arXiv subjects

Kyomin Jung

Publications and source records attributed to Kyomin Jung.

102 records · Page 6Linked to original sources

arXiv2018

AttnConvnet at SemEval-2018 Task 1: Attention-based Convolutional Neural Networks for Multi-label Emotion Classification

In this paper, we propose an attention-based classifier that predicts multiple emotions of a given sentence. Our model imitates human's two-step procedure of sentence understanding and it can effectively represent and classify sentences. With emoji-to-meaning preprocessing and extra lexicon utilization, we further improve the model performance. We train and evaluate our model with data provided by SemEval-2018 task 1-5, each sentence of which has several labels among 11 given sentiments. Our model achieves 5-th/1-th rank in English/Spanish respectively.

cs.CL↗

arXiv2018

Learning to Rank Question-Answer Pairs using Hierarchical Recurrent Encoder with Latent Topic Clustering

In this paper, we propose a novel end-to-end neural architecture for ranking candidate answers, that adapts a hierarchical recurrent neural network and a latent topic clustering module. With our proposed model, a text is encoded to a vector representation from an word-level to a chunk-level to effectively capture the entire meaning. In particular, by adapting the hierarchical structure, our model shows very small performance degradations in longer text comprehension while other state-of-the-art recurrent neural network models suffer from it. Additionally, the latent topic clustering module extracts semantic information from target samples. This clustering module is useful for any text related tasks by allowing each data sample to find its nearest topic cluster, thus helping the neural network model analyze the entire data. We evaluate our models on the Ubuntu Dialogue Corpus and consumer electronic domain question answering dataset, which is related to Samsung products. The proposed model shows state-of-the-art results for ranking question-answer pairs.

cs.CL↗

arXiv2017

Synonym Discovery with Etymology-based Word Embeddings

We propose a novel approach to learn word embeddings based on an extended version of the distributional hypothesis. Our model derives word embedding vectors using the etymological composition of words, rather than the context in which they appear. It has the strength of not requiring a large text corpus, but instead it requires reliable access to etymological roots of words, making it specially fit for languages with logographic writing systems. The model consists on three steps: (1) building an etymological graph, which is a bipartite network of words and etymological roots, (2) obtaining the biadjacency matrix of the etymological graph and reducing its dimensionality, (3) using columns/rows of the resulting matrices as embedding vectors. We test our model in the Chinese and Sino-Korean vocabularies. Our graphs are formed by a set of 117,000 Chinese words, and a set of 135,000 Sino-Korean words. In both cases we show that our model performs well in the task of synonym discovery.

cs.CL↗

arXiv2017

Efficient Transfer Learning Schemes for Personalized Language Modeling using Recurrent Neural Network

In this paper, we propose an efficient transfer leaning methods for training a personalized language model using a recurrent neural network with long short-term memory architecture. With our proposed fast transfer learning schemes, a general language model is updated to a personalized language model with a small amount of user data and a limited computing resource. These methods are especially useful for a mobile device environment while the data is prevented from transferring out of the device for privacy purposes. Through experiments on dialogue data in a drama, it is verified that our transfer learning methods have successfully generated the personalized language model, whose output is more similar to the personal language style in both qualitative and quantitative aspects.

cs.CL↗

arXiv2013

Partition-Merge: Distributed Inference and Modularity Optimization

This paper presents a novel meta algorithm, Partition-Merge (PM), which takes existing centralized algorithms for graph computation and makes them distributed and faster. In a nutshell, PM divides the graph into small subgraphs using our novel randomized partitioning scheme, runs the centralized algorithm on each partition separately, and then stitches the resulting solutions to produce a global solution. We demonstrate the efficiency of the PM algorithm on two popular problems: computation of Maximum A Posteriori (MAP) assignment in an arbitrary pairwise Markov Random Field (MRF), and modularity optimization for community detection. We show that the resulting distributed algorithms for these problems essentially run in time linear in the number of nodes in the graph, and perform as well -- or even better -- than the original centralized algorithm as long as the graph has geometric structures. Here we say a graph has geometric structures, or polynomial growth property, when the number of nodes within distance r of any given node grows no faster than a polynomial function of r. More precisely, if the centralized algorithm is a C-factor approximation with constant C \ge 1, the resulting distributed algorithm is a (C+δ)-factor approximation for any small δ>0; but if the centralized algorithm is a non-constant (e.g. logarithmic) factor approximation, then the resulting distributed algorithm becomes a constant factor approximation. For general graphs, we compute explicit bounds on the loss of performance of the resulting distributed algorithm with respect to the centralized algorithm.

cs.DS↗

arXiv2013

Multi-dimensional Parametric Mincuts for Constrained MAP Inference

In this paper, we propose novel algorithms for inferring the Maximum a Posteriori (MAP) solution of discrete pairwise random field models under multiple constraints. We show how this constrained discrete optimization problem can be formulated as a multi-dimensional parametric mincut problem via its Lagrangian dual, and prove that our algorithm isolates all constraint instances for which the problem can be solved exactly. These multiple solutions enable us to even deal with `soft constraints' (higher order penalty functions). Moreover, we propose two practical variants of our algorithm to solve problems with hard constraints. We also show how our method can be applied to solve various constrained discrete optimization problems such as submodular minimization and shortest path computation. Experimental evaluation using the foreground-background image segmentation problem with statistic constraints reveals that our method is faster and its results are closer to the ground truth labellings compared with the popular continuous relaxation based methods.

cs.LG↗

arXiv2013

Efficient Energy Minimization for Enforcing Statistics

Energy minimization algorithms, such as graph cuts, enable the computation of the MAP solution under certain probabilistic models such as Markov random fields. However, for many computer vision problems, the MAP solution under the model is not the ground truth solution. In many problem scenarios, the system has access to certain statistics of the ground truth. For instance, in image segmentation, the area and boundary length of the object may be known. In these cases, we want to estimate the most probable solution that is consistent with such statistics, i.e., satisfies certain equality or inequality constraints. The above constrained energy minimization problem is NP-hard in general, and is usually solved using Linear Programming formulations, which relax the integrality constraints. This paper proposes a novel method that finds the discrete optimal solution of such problems by maximizing the corresponding Lagrangian dual. This method can be applied to any constrained energy minimization problem whose unconstrained version is polynomial time solvable, and can handle multiple, equality or inequality, and linear or non-linear constraints. We demonstrate the efficacy of our method on the foreground/background image segmentation problem, and show that it produces impressive segmentation results with less error, and runs more than 20 times faster than the state-of-the-art LP relaxation based approaches.

cs.CV↗

arXiv2012

IRIE: Scalable and Robust Influence Maximization in Social Networks

Influence maximization is the problem of selecting top $k$ seed nodes in a social network to maximize their influence coverage under certain influence diffusion models. In this paper, we propose a novel algorithm IRIE that integrates a new message passing based influence ranking (IR), and influence estimation (IE) methods for influence maximization in both the independent cascade (IC) model and its extension IC-N that incorporates negative opinion propagations. Through extensive experiments, we demonstrate that IRIE matches the influence coverage of other algorithms while scales much better than all other algorithms. Moreover IRIE is more robust and stable than other algorithms both in running time and memory usage for various density of networks and cascade size. It runs up to two orders of magnitude faster than other state-of-the-art algorithms such as PMIA for large networks with tens of millions of nodes and edges, while using only a fraction of memory comparing with PMIA.

cs.SI↗

arXiv2012

Stability of the Max-Weight Protocol in Adversarial Wireless Networks

In this paper we consider the Max-Weight protocol for routing and scheduling in wireless networks under an adversarial model. This protocol has received a significant amount of attention dating back to the papers of Tassiulas and Ephremides. In particular, this protocol is known to be throughput-optimal whenever the traffic patterns and propagation conditions are governed by a stationary stochastic process. However, the standard proof of throughput optimality (which is based on the negative drift of a quadratic potential function) does not hold when the traffic patterns and the edge capacity changes over time are governed by an arbitrary adversarial process. Such an environment appears frequently in many practical wireless scenarios when the assumption that channel conditions are governed by a stationary stochastic process does not readily apply. In this paper we prove that even in the above adversarial setting, the Max-Weight protocol keeps the queues in the network stable (i.e. keeps the queue sizes bounded) whenever this is feasible by some routing and scheduling algorithm. However, the proof is somewhat more complex than the negative potential drift argument that applied in the stationary case. Our proof holds for any arbitrary interference relationships among edges. We also prove the stability of $\ep$-approximate Max-Weight under the adversarial model. We conclude the paper with a discussion of queue sizes in the adversarial model as well as a set of simulation results.

cs.NI↗

arXiv2009

Distributed Averaging via Lifted Markov Chains

Motivated by applications of distributed linear estimation, distributed control and distributed optimization, we consider the question of designing linear iterative algorithms for computing the average of numbers in a network. Specifically, our interest is in designing such an algorithm with the fastest rate of convergence given the topological constraints of the network. As the main result of this paper, we design an algorithm with the fastest possible rate of convergence using a non-reversible Markov chain on the given network graph. We construct such a Markov chain by transforming the standard Markov chain, which is obtained using the Metropolis-Hastings method. We call this novel transformation pseudo-lifting. We apply our method to graphs with geometry, or graphs with doubling dimension. Specifically, the convergence time of our algorithm (equivalently, the mixing time of our Markov chain) is proportional to the diameter of the network graph and hence optimal. As a byproduct, our result provides the fastest mixing Markov chain given the network topological constraints, and should naturally find their applications in the context of distributed optimization, estimation and control.

cs.IT↗

arXiv2008

Transitive-Closure Spanners

Given a directed graph G = (V,E) and an integer k>=1, a k-transitive-closure-spanner (k-TC-spanner) of G is a directed graph H = (V, E_H) that has (1) the same transitive-closure as G and (2) diameter at most k. These spanners were implicitly studied in access control, data structures, and property testing, and properties of these spanners have been rediscovered over the span of 20 years. The main goal in each of these applications is to obtain the sparsest k-TC-spanners. We bring these diverse areas under the unifying framework of TC-spanners. We initiate the study of approximability of the size of the sparsest k-TC-spanner for a given directed graph. We completely resolve the approximability of 2-TC-spanners, showing that it is Theta(log n) unless P = NP. For k>2, we present a polynomial-time algorithm that finds a k-TC-spanner with size within O((n log n)^{1-1/k}) of the optimum. Our algorithmic techniques also yield algorithms with the best-known approximation ratio for well-studied problems on directed spanners when k>3: DIRECTED k-SPANNER, CLIENT/SERVER DIRECTED k-SPANNER, and k-DIAMETER SPANNING SUBGRAPH. For constant k>=3, we show that the size of the sparsest k-TC-spanner is hard to approximate with 2^{log^{1-eps} n} ratio unless NP \subseteq DTIME(n^{polylog n}}). Finally, we study the size of the sparsest k-TC-spanners for H-minor-free graph families. Combining our constructions with our insight that 2-TC-spanners can be used for designing property testers, we obtain a monotonicity tester with O(log^2 n /eps) queries for any poset whose transitive reduction is an H-minor free digraph, improving the Theta(sqrt(n) log n/eps)-queries required of the tester due to Fischer et al (2002).

cs.DS↗

arXiv2007

Local approximate inference algorithms

We present a new local approximation algorithm for computing Maximum a Posteriori (MAP) and log-partition function for arbitrary exponential family distribution represented by a finite-valued pair-wise Markov random field (MRF), say $G$. Our algorithm is based on decomposition of $G$ into {\em appropriately} chosen small components; then computing estimates locally in each of these components and then producing a {\em good} global solution. We show that if the underlying graph $G$ either excludes some finite-sized graph as its minor (e.g. Planar graph) or has low doubling dimension (e.g. any graph with {\em geometry}), then our algorithm will produce solution for both questions within {\em arbitrary accuracy}. We present a message-passing implementation of our algorithm for MAP computation using self-avoiding walk of graph. In order to evaluate the computational cost of this implementation, we derive novel tight bounds on the size of self-avoiding walk tree for arbitrary graph. As a consequence of our algorithmic result, we show that the normalized log-partition function (also known as free-energy) for a class of {\em regular} MRFs will converge to a limit, that is computable to an arbitrary accuracy.

cs.AI↗