Search Results for author: Jiaming Xu

Found 60 papers, 12 papers with code

Spectral Graph Matching and Regularized Quadratic Relaxations: Algorithm and Theory

no code implementations ICML 2020 Zhou Fan, Cheng Mao, Yihong Wu, Jiaming Xu

Graph matching, also known as network alignment, aims at recovering the latent vertex correspondence between two unlabeled, edge-correlated weighted graphs.

Graph Matching

Random Graph Matching in Geometric Models: the Case of Complete Graphs

no code implementations22 Feb 2022 Haoyu Wang, Yihong Wu, Jiaming Xu, Israel Yolou

This paper studies the problem of matching two complete graphs with edge weights correlated through latent geometries, extending a recent line of research on random graph matching with independent edge weights to geometric models.

Graph Matching

LiMuSE: Lightweight Multi-modal Speaker Extraction

1 code implementation7 Nov 2021 Qinghua Liu, Yating Huang, Yunzhe Hao, Jiaming Xu, Bo Xu

In recent years, multi-modal cues, including spatial information, facial expression and voiceprint, are introduced to the speaker extraction task to serve as complementary information to each other to achieve better performance.

Model Compression Quantization +1

Testing network correlation efficiently via counting trees

no code implementations22 Oct 2021 Cheng Mao, Yihong Wu, Jiaming Xu, Sophie H. Yu

We propose a new procedure for testing whether two networks are edge-correlated through some latent vertex correspondence.

A Non-parametric View of FedAvg and FedProx: Beyond Stationary Points

no code implementations29 Jun 2021 Lili Su, Jiaming Xu, Pengkun Yang

We discover that when the data heterogeneity is moderate, a client with limited local data can benefit from a common model with a large federation gain.

Federated Learning

WASE: Learning When to Attend for Speaker Extraction in Cocktail Party Environments

1 code implementation13 Jun 2021 Yunzhe Hao, Jiaming Xu, Peng Zhang, Bo Xu

In the speaker extraction problem, it is found that additional information from the target speaker contributes to the tracking and extraction of the target speaker, which includes voiceprint, lip movement, facial expression, and spatial information.

Action Detection Activity Detection

One-pass Stochastic Gradient Descent in Overparametrized Two-layer Neural Networks

no code implementations1 May 2021 Jiaming Xu, Hanjing Zhu

There has been a recent surge of interest in understanding the convergence of gradient descent (GD) and stochastic gradient descent (SGD) in overparameterized neural networks.

MIMO Self-attentive RNN Beamformer for Multi-speaker Speech Separation

no code implementations17 Apr 2021 Xiyun Li, Yong Xu, Meng Yu, Shi-Xiong Zhang, Jiaming Xu, Bo Xu, Dong Yu

The spatial self-attention module is designed to attend on the cross-channel correlation in the covariance matrices.

Automatic Speech Recognition Speech Separation

The planted matching problem: Sharp threshold and infinite-order phase transition

no code implementations17 Mar 2021 Jian Ding, Yihong Wu, Jiaming Xu, Dana Yang

Conversely, if $\sqrt{d} B(\mathcal{P},\mathcal{Q}) \ge 1+\epsilon$ for an arbitrarily small constant $\epsilon>0$, the reconstruction error for any estimator is shown to be bounded away from $0$ under both the sparse and dense model, resolving the conjecture in [Moharrami et al. 2019, Semerjian et al. 2020].

Learner-Private Convex Optimization

no code implementations23 Feb 2021 Jiaming Xu, Kuang Xu, Dana Yang

Convex optimization with feedback is a framework where a learner relies on iterative queries and feedback to arrive at the minimizer of a convex function.

The Power of $D$-hops in Matching Power-Law Graphs

no code implementations23 Feb 2021 Liren Yu, Jiaming Xu, Xiaojun Lin

Under the Chung-Lu random graph model with $n$ vertices, max degree $\Theta(\sqrt{n})$, and the power-law exponent $2<\beta<3$, we show that as soon as $D> \frac{4-\beta}{3-\beta}$, by optimally choosing the first slice, with high probability our algorithm can correctly match a constant fraction of the true pairs without any error, provided with only $\Omega((\log n)^{4-\beta})$ initial seeds.

Graph Matching

Settling the Sharp Reconstruction Thresholds of Random Graph Matching

no code implementations29 Jan 2021 Yihong Wu, Jiaming Xu, Sophie H. Yu

This paper studies the problem of recovering the hidden vertex correspondence between two edge-correlated random graphs.

Graph Matching

Audio-visual Speech Separation with Adversarially Disentangled Visual Representation

no code implementations29 Nov 2020 Peng Zhang, Jiaming Xu, Jing Shi, Yunzhe Hao, Bo Xu

In our model, we use the face detector to detect the number of speakers in the scene and use visual information to avoid the permutation problem.

Speech Separation

Testing correlation of unlabeled random graphs

no code implementations23 Aug 2020 Yihong Wu, Jiaming Xu, Sophie H. Yu

We study the problem of detecting the edge correlation between two random graphs with $n$ unlabeled nodes.

Two-sample testing

Speaker-Conditional Chain Model for Speech Separation and Extraction

no code implementations25 Jun 2020 Jing Shi, Jiaming Xu, Yusuke Fujita, Shinji Watanabe, Bo Xu

With the predicted speaker information from whole observation, our model is helpful to solve the problem of conventional speech separation and speaker extraction for multi-round long recordings.

Audio and Speech Processing Sound

Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals

no code implementations NeurIPS 2020 Jing Shi, Xuankai Chang, Pengcheng Guo, Shinji Watanabe, Yusuke Fujita, Jiaming Xu, Bo Xu, Lei Xie

This model additionally has a simple and efficient stop criterion for the end of the transduction, making it able to infer the variable number of output sequences.

Speech Recognition Speech Separation

Graph Matching with Partially-Correct Seeds

1 code implementation8 Apr 2020 Liren Yu, Jiaming Xu, Xiaojun Lin

We establish non-asymptotic performance guarantees of perfect matching for both $1$-hop and $2$-hop algorithms, showing that our new $2$-hop algorithm requires substantially fewer correct seeds than the $1$-hop algorithm when graphs are sparse.

Graph Matching

The Planted Matching Problem: Phase Transitions and Exact Results

no code implementations18 Dec 2019 Mehrdad Moharrami, Cristopher Moore, Jiaming Xu

We study the problem of recovering a planted matching in randomly weighted complete bipartite graphs $K_{n, n}$.

DMRM: A Dual-channel Multi-hop Reasoning Model for Visual Dialog

1 code implementation18 Dec 2019 Feilong Chen, Fandong Meng, Jiaming Xu, Peng Li, Bo Xu, Jie zhou

Visual Dialog is a vision-language task that requires an AI agent to engage in a conversation with humans grounded in an image.

Visual Dialog

Consistent recovery threshold of hidden nearest neighbor graphs

no code implementations18 Nov 2019 Jian Ding, Yihong Wu, Jiaming Xu, Dana Yang

Motivated by applications such as discovering strong ties in social networks and assembling genome subsequences in biology, we study the problem of recovering a hidden $2k$-nearest neighbor (NN) graph in an $n$-vertex complete graph, whose edge weights are independent and distributed according to $P_n$ for edges in the hidden $2k$-NN graph and $Q_n$ otherwise.

Optimal query complexity for private sequential learning against eavesdropping

no code implementations21 Sep 2019 Jiaming Xu, Kuang Xu, Dana Yang

We study the query complexity of a learner-private sequential learning problem, motivated by the privacy and security concerns due to eavesdropping that arise in practical applications such as pricing and Federated Learning.

Federated Learning

Spectral Graph Matching and Regularized Quadratic Relaxations II: Erdős-Rényi Graphs and Universality

no code implementations20 Jul 2019 Zhou Fan, Cheng Mao, Yihong Wu, Jiaming Xu

We analyze a new spectral graph matching algorithm, GRAph Matching by Pairwise eigen-Alignments (GRAMPA), for recovering the latent vertex correspondence between two unlabeled, edge-correlated weighted graphs.

Graph Matching

Spectral Graph Matching and Regularized Quadratic Relaxations I: The Gaussian Model

no code implementations20 Jul 2019 Zhou Fan, Cheng Mao, Yihong Wu, Jiaming Xu

Departing from prior spectral approaches that only compare top eigenvectors, or eigenvectors of the same order, GRAMPA first constructs a similarity matrix as a weighted sum of outer products between all pairs of eigenvectors of the two graphs, with weights given by a Cauchy kernel applied to the separation of the corresponding eigenvalues, then outputs a matching by a simple rounding procedure.

Graph Matching

A Working Memory Model for Task-oriented Dialog Response Generation

no code implementations ACL 2019 Xiuyi Chen, Jiaming Xu, Bo Xu

Our WMM2Seq adopts a working memory to interact with two separated long-term memories, which are the episodic memory for memorizing dialog history and the semantic memory for storing KB tuples.

Response Generation

The World in My Mind: Visual Dialog with Adversarial Multi-modal Feature Encoding

no code implementations NAACL 2019 Yiqun Yao, Jiaming Xu, Bo Xu

Visual Dialog is a multi-modal task that requires a model to participate in a multi-turn human dialog grounded on an image, and generate correct, human-like responses.

Visual Dialog

POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashion

1 code implementation6 May 2019 Wen Chen, Pipei Huang, Jiaming Xu, Xin Guo, Cheng Guo, Fei Sun, Chao Li, Andreas Pfadler, Huan Zhao, Binqiang Zhao

In particular, there exist two requirements for fashion outfit recommendation: the Compatibility of the generated fashion outfits, and the Personalization in the recommendation process.

Efficient random graph matching via degree profiles

1 code implementation19 Nov 2018 Jian Ding, Zongming Ma, Yihong Wu, Jiaming Xu

This work develops an $\tilde{O}(n d^2+n^2)$-time algorithm which perfectly recovers the true vertex correspondence with high probability, provided that the average degree is at least $d = \Omega(\log^2 n)$ and the two graphs differ by at most $\delta = O( \log^{-2}(n) )$ fraction of edges.

Graph Matching

Concept Learning through Deep Reinforcement Learning with Memory-Augmented Neural Networks

no code implementations15 Nov 2018 Jing Shi, Jiaming Xu, Yiqun Yao, Bo Xu

In this paper, we present a memory-augmented neural network which is motivated by the process of human concept learning.

One-Shot Learning Outlier Detection +1

Convex Relaxation Methods for Community Detection

no code implementations30 Sep 2018 Xiao-Dong Li, Yudong Chen, Jiaming Xu

We introduce some important theoretical techniques and results for establishing the consistency of convex community detection under various statistical models.

Community Detection

Seeded Graph Matching via Large Neighborhood Statistics

no code implementations26 Jul 2018 Elchanan Mossel, Jiaming Xu

We study a well known noisy model of the graph isomorphism problem.

Graph Matching

Securing Distributed Gradient Descent in High Dimensional Statistical Learning

no code implementations26 Apr 2018 Lili Su, Jiaming Xu

Nevertheless, the empirical risk (sample version) is allowed to be non-convex.

Hidden Hamiltonian Cycle Recovery via Linear Programming

no code implementations15 Apr 2018 Vivek Bagaria, Jian Ding, David Tse, Yihong Wu, Jiaming Xu

Represented as bicolored multi-graphs, these extreme points are further decomposed into simpler "blossom-type" structures for the large deviation analysis and counting arguments.

Traveling Salesman Problem

Rates of Convergence of Spectral Methods for Graphon Estimation

no code implementations ICML 2018 Jiaming Xu

Recent studies have identified the minimax error rate of estimating the graphon from a single realization of the random graph.

Community Detection Graphon Estimation +2

Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent

no code implementations16 May 2017 Yudong Chen, Lili Su, Jiaming Xu

The total computational complexity of our algorithm is of $O((Nd/m) \log N)$ at each working machine and $O(md + kd \log^3 N)$ at the central server, and the total communication cost is of $O(m d \log N)$.

Federated Learning

Learning from Comparisons and Choices

no code implementations24 Apr 2017 Sahand Negahban, Sewoong Oh, Kiran K. Thekumparampil, Jiaming Xu

This also allows one to compute similarities among users and items to be used for categorization and search.

Recommendation Systems

Combining Lexical and Semantic-based Features for Answer Sentence Selection

no code implementations WS 2016 Jing Shi, Jiaming Xu, Yiqun Yao, Suncong Zheng, Bo Xu

As the result of the evaluation shows, our solution provides a valuable and brief model which could be used in modelling question answering or sentence semantic relevance.

Feature Engineering Open-Domain Question Answering

Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling

3 code implementations COLING 2016 Peng Zhou, Zhenyu Qi, Suncong Zheng, Jiaming Xu, Hongyun Bao, Bo Xu

To integrate the features on both dimensions of the matrix, this paper explores applying 2D max pooling operation to obtain a fixed-length representation of the text.

Classification General Classification +2

Hierarchical Memory Networks for Answer Selection on Unknown Words

1 code implementation COLING 2016 Jiaming Xu, Jing Shi, Yiqun Yao, Suncong Zheng, Bo Xu

Recently, end-to-end memory networks have shown promising results on Question Answering task, which encode the past facts into an explicit memory and perform reasoning ability by making multiple computational steps on the memory.

Answer Selection

Semidefinite Programs for Exact Recovery of a Hidden Community

no code implementations20 Feb 2016 Bruce Hajek, Yihong Wu, Jiaming Xu

We study a semidefinite programming (SDP) relaxation of the maximum likelihood estimation for exactly recovering a hidden community of cardinality $K$ from an $n \times n$ symmetric data matrix $A$, where for distinct indices $i, j$, $A_{ij} \sim P$ if $i, j$ are both in the community and $A_{ij} \sim Q$ otherwise, for two known probability distributions $P$ and $Q$.

Stochastic Block Model

Convexified Modularity Maximization for Degree-corrected Stochastic Block Models

no code implementations28 Dec 2015 Yudong Chen, Xiao-Dong Li, Jiaming Xu

We establish non-asymptotic theoretical guarantees for both approximate clustering and perfect clustering.

Community Detection Stochastic Block Model

Submatrix localization via message passing

no code implementations30 Oct 2015 Bruce Hajek, Yihong Wu, Jiaming Xu

The principal submatrix localization problem deals with recovering a $K\times K$ principal submatrix of elevated mean $\mu$ in a large $n\times n$ symmetric matrix subject to additive standard Gaussian noise.

Community Detection

Recovering a Hidden Community Beyond the Kesten-Stigum Threshold in $O(|E| \log^*|V|)$ Time

no code implementations9 Oct 2015 Bruce Hajek, Yihong Wu, Jiaming Xu

We show that a belief propagation algorithm achieves weak recovery if $\lambda>1/e$, beyond the Kesten-Stigum threshold by a factor of $1/e.$ The belief propagation algorithm only needs to run for $\log^\ast n+O(1) $ iterations, with the total time complexity $O(|E| \log^*n)$, where $\log^*n$ is the iterated logarithm of $n.$ Conversely, if $\lambda \leq 1/e$, no local algorithm can asymptotically outperform trivial random guessing.

Community Detection Stochastic Block Model

Information Limits for Recovering a Hidden Community

no code implementations25 Sep 2015 Bruce Hajek, Yihong Wu, Jiaming Xu

We study the problem of recovering a hidden community of cardinality $K$ from an $n \times n$ symmetric data matrix $A$, where for distinct indices $i, j$, $A_{ij} \sim P$ if $i, j$ both belong to the community and $A_{ij} \sim Q$ otherwise, for two known probability distributions $P$ and $Q$ depending on $n$.

Density Evolution in the Degree-correlated Stochastic Block Model

no code implementations10 Sep 2015 Elchanan Mossel, Jiaming Xu

There is a recent surge of interest in identifying the sharp recovery thresholds for cluster recovery under the stochastic block model.

Stochastic Block Model

Local Algorithms for Block Models with Side Information

no code implementations10 Aug 2015 Elchanan Mossel, Jiaming Xu

There has been a recent interest in understanding the power of local algorithms for optimization and inference problems on sparse graphs.

Community Detection Stochastic Block Model

Collaboratively Learning Preferences from Ordinal Data

no code implementations NeurIPS 2015 Sewoong Oh, Kiran K. Thekumparampil, Jiaming Xu

In order to predict the preferences, we want to learn the underlying model from noisy observations of the low-rank matrix, collected as revealed preferences in various forms of ordinal data.

Collaborative Ranking Recommendation Systems

Achieving Exact Cluster Recovery Threshold via Semidefinite Programming: Extensions

no code implementations26 Feb 2015 Bruce Hajek, Yihong Wu, Jiaming Xu

Extending the proof techniques, in this paper it is shown that SDP relaxations also achieve the sharp recovery threshold in the following cases: (1) Binary stochastic block model with two clusters of sizes proportional to network size but not necessarily equal; (2) Stochastic block model with a fixed number of equal-sized clusters; (3) Binary censored block model with the background graph being Erd\H{o}s-R\'enyi.

Community Detection Stochastic Block Model

Clustering and Inference From Pairwise Comparisons

no code implementations16 Feb 2015 Rui Wu, Jiaming Xu, R. Srikant, Laurent Massoulié, Marc Lelarge, Bruce Hajek

We propose an efficient algorithm that accurately estimates the individual preferences for almost all users, if there are $r \max \{m, n\}\log m \log^2 n$ pairwise comparisons per type, which is near optimal in sample complexity when $r$ only grows logarithmically with $m$ or $n$.

Reconstruction in the Labeled Stochastic Block Model

no code implementations11 Feb 2015 Marc Lelarge, Laurent Massoulié, Jiaming Xu

The labeled stochastic block model is a random graph model representing networks with community structure and interactions of multiple types.

Stochastic Block Model Two-sample testing

Achieving Exact Cluster Recovery Threshold via Semidefinite Programming

no code implementations24 Nov 2014 Bruce Hajek, Yihong Wu, Jiaming Xu

The binary symmetric stochastic block model deals with a random graph of $n$ vertices partitioned into two equal-sized clusters, such that each pair of vertices is connected independently with probability $p$ within clusters and $q$ across clusters.

Stochastic Block Model

Computational Lower Bounds for Community Detection on Random Graphs

no code implementations25 Jun 2014 Bruce Hajek, Yihong Wu, Jiaming Xu

This paper studies the problem of detecting the presence of a small dense community planted in a large Erd\H{o}s-R\'enyi random graph $\mathcal{G}(N, q)$, where the edge probability within the community exceeds $q$ by a constant factor.

Community Detection

Minimax-optimal Inference from Partial Rankings

no code implementations NeurIPS 2014 Bruce Hajek, Sewoong Oh, Jiaming Xu

For a given assignment of items to users, we first derive an oracle lower bound of the estimation error that holds even for the more general Thurstone models.

Jointly Clustering Rows and Columns of Binary Matrices: Algorithms and Trade-offs

no code implementations1 Oct 2013 Jiaming Xu, Rui Wu, Kai Zhu, Bruce Hajek, R. Srikant, Lei Ying

In standard clustering problems, data points are represented by vectors, and by stacking them together, one forms a data matrix with row or column cluster structure.

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