arXiv subjects

Yufei Han

Publications and source records attributed to Yufei Han.

42 records · Page 3Linked to original sources

arXiv2019

Robust Federated Training via Collaborative Machine Teaching using Trusted Instances

Federated learning performs distributed model training using local data hosted by agents. It shares only model parameter updates for iterative aggregation at the server. Although it is privacy-preserving by design, federated learning is vulnerable to noise corruption of local agents, as demonstrated in the previous study on adversarial data poisoning threat against federated learning systems. Even a single noise-corrupted agent can bias the model training. In our work, we propose a collaborative and privacy-preserving machine teaching paradigm with multiple distributed teachers, to improve robustness of the federated training process against local data corruption. We assume that each local agent (teacher) have the resources to verify a small portions of trusted instances, which may not by itself be adequate for learning. In the proposed collaborative machine teaching method, these trusted instances guide the distributed agents to jointly select a compact while informative training subset from data hosted by their own. Simultaneously, the agents learn to add changes of limited magnitudes into the selected data instances, in order to improve the testing performances of the federally trained model despite of the training data corruption. Experiments on toy and real data demonstrate that our approach can identify training set bugs effectively and suggest appropriate changes to the labels. Our algorithm is a step toward trustworthy machine learning.

cs.LG↗

arXiv2019

Collaborative and Privacy-Preserving Machine Teaching via Consensus Optimization

In this work, we define a collaborative and privacy-preserving machine teaching paradigm with multiple distributed teachers. We focus on consensus super teaching. It aims at organizing distributed teachers to jointly select a compact while informative training subset from data hosted by the teachers to make a learner learn better. The challenges arise from three perspectives. First, the state-of-the-art pool-based super teaching method applies mixed-integer non-linear programming (MINLP) which does not scale well to very large data sets. Second, it is desirable to restrict data access of the teachers to only their own data during the collaboration stage to mitigate privacy leaks. Finally, the teaching collaboration should be communication-efficient since large communication overheads can cause synchronization delays between teachers. To address these challenges, we formulate collaborative teaching as a consensus and privacy-preserving optimization process to minimize teaching risk. We theoretically demonstrate the necessity of collaboration between teachers for improving the learner's learning. Furthermore, we show that the proposed method enjoys a similar property as the Oracle property of adaptive Lasso. The empirical study illustrates that our teaching method can deliver significantly more accurate teaching results with high speed, while the non-collaborative MINLP-based super teaching becomes prohibitively expensive to compute.

cs.LG↗

arXiv2016

Mini-Batch Spectral Clustering

The cost of computing the spectrum of Laplacian matrices hinders the application of spectral clustering to large data sets. While approximations recover computational tractability, they can potentially affect clustering performance. This paper proposes a practical approach to learn spectral clustering based on adaptive stochastic gradient optimization. Crucially, the proposed approach recovers the exact spectrum of Laplacian matrices in the limit of the iterations, and the cost of each iteration is linear in the number of samples. Extensive experimental validation on data sets with up to half a million samples demonstrate its scalability and its ability to outperform state-of-the-art approximate methods to learn spectral clustering for a given computational budget.

stat.ML↗

arXiv2013

Pairwise MRF Calibration by Perturbation of the Bethe Reference Point

We investigate different ways of generating approximate solutions to the pairwise Markov random field (MRF) selection problem. We focus mainly on the inverse Ising problem, but discuss also the somewhat related inverse Gaussian problem because both types of MRF are suitable for inference tasks with the belief propagation algorithm (BP) under certain conditions. Our approach consists in to take a Bethe mean-field solution obtained with a maximum spanning tree (MST) of pairwise mutual information, referred to as the \emph{Bethe reference point}, for further perturbation procedures. We consider three different ways following this idea: in the first one, we select and calibrate iteratively the optimal links to be added starting from the Bethe reference point; the second one is based on the observation that the natural gradient can be computed analytically at the Bethe point; in the third one, assuming no local field and using low temperature expansion we develop a dual loop joint model based on a well chosen fundamental cycle basis. We indeed identify a subclass of planar models, which we refer to as \emph{Bethe-dual graph models}, having possibly many loops, but characterized by a singly connected dual factor graph, for which the partition function and the linear response can be computed exactly in respectively O(N) and $O(N^2)$ operations, thanks to a dual weight propagation (DWP) message passing procedure that we set up. When restricted to this subclass of models, the inverse Ising problem being convex, becomes tractable at any temperature. Experimental tests on various datasets with refined $L_0$ or $L_1$ regularization procedures indicate that these approaches may be competitive and useful alternatives to existing ones.

cond-mat.dis-nn↗

arXiv2012

Statistical Traffic State Analysis in Large-scale Transportation Networks Using Locality-Preserving Non-negative Matrix Factorization

Statistical traffic data analysis is a hot topic in traffic management and control. In this field, current research progresses focus on analyzing traffic flows of individual links or local regions in a transportation network. Less attention are paid to the global view of traffic states over the entire network, which is important for modeling large-scale traffic scenes. Our aim is precisely to propose a new methodology for extracting spatio-temporal traffic patterns, ultimately for modeling large-scale traffic dynamics, and long-term traffic forecasting. We attack this issue by utilizing Locality-Preserving Non-negative Matrix Factorization (LPNMF) to derive low-dimensional representation of network-level traffic states. Clustering is performed on the compact LPNMF projections to unveil typical spatial patterns and temporal dynamics of network-level traffic states. We have tested the proposed method on simulated traffic data generated for a large-scale road network, and reported experimental results validate the ability of our approach for extracting meaningful large-scale space-time traffic patterns. Furthermore, the derived clustering results provide an intuitive understanding of spatial-temporal characteristics of traffic flows in the large-scale network, and a basis for potential long-term forecasting.

cs.CE↗

arXiv2012

Analysis of Large-scale Traffic Dynamics using Non-negative Tensor Factorization

In this paper, we present our work on clustering and prediction of temporal dynamics of global congestion configurations in large-scale road networks. Instead of looking into temporal traffic state variation of individual links, or of small areas, we focus on spatial congestion configurations of the whole network. In our work, we aim at describing the typical temporal dynamic patterns of this network-level traffic state and achieving long-term prediction of the large-scale traffic dynamics, in a unified data-mining framework. To this end, we formulate this joint task using Non-negative Tensor Factorization (NTF), which has been shown to be a useful decomposition tools for multivariate data sequences. Clustering and prediction are performed based on the compact tensor factorization results. Experiments on large-scale simulated data illustrate the interest of our method with promising results for long-term forecast of traffic evolution.

cs.LG↗