Consumption Prediction
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.
