Search Results for author:
Found 27 papers, 17 papers with code
Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning
Given that the right to be forgotten should be upheld for every individual, we advocate for a more rigorous evaluation of LLM unlearning methods.
LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation
By interpreting the partial order of nodes as a sequence of bipartite graphs, LayerDAG leverages autoregressive generation to model directional dependencies and employs diffusion models to capture logical dependencies within each bipartite graph.
Privately Learning from Graphs with Applications in Fine-tuning Large Language Models
Additionally, we explore the trade-offs between privacy, utility, and computational efficiency, offering insights into the practical deployment of our approach.
Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness
We also provide a strictly better privacy bound compared to state-of-the-art results for smooth strongly convex losses.
Differentially Private Graph Diffusion with Applications in Personalized PageRanks
Our privacy loss analysis is based on Privacy Amplification by Iteration (PABI), which to our best knowledge, is the first effort that analyzes PABI with Laplace noise and provides relevant applications.
Certified Machine Unlearning via Noisy Stochastic Gradient Descent
``The right to be forgotten'' ensured by laws for user data privacy becomes increasingly important.
Machine Unlearning of Pre-trained Large Language Models
This study investigates the concept of the `right to be forgotten' within the context of large language models (LLMs).
Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
Machine unlearning has raised significant interest with the adoption of laws ensuring the ``right to be forgotten''.
Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning
Exploring the full spectrum of trade-offs between privacy, model utility, and runtime efficiency is critical for practical unlearning scenarios.
On the Inherent Privacy Properties of Discrete Denoising Diffusion Models
Privacy concerns have led to a surge in the creation of synthetic datasets, with diffusion models emerging as a promising avenue.
Federated Classification in Hyperbolic Spaces via Secure Aggregation of Convex Hulls
Third, we compute the complexity of the convex hulls in hyperbolic spaces to assess the extent of data leakage; at the same time, in order to limit communication cost for the hulls, we propose a new quantization method for the Poincar\'e disc coupled with Reed-Solomon-like encoding.
Representer Point Selection for Explaining Regularized High-dimensional Models
We introduce a novel class of sample-based explanations we term high-dimensional representers, that can be used to explain the predictions of a regularized high-dimensional model in terms of importance weights for each of the training samples.
PINA: Leveraging Side Information in eXtreme Multi-label Classification via Predicted Instance Neighborhood Aggregation
Unlike most existing XMC frameworks that treat labels and input instances as featureless indicators and independent entries, PINA extracts information from the label metadata and the correlations among training instances.
Extreme Multi-Label Classification
MUlTI-LABEL-ClASSIFICATION
+1
Unlearning Graph Classifiers with Limited Data Resources
As the demand for user privacy grows, controlled data removal (machine unlearning) is becoming an important feature of machine learning models for data-sensitive Web applications such as social networks and recommender systems.
Certified Graph Unlearning
For example, when unlearning $20\%$ of the nodes on the Cora dataset, our approach suffers only a $0. 1\%$ loss in test accuracy while offering a $4$-fold speed-up compared to complete retraining.
HyperAid: Denoising in hyperbolic spaces for tree-fitting and hierarchical clustering
Furthermore, it is currently not known how to choose the most suitable approximation objective for noisy fitting.
Provably Accurate and Scalable Linear Classifiers in Hyperbolic Spaces
The excellent performance of the Poincar\'e second-order and strategic perceptrons shows that the proposed framework can be extended to general machine learning problems in hyperbolic spaces.
Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction
We also provide a theoretical analysis that justifies the use of XMC over link prediction and motivates integrating XR-Transformers, a powerful method for solving XMC problems, into the GIANT framework.
Ranked #2 on
Node Property Prediction
on ogbn-papers100M
Highly Scalable and Provably Accurate Classification in Poincare Balls
For hierarchical data, the space of choice is a hyperbolic space since it guarantees low-distortion embeddings for tree-like structures.
You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks
We propose AllSet, a new hypergraph neural network paradigm that represents a highly general framework for (hyper)graph neural networks and for the first time implements hypergraph neural network layers as compositions of two multiset functions that can be efficiently learned for each task and each dataset.
Linear Classifiers in Product Space Forms
The results show that classification in low-dimensional product space forms for scRNA-seq data offers, on average, a performance improvement of $\sim15\%$ when compared to that in Euclidean spaces of the same dimension.
Support Estimation with Sampling Artifacts and Errors
Here we introduce the first known approach to support estimation in the presence of sampling artifacts and errors where each sample is assumed to arise from a Poisson repeat channel which simultaneously captures repetitions and deletions of samples.
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.
Active learning in the geometric block model
Galhotra et al. recently proposed a motif-counting algorithm for unsupervised community detection in the geometric block model that is proved to be near-optimal.
Multi-MotifGAN (MMGAN): Motif-targeted Graph Generation and Prediction
Generative models are successful at retaining pairwise associations in the underlying networks but often fail to capture higher-order connectivity patterns known as network motifs.
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.
Optimizing Generalized PageRank Methods for Seed-Expansion Community Detection
Landing probabilities (LP) of random walks (RW) over graphs encode rich information regarding graph topology.
