arXiv subjects

Yixin Cao

Publications and source records attributed to Yixin Cao.

At least 163 records · Page 9Linked to original sources

arXiv2020

Recognizing (Unit) Interval Graphs by Zigzag Graph Searches

Corneil, Olariu, and Stewart [SODA 1998; SIAM Journal on Discrete Mathematics 2009] presented a recognition algorithm for interval graphs by six graph searches. Li and Wu [Discrete Mathematics \& Theoretical Computer Science 2014] simplified it to only four. The great simplicity of the latter algorithm is however eclipsed by the complicated and long proofs. The main purpose of this paper is to present a new and significantly short proof for Li and Wu's algorithm, as well as a simpler implementation. We also give a self-contained simpler interpretation of the recognition algorithm of Corneil [Discrete Applied Mathematics 2004] for unit interval graphs, based on three sweeps of graph searches. Moreover, we show that two sweeps are already sufficient. Toward the proofs of the main results, we make several new structural observations that might be of independent interests.

cs.DS↗

arXiv2020

Tree-Augmented Cross-Modal Encoding for Complex-Query Video Retrieval

The rapid growth of user-generated videos on the Internet has intensified the need for text-based video retrieval systems. Traditional methods mainly favor the concept-based paradigm on retrieval with simple queries, which are usually ineffective for complex queries that carry far more complex semantics. Recently, embedding-based paradigm has emerged as a popular approach. It aims to map the queries and videos into a shared embedding space where semantically-similar texts and videos are much closer to each other. Despite its simplicity, it forgoes the exploitation of the syntactic structure of text queries, making it suboptimal to model the complex queries. To facilitate video retrieval with complex queries, we propose a Tree-augmented Cross-modal Encoding method by jointly learning the linguistic structure of queries and the temporal representation of videos. Specifically, given a complex user query, we first recursively compose a latent semantic tree to structurally describe the text query. We then design a tree-augmented query encoder to derive structure-aware query representation and a temporal attentive video encoder to model the temporal characteristics of videos. Finally, both the query and videos are mapped into a joint embedding space for matching and ranking. In this approach, we have a better understanding and modeling of the complex queries, thereby achieving a better video retrieval performance. Extensive experiments on large scale video retrieval benchmark datasets demonstrate the effectiveness of our approach.

cs.CV↗

arXiv2020

Expertise Style Transfer: A New Task Towards Better Communication between Experts and Laymen

The curse of knowledge can impede communication between experts and laymen. We propose a new task of expertise style transfer and contribute a manually annotated dataset with the goal of alleviating such cognitive biases. Solving this task not only simplifies the professional language, but also improves the accuracy and expertise level of laymen descriptions using simple words. This is a challenging task, unaddressed in previous work, as it requires the models to have expert intelligence in order to modify text with a deep understanding of domain knowledge and structures. We establish the benchmark performance of five state-of-the-art models for style transfer and text simplification. The results demonstrate a significant gap between machine and human performance. We also discuss the challenges of automatic evaluation, to provide insights into future research directions. The dataset is publicly available at https://srhthu.github.io/expertise-style-transfer.

cs.CL↗

arXiv2020

Enumerating Maximal Induced Subgraphs

Given a graph $G$, the maximal induced subgraphs problem asks to enumerate all maximal induced subgraphs of $G$ that belong to a certain hereditary graph class. While its optimization version, known as the minimum vertex deletion problem in literature, has been intensively studied, enumeration algorithms are known for a few simple graph classes, e.g., independent sets, cliques, and forests, until very recently [Conte and Uno, STOC 2019]. There is also a connected variation of this problem, where one is concerned with only those induced subgraphs that are connected. We introduce two new approaches, which enable us to develop algorithms that solve both variations for a number of important graph classes. A general technique that has been proved very powerful in enumeration algorithms is to build a solution map, i.e., a multiple digraph on all the solutions of the problem, and the key of this approach is to make the solution map strongly connected, so that a simple traversal of the solution map solves the problem. We introduce retaliation-free paths to certificate strong connectedness of the solution map we build. Generalizing the idea of Cohen, Kimelfeld, and Sagiv [JCSS 2008], we introduce the $t$-restricted version, $t$ being a positive integer, of the maximal (connected) induced subgraphs problem, and show that it is equivalent to the original problem in terms of solvability in incremental polynomial time. Moreover, we give reductions between the two variations, so that it suffices to solve one of the variations for each class we study. Our work also leads to direct and simpler proofs of several important known results.

cs.DS↗

arXiv2020

Polynomial Kernels for Paw-free Edge Modification Problems

Let $H$ be a fixed graph. Given a graph $G$ and an integer $k$, the $H$-free edge modification problem asks whether it is possible to modify at most $k$ edges in $G$ to make it $H$-free. Sandeep and Sivadasan (IPEC 2015) asks whether the paw-free completion problem and the paw-free edge deletion problem admit polynomial kernels. We answer both questions affirmatively by presenting, respectively, $O(k)$-vertex and $O(k^4)$-vertex kernels for them. This is part of an ongoing program that aims at understanding compressibility of $H$-free edge modification problems.

cs.DS↗

arXiv2020

Reinforced Negative Sampling over Knowledge Graph for Recommendation

Properly handling missing data is a fundamental challenge in recommendation. Most present works perform negative sampling from unobserved data to supply the training of recommender models with negative signals. Nevertheless, existing negative sampling strategies, either static or adaptive ones, are insufficient to yield high-quality negative samples --- both informative to model training and reflective of user real needs. In this work, we hypothesize that item knowledge graph (KG), which provides rich relations among items and KG entities, could be useful to infer informative and factual negative samples. Towards this end, we develop a new negative sampling model, Knowledge Graph Policy Network (KGPolicy), which works as a reinforcement learning agent to explore high-quality negatives. Specifically, by conducting our designed exploration operations, it navigates from the target positive interaction, adaptively receives knowledge-aware negative signals, and ultimately yields a potential negative item to train the recommender. We tested on a matrix factorization (MF) model equipped with KGPolicy, and it achieves significant improvements over both state-of-the-art sampling methods like DNS and IRGAN, and KG-enhanced recommender models like KGAT. Further analyses from different angles provide insights of knowledge-aware sampling. We release the codes and datasets at https://github.com/xiangwang1223/kgpolicy.

cs.IR↗

arXiv2019

Characterization and Linear-time Recognition of Paired Threshold Graphs

In a paired threshold graph, each vertex has a weight, and two vertices are adjacent if their weight sum is large enough and their weight difference is small enough. It generalizes threshold graphs and unit interval graphs, both very well studied. We present a vertex ordering characterization of this graph class, which enables us to prove that it is a subclass of interval graphs. Further study of clique paths of paired threshold graphs leads to a simple linear-time recognition algorithm for the class.

cs.DS↗

arXiv2019

Low-Resource Name Tagging Learned with Weakly Labeled Data

Name tagging in low-resource languages or domains suffers from inadequate training data. Existing work heavily relies on additional information, while leaving those noisy annotations unexplored that extensively exist on the web. In this paper, we propose a novel neural model for name tagging solely based on weakly labeled (WL) data, so that it can be applied in any low-resource settings. To take the best advantage of all WL sentences, we split them into high-quality and noisy portions for two modules, respectively: (1) a classification module focusing on the large portion of noisy data can efficiently and robustly pretrain the tag classifier by capturing textual context semantics; and (2) a costly sequence labeling module focusing on high-quality data utilizes Partial-CRFs with non-entity sampling to achieve global optimum. Two modules are combined via shared parameters. Extensive experiments involving five low-resource languages and fine-grained food domain demonstrate our superior performance (6% and 7.8% F1 gains on average) as well as efficiency.

cs.CL↗

arXiv2019

Multi-Channel Graph Neural Network for Entity Alignment

Entity alignment typically suffers from the issues of structural heterogeneity and limited seed alignments. In this paper, we propose a novel Multi-channel Graph Neural Network model (MuGNN) to learn alignment-oriented knowledge graph (KG) embeddings by robustly encoding two KGs via multiple channels. Each channel encodes KGs via different relation weighting schemes with respect to self-attention towards KG completion and cross-KG attention for pruning exclusive entities respectively, which are further combined via pooling techniques. Moreover, we also infer and transfer rule knowledge for completing two KGs consistently. MuGNN is expected to reconcile the structural differences of two KGs, and thus make better use of seed alignments. Extensive experiments on five publicly available datasets demonstrate our superior performance (5% Hits@1 up on average).

cs.CL↗

arXiv2019

Who, Where, and What to Wear? Extracting Fashion Knowledge from Social Media

Fashion knowledge helps people to dress properly and addresses not only physiological needs of users, but also the demands of social activities and conventions. It usually involves three mutually related aspects of: occasion, person and clothing. However, there are few works focusing on extracting such knowledge, which will greatly benefit many downstream applications, such as fashion recommendation. In this paper, we propose a novel method to automatically harvest fashion knowledge from social media. We unify three tasks of occasion, person and clothing discovery from multiple modalities of images, texts and metadata. For person detection and analysis, we use the off-the-shelf tools due to their flexibility and satisfactory performance. For clothing recognition and occasion prediction, we unify the two tasks by using a contextualized fashion concept learning module, which captures the dependencies and correlations among different fashion concepts. To alleviate the heavy burden of human annotations, we introduce a weak label modeling module which can effectively exploit machine-labeled data, a complementary of clean data. In experiments, we contribute a benchmark dataset and conduct extensive experiments from both quantitative and qualitative perspectives. The results demonstrate the effectiveness of our model in fashion concept prediction, and the usefulness of extracted knowledge with comprehensive analysis.

cs.CV↗

arXiv2019

Improving Neural Relation Extraction with Implicit Mutual Relations

Relation extraction (RE) aims at extracting the relation between two entities from the text corpora. It is a crucial task for Knowledge Graph (KG) construction. Most existing methods predict the relation between an entity pair by learning the relation from the training sentences, which contain the targeted entity pair. In contrast to existing distant supervision approaches that suffer from insufficient training corpora to extract relations, our proposal of mining implicit mutual relation from the massive unlabeled corpora transfers the semantic information of entity pairs into the RE model, which is more expressive and semantically plausible. After constructing an entity proximity graph based on the implicit mutual relations, we preserve the semantic relations of entity pairs via embedding each vertex of the graph into a low-dimensional space. As a result, we can easily and flexibly integrate the implicit mutual relations and other entity information, such as entity types, into the existing RE methods. Our experimental results on a New York Times and another Google Distant Supervision datasets suggest that our proposed neural RE framework provides a promising improvement for the RE task, and significantly outperforms the state-of-the-art methods. Moreover, the component for mining implicit mutual relations is so flexible that can help to improve the performance of both CNN-based and RNN-based RE models significant.

cs.CL↗

arXiv2019

KGAT: Knowledge Graph Attention Network for Recommendation

To provide more accurate, diverse, and explainable recommendation, it is compulsory to go beyond modeling user-item interactions and take side information into account. Traditional methods like factorization machine (FM) cast it as a supervised learning problem, which assumes each interaction as an independent instance with side information encoded. Due to the overlook of the relations among instances or items (e.g., the director of a movie is also an actor of another movie), these methods are insufficient to distill the collaborative signal from the collective behaviors of users. In this work, we investigate the utility of knowledge graph (KG), which breaks down the independent interaction assumption by linking items with their attributes. We argue that in such a hybrid structure of KG and user-item graph, high-order relations --- which connect two items with one or multiple linked attributes --- are an essential factor for successful recommendation. We propose a new method named Knowledge Graph Attention Network (KGAT) which explicitly models the high-order connectivities in KG in an end-to-end fashion. It recursively propagates the embeddings from a node's neighbors (which can be users, items, or attributes) to refine the node's embedding, and employs an attention mechanism to discriminate the importance of the neighbors. Our KGAT is conceptually advantageous to existing KG-based recommendation methods, which either exploit high-order relations by extracting paths or implicitly modeling them with regularization. Empirical results on three public benchmarks show that KGAT significantly outperforms state-of-the-art methods like Neural FM and RippleNet. Further studies verify the efficacy of embedding propagation for high-order relation modeling and the interpretability benefits brought by the attention mechanism.

cs.LG↗

arXiv2019

Graph Searches and Their End Vertices

Graph search, the process of visiting vertices in a graph in a specific order, has demonstrated magical powers in many important algorithms. But a systematic study was only initiated by Corneil et al.~a decade ago, and only by then we started to realize how little we understand it. Even the apparently naïve question "which vertex can be the last visited by a graph search algorithm," known as the end vertex problem, turns out to be quite elusive. We give a full picture of all maximum cardinality searches on chordal graphs, which implies a polynomial-time algorithm for the end vertex problem of maximum cardinality search. It is complemented by a proof of NP-completeness of the same problem on weakly chordal graphs. We also show linear-time algorithms for deciding end vertices of breadth-first searches on interval graphs, and end vertices of lexicographic depth-first searches on chordal graphs. Finally, we present $2^n\cdot n^{O(1)}$-time algorithms for deciding the end vertices of breadth-first searches, depth-first searches, maximum cardinality searches, and maximum neighborhood searches on general graphs.

cs.DS↗

arXiv2019

Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences

Incorporating knowledge graph (KG) into recommender system is promising in improving the recommendation accuracy and explainability. However, existing methods largely assume that a KG is complete and simply transfer the "knowledge" in KG at the shallow level of entity raw data or embeddings. This may lead to suboptimal performance, since a practical KG can hardly be complete, and it is common that a KG has missing facts, relations, and entities. Thus, we argue that it is crucial to consider the incomplete nature of KG when incorporating it into recommender system. In this paper, we jointly learn the model of recommendation and knowledge graph completion. Distinct from previous KG-based recommendation methods, we transfer the relation information in KG, so as to understand the reasons that a user likes an item. As an example, if a user has watched several movies directed by (relation) the same person (entity), we can infer that the director relation plays a critical role when the user makes the decision, thus help to understand the user's preference at a finer granularity. Technically, we contribute a new translation-based recommendation model, which specially accounts for various preferences in translating a user to an item, and then jointly train it with a KG completion model by combining several transfer schemes. Extensive experiments on two benchmark datasets show that our method outperforms state-of-the-art KG-based recommendation methods. Further analysis verifies the positive effect of joint training on both tasks of recommendation and KG completion, and the advantage of our model in understanding user preference. We publish our project at https://github.com/TaoMiner/joint-kg-recommender.

cs.IR↗

arXiv2018

Joint Representation Learning of Cross-lingual Words and Entities via Attentive Distant Supervision

Joint representation learning of words and entities benefits many NLP tasks, but has not been well explored in cross-lingual settings. In this paper, we propose a novel method for joint representation learning of cross-lingual words and entities. It captures mutually complementary knowledge, and enables cross-lingual inferences among knowledge bases and texts. Our method does not require parallel corpora, and automatically generates comparable data via distant supervision using multi-lingual knowledge bases. We utilize two types of regularizers to align cross-lingual words and entities, and design knowledge attention and cross-lingual attention to further reduce noises. We conducted a series of experiments on three tasks: word translation, entity relatedness, and cross-lingual entity linking. The results, both qualitatively and quantitatively, demonstrate the significance of our method.

cs.CL↗

arXiv2018

Neural Collective Entity Linking

Entity Linking aims to link entity mentions in texts to knowledge bases, and neural models have achieved recent success in this task. However, most existing methods rely on local contexts to resolve entities independently, which may usually fail due to the data sparsity of local information. To address this issue, we propose a novel neural model for collective entity linking, named as NCEL. NCEL applies Graph Convolutional Network to integrate both local contextual features and global coherence information for entity linking. To improve the computation efficiency, we approximately perform graph convolution on a subgraph of adjacent entity mentions instead of those in the entire text. We further introduce an attention scheme to improve the robustness of NCEL to data noise and train the model on Wikipedia hyperlinks to avoid overfitting and domain bias. In experiments, we evaluate NCEL on five publicly available datasets to verify the linking performance as well as generalization ability. We also conduct an extensive analysis of time complexity, the impact of key modules, and qualitative results, which demonstrate the effectiveness and efficiency of our proposed method.

cs.CL↗

arXiv2018

Explainable Reasoning over Knowledge Graphs for Recommendation

Incorporating knowledge graph into recommender systems has attracted increasing attention in recent years. By exploring the interlinks within a knowledge graph, the connectivity between users and items can be discovered as paths, which provide rich and complementary information to user-item interactions. Such connectivity not only reveals the semantics of entities and relations, but also helps to comprehend a user's interest. However, existing efforts have not fully explored this connectivity to infer user preferences, especially in terms of modeling the sequential dependencies within and holistic semantics of a path. In this paper, we contribute a new model named Knowledge-aware Path Recurrent Network (KPRN) to exploit knowledge graph for recommendation. KPRN can generate path representations by composing the semantics of both entities and relations. By leveraging the sequential dependencies within a path, we allow effective reasoning on paths to infer the underlying rationale of a user-item interaction. Furthermore, we design a new weighted pooling operation to discriminate the strengths of different paths in connecting a user with an item, endowing our model with a certain level of explainability. We conduct extensive experiments on two datasets about movie and music, demonstrating significant improvements over state-of-the-art solutions Collaborative Knowledge Base Embedding and Neural Factorization Machine.

cs.IR↗

arXiv2018

Local Coloring and its Complexity

A $k$-coloring of a graph is an assignment of integers between $1$ and $k$ to vertices in the graph such that the endpoints of each edge receive different numbers. We study a local variation of the coloring problem, which imposes further requirements on three vertices: We are not allowed to use two consecutive numbers for a path on three vertices, or three consecutive numbers for a cycle on three vertices. Given a graph $G$ and a positive integer $k$, the local coloring problem asks for whether $G$ admits a local $k$-coloring. We give a characterization of graphs admitting local $3$-coloring, which implies a simple polynomial-time algorithm for it. Li et al.~[\href{http://dx.doi.org/10.1016/j.ipl.2017.09.013} {Inf.~Proc.~Letters 130 (2018)}] recently showed it is NP-hard when $k$ is an odd number of at least $5$, or $k = 4$. We show that it is NP-hard when $k$ is any fixed even number at least $6$, thereby completing the complexity picture of this problem. We close the paper with a short remark on local colorings of perfect graphs.

math.CO↗