arXiv subjects

Han Xiao

Publications and source records attributed to Han Xiao.

At least 145 records · Page 8Linked to original sources

arXiv2020

MODMA dataset: a Multi-modal Open Dataset for Mental-disorder Analysis

According to the World Health Organization, the number of mental disorder patients, especially depression patients, has grown rapidly and become a leading contributor to the global burden of disease. However, the present common practice of depression diagnosis is based on interviews and clinical scales carried out by doctors, which is not only labor-consuming but also time-consuming. One important reason is due to the lack of physiological indicators for mental disorders. With the rising of tools such as data mining and artificial intelligence, using physiological data to explore new possible physiological indicators of mental disorder and creating new applications for mental disorder diagnosis has become a new research hot topic. However, good quality physiological data for mental disorder patients are hard to acquire. We present a multi-modal open dataset for mental-disorder analysis. The dataset includes EEG and audio data from clinically depressed patients and matching normal controls. All our patients were carefully diagnosed and selected by professional psychiatrists in hospitals. The EEG dataset includes not only data collected using traditional 128-electrodes mounted elastic cap, but also a novel wearable 3-electrode EEG collector for pervasive applications. The 128-electrodes EEG signals of 53 subjects were recorded as both in resting state and under stimulation; the 3-electrode EEG signals of 55 subjects were recorded in resting state; the audio data of 52 subjects were recorded during interviewing, reading, and picture description. We encourage other researchers in the field to use it for testing their methods of mental-disorder analysis.

cs.DL↗

arXiv2020

Searching for polarization in signed graphs: a local spectral approach

Signed graphs have been used to model interactions in social net-works, which can be either positive (friendly) or negative (antagonistic). The model has been used to study polarization and other related phenomena in social networks, which can be harmful to the process of democratic deliberation in our society. An interesting and challenging task in this application domain is to detect polarized communities in signed graphs. A number of different methods have been proposed for this task. However, existing approaches aim at finding globally optimal solutions. Instead, in this paper we are interested in finding polarized communities that are related to a small set of seed nodes provided as input. Seed nodes may consist of two sets, which constitute the two sides of a polarized structure. In this paper we formulate the problem of finding local polarized communities in signed graphs as a locally-biased eigen-problem. By viewing the eigenvector associated with the smallest eigenvalue of the Laplacian matrix as the solution of a constrained optimization problem, we are able to incorporate the local information as an additional constraint. In addition, we show that the locally-biased vector can be used to find communities with approximation guarantee with respect to a local analogue of the Cheeger constant on signed graphs. By exploiting the sparsity in the input graph, an indicator vector for the polarized communities can be found in time linear to the graph size. Our experiments on real-world networks validate the proposed algorithm and demonstrate its usefulness in finding local structures in this semi-supervised manner.

cs.SI↗

arXiv2019

Hybrid Kronecker Product Decomposition and Approximation

Discovering the underlying low dimensional structure of high dimensional data has attracted a significant amount of researches recently and has shown to have a wide range of applications. As an effective dimension reduction tool, singular value decomposition is often used to analyze high dimensional matrices, which are traditionally assumed to have a low rank matrix approximation. In this paper, we propose a new approach. We assume a high dimensional matrix can be approximated by a sum of a small number of Kronecker products of matrices with potentially different configurations, named as a hybird Kronecker outer Product Approximation (hKoPA). It provides an extremely flexible way of dimension reduction compared to the low-rank matrix approximation. Challenges arise in estimating a hKoPA when the configurations of component Kronecker products are different or unknown. We propose an estimation procedure when the set of configurations are given and a joint configuration determination and component estimation procedure when the configurations are unknown. Specifically, a least squares backfitting algorithm is used when the configuration is given. When the configuration is unknown, an iterative greedy algorithm is used. Both simulation and real image examples show that the proposed algorithms have promising performances. The hybrid Kronecker product approximation may have potentially wider applications in low dimensional representation of high dimensional data

stat.ME↗

arXiv2019

Bonsai -- Diverse and Shallow Trees for Extreme Multi-label Classification

Extreme multi-label classification (XMC) refers to supervised multi-label learning involving hundreds of thousand or even millions of labels. In this paper, we develop a suite of algorithms, called Bonsai, which generalizes the notion of label representation in XMC, and partitions the labels in the representation space to learn shallow trees. We show three concrete realizations of this label representation space including : (i) the input space which is spanned by the input features, (ii) the output space spanned by label vectors based on their co-occurrence with other labels, and (iii) the joint space by combining the input and output representations. Furthermore, the constraint-free multi-way partitions learnt iteratively in these spaces lead to shallow trees. By combining the effect of shallow trees and generalized label representation, Bonsai achieves the best of both worlds - fast training which is comparable to state-of-the-art tree-based methods in XMC, and much better prediction accuracy, particularly on tail-labels. On a benchmark Amazon-3M dataset with 3 million labels, \bonsai outperforms a state-of-the-art one-vs-rest method in terms of prediction accuracy, while being approximately 200 times faster to train. The code for Bonsai is available at \url{https://github.com/xmc-aalto/bonsai}

cs.LG↗

arXiv2019

Autoregressive Models for Matrix-Valued Time Series

In finance, economics and many other fields, observations in a matrix form are often generated over time. For example, a set of key economic indicators are regularly reported in different countries every quarter. The observations at each quarter neatly form a matrix and are observed over many consecutive quarters. Dynamic transport networks with observations generated on the edges can be formed as a matrix observed over time. Although it is natural to turn the matrix observations into a long vector, and then use the standard vector time series models for analysis, it is often the case that the columns and rows of the matrix represent different types of structures that are closely interplayed. In this paper we follow the autoregressive structure for modeling time series and propose a novel matrix autoregressive model in a bilinear form that maintains and utilizes the matrix structure to achieve a greater dimensional reduction, as well as more interpretable results. Probabilistic properties of the models are investigated. Estimation procedures with their theoretical properties are presented and demonstrated with simulated and real examples.

stat.ME↗

arXiv2019

Asynchronous "Events" are Better For Motion Estimation

Event-based camera is a bio-inspired vision sensor that records intensity changes (called event) asynchronously in each pixel. As an instance of event-based camera, Dynamic and Active-pixel Vision Sensor (DAVIS) combines a standard camera and an event-based camera. However, traditional models could not deal with the event stream asynchronously. To analyze the event stream asynchronously, most existing approaches accumulate events within a certain time interval and treat the accumulated events as a synchronous frame, which wastes the intensity change information and weakens the advantages of DAVIS. Therefore, in this paper, we present the first neural asynchronous approach to process event stream for event-based camera. Our method asynchronously extracts dynamic information from events by leveraging previous motion and critical features of gray-scale frames. To our best knowledge, this is the first neural asynchronous method to analyze event stream through a novel deep neural network. Extensive experiments demonstrate that our proposed model achieves remarkable improvements against the state-of-the-art baselines.

cs.CV↗

arXiv2018

Robust Cascade Reconstruction by Steiner Tree Sampling

We consider a network where an infection cascade has taken place and a subset of infected nodes has been partially observed. Our goal is to reconstruct the underlying cascade that is likely to have generated these observations. We reduce this cascade-reconstruction problem to computing the marginal probability that a node is infected given the partial observations, which is a #P-hard problem. To circumvent this issue, we resort to estimating infection probabilities by generating a sample of probable cascades, which span the nodes that have already been observed to be infected, and avoid the nodes that have been observed to be uninfected. The sampling problem corresponds to sampling directed Steiner trees with a given set of terminals, which is a problem of independent interest and has received limited attention in the literature. For the latter problem we propose two novel algorithms with provable guarantees on the sampling distribution of the returned Steiner trees. The resulting method improves over state-of-the-art approaches that often make explicit assumptions about the infection-propagation model, or require additional parameters. Our method provides a more robust approach to the cascadereconstruction problem, which makes weaker assumptions about the infection model, requires fewer additional parameters, and can be used to estimate node infection probabilities. Empirically, we validate the proposed reconstruction algorithm on real-world graphs with both synthetic and real cascades. We show that our method outperforms all other baseline strategies in most cases

cs.SI↗

arXiv2018

Dual Ask-Answer Network for Machine Reading Comprehension

There are three modalities in the reading comprehension setting: question, answer and context. The task of question answering or question generation aims to infer an answer or a question when given the counterpart based on context. We present a novel two-way neural sequence transduction model that connects three modalities, allowing it to learn two tasks simultaneously and mutually benefit one another. During training, the model receives question-context-answer triplets as input and captures the cross-modal interaction via a hierarchical attention process. Unlike previous joint learning paradigms that leverage the duality of question generation and question answering at data level, we solve such dual tasks at the architecture level by mirroring the network structure and partially sharing components at different layers. This enables the knowledge to be transferred from one task to another, helping the model to find a general representation for each modality. The evaluation on four public datasets shows that our dual-learning model outperforms the mono-learning counterpart as well as the state-of-the-art joint models on both question answering and question generation tasks.

cs.AI↗

arXiv2018

Multi-Perspective Neural Architecture for Recommendation System

Currently, there starts a research trend to leverage neural architecture for recommendation systems. Though several deep recommender models are proposed, most methods are too simple to characterize users' complex preference. In this paper, for a fine-grain analysis, users' ratings are explained from multiple perspectives, based on which, we propose our neural architecture. Specifically, our model employs several sequential stages to encode the user and item into hidden representations. In one stage, the user and item are represented from multiple perspectives and in each perspective, the representations of user and item put attentions to each other. Last, we metric the output representations of final stage to approach the users' rating. Extensive experiments demonstrate that our method achieves substantial improvements against baselines.

cs.IR↗

arXiv2018

Hungarian Layer: Logics Empowered Neural Architecture

Neural architecture is a purely numeric framework, which fits the data as a continuous function. However, lacking of logic flow (e.g. \textit{if, for, while}), traditional algorithms (e.g. \textit{Hungarian algorithm, A$^*$ searching, decision tress algorithm}) could not be embedded into this paradigm, which limits the theories and applications. In this paper, we reform the calculus graph as a dynamic process, which is guided by logic flow. Within our novel methodology, traditional algorithms could empower numerical neural network. Specifically, regarding the subject of sentence matching, we reformulate this issue as the form of task-assignment, which is solved by Hungarian algorithm. First, our model applies BiLSTM to parse the sentences. Then Hungarian layer aligns the matching positions. Last, we transform the matching results for soft-max regression by another BiLSTM. Extensive experiments show that our model outperforms other state-of-the-art baselines substantially.

cs.CL↗

arXiv2018

Reconstructing a cascade from temporal observations

Given a subset of active nodes in a network can we re- construct the cascade that has generated these observa- tions? This is a problem that has been studied in the literature, but here we focus in the case that tempo- ral information is available about the active nodes. In particular, we assume that in addition to the subset of active nodes we also know their activation time. We formulate this cascade-reconstruction problem as a variant of a Steiner-tree problem: we ask to find a tree that spans all reported active nodes while satisfying temporal-consistency constraints. We present three approximation algorithms. The best algorithm in terms of quality achieves a O(\sqrt{k})-approximation guarantee, where k is the number of active nodes, while the most efficient algorithm has linearithmic running time, making it scalable to very large graphs. We evaluate our algorithms on real-world networks with both simulated and real cascades. Our results in- dicate that utilizing the available temporal information allows for more accurate cascade reconstruction. Fur- thermore, our objective leads to finding the "backbone" of the cascade and it gives solutions of high precision.

cs.SI↗

arXiv2018

Convexification of Neural Graph

Traditionally, most complex intelligence architectures are extremely non-convex, which could not be well performed by convex optimization. However, this paper decomposes complex structures into three types of nodes: operators, algorithms and functions. Iteratively, propagating from node to node along edge, we prove that "regarding the tree-structured neural graph, it is nearly convex in each variable, when the other variables are fixed." In fact, the non-convex properties stem from circles and functions, which could be transformed to be convex with our proposed \textit{\textbf{scale mechanism}}. Experimentally, we justify our theoretical analysis by two practical applications.

cs.LG↗

arXiv2018

Intelligence Graph

In fact, there exist three genres of intelligence architectures: logics (e.g. \textit{Random Forest, A$^*$ Searching}), neurons (e.g. \textit{CNN, LSTM}) and probabilities (e.g. \textit{Naive Bayes, HMM}), all of which are incompatible to each other. However, to construct powerful intelligence systems with various methods, we propose the intelligence graph (short as \textbf{\textit{iGraph}}), which is composed by both of neural and probabilistic graph, under the framework of forward-backward propagation. By the paradigm of iGraph, we design a recommendation model with semantic principle. First, the probabilistic distributions of categories are generated from the embedding representations of users/items, in the manner of neurons. Second, the probabilistic graph infers the distributions of features, in the manner of probabilities. Last, for the recommendation diversity, we perform an expectation computation then conduct a logic judgment, in the manner of logics. Experimentally, we beat the state-of-the-art baselines and verify our conclusions.

cs.AI↗

arXiv2017

SAR: Semantic Analysis for Recommendation

Recommendation system is a common demand in daily life and matrix completion is a widely adopted technique for this task. However, most matrix completion methods lack semantic interpretation and usually result in weak-semantic recommendations. To this end, this paper proposes a $S$emantic $A$nalysis approach for $R$ecommendation systems $(SAR)$, which applies a two-level hierarchical generative process that assigns semantic properties and categories for user and item. $SAR$ learns semantic representations of users/items merely from user ratings on items, which offers a new path to recommendation by semantic matching with the learned representations. Extensive experiments demonstrate $SAR$ outperforms other state-of-the-art baselines substantially.

cs.IR↗

arXiv2017

NDT: Neual Decision Tree Towards Fully Functioned Neural Graph

Though traditional algorithms could be embedded into neural architectures with the proposed principle of \cite{xiao2017hungarian}, the variables that only occur in the condition of branch could not be updated as a special case. To tackle this issue, we multiply the conditioned branches with Dirac symbol (i.e. $\mathbf{1}_{x>0}$), then approximate Dirac symbol with the continuous functions (e.g. $1 - e^{-α|x|}$). In this way, the gradients of condition-specific variables could be worked out in the back-propagation process, approximately, making a fully functioned neural graph. Within our novel principle, we propose the neural decision tree \textbf{(NDT)}, which takes simplified neural networks as decision function in each branch and employs complex neural networks to generate the output in each leaf. Extensive experiments verify our theoretical analysis and demonstrate the effectiveness of our model.

cs.NE↗

arXiv2017

Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms

We present Fashion-MNIST, a new dataset comprising of 28x28 grayscale images of 70,000 fashion products from 10 categories, with 7,000 images per category. The training set has 60,000 images and the test set has 10,000 images. Fashion-MNIST is intended to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking machine learning algorithms, as it shares the same image size, data format and the structure of training and testing splits. The dataset is freely available at https://github.com/zalandoresearch/fashion-mnist

cs.LG↗

arXiv2017

TransG : A Generative Mixture Model for Knowledge Graph Embedding

Recently, knowledge graph embedding, which projects symbolic entities and relations into continuous vector space, has become a new, hot topic in artificial intelligence. This paper addresses a new issue of multiple relation semantics that a relation may have multiple meanings revealed by the entity pairs associated with the corresponding triples, and proposes a novel Gaussian mixture model for embedding, TransG. The new model can discover latent semantics for a relation and leverage a mixture of relation component vectors for embedding a fact triple. To the best of our knowledge, this is the first generative model for knowledge graph embedding, which is able to deal with multiple relation semantics. Extensive experiments show that the proposed model achieves substantial improvements against the state-of-the-art baselines.

cs.CL↗

arXiv2017

From One Point to A Manifold: Knowledge Graph Embedding For Precise Link Prediction

Knowledge graph embedding aims at offering a numerical knowledge representation paradigm by transforming the entities and relations into continuous vector space. However, existing methods could not characterize the knowledge graph in a fine degree to make a precise prediction. There are two reasons: being an ill-posed algebraic system and applying an overstrict geometric form. As precise prediction is critical, we propose an manifold-based embedding principle (\textbf{ManifoldE}) which could be treated as a well-posed algebraic system that expands the position of golden triples from one point in current models to a manifold in ours. Extensive experiments show that the proposed models achieve substantial improvements against the state-of-the-art baselines especially for the precise prediction task, and yet maintain high efficiency.

cs.AI↗