arXiv subjects

Luoyi Fu

Publications and source records attributed to Luoyi Fu.

At least 55 records · Page 3Linked to original sources

arXiv2023

PK-Chat: Pointer Network Guided Knowledge Driven Generative Dialogue Model

In the research of end-to-end dialogue systems, using real-world knowledge to generate natural, fluent, and human-like utterances with correct answers is crucial. However, domain-specific conversational dialogue systems may be incoherent and introduce erroneous external information to answer questions due to the out-of-vocabulary issue or the wrong knowledge from the parameters of the neural network. In this work, we propose PK-Chat, a Pointer network guided Knowledge-driven generative dialogue model, incorporating a unified pretrained language model and a pointer network over knowledge graphs. The words generated by PK-Chat in the dialogue are derived from the prediction of word lists and the direct prediction of the external knowledge graph knowledge. Moreover, based on the PK-Chat, a dialogue system is built for academic scenarios in the case of geosciences. Finally, an academic dialogue benchmark is constructed to evaluate the quality of dialogue systems in academic scenarios and the source code is available online.

cs.CL↗

arXiv2022

Temporal Knowledge Graph Reasoning with Historical Contrastive Learning

Temporal knowledge graph, serving as an effective way to store and model dynamic relations, shows promising prospects in event forecasting. However, most temporal knowledge graph reasoning methods are highly dependent on the recurrence or periodicity of events, which brings challenges to inferring future events related to entities that lack historical interaction. In fact, the current moment is often the combined effect of a small part of historical information and those unobserved underlying factors. To this end, we propose a new event forecasting model called Contrastive Event Network (CENET), based on a novel training framework of historical contrastive learning. CENET learns both the historical and non-historical dependency to distinguish the most potential entities that can best match the given query. Simultaneously, it trains representations of queries to investigate whether the current moment depends more on historical or non-historical events by launching contrastive learning. The representations further help train a binary classifier whose output is a boolean mask to indicate related entities in the search space. During the inference process, CENET employs a mask-based strategy to generate the final results. We evaluate our proposed model on five benchmark graphs. The results demonstrate that CENET significantly outperforms all existing methods in most metrics, achieving at least $8.3\%$ relative improvement of Hits@1 over previous state-of-the-art baselines on event-based datasets.

cs.AI↗

arXiv2022

IdeaReader: A Machine Reading System for Understanding the Idea Flow of Scientific Publications

Understanding the origin and influence of the publication's idea is critical to conducting scientific research. However, the proliferation of scientific publications makes it difficult for researchers to sort out the evolution of all relevant literature. To this end, we present IdeaReader, a machine reading system that finds out which papers are most likely to inspire or be influenced by the target publication and summarizes the ideas of these papers in natural language. Specifically, IdeaReader first clusters the references and citations (first-order or higher-order) of the target publication, and the obtained clusters are regarded as the topics that inspire or are influenced by the target publication. It then picks out the important papers from each cluster to extract the skeleton of the idea flow. Finally, IdeaReader automatically generates a literature review of the important papers in each topic. Our system can help researchers gain insight into how scientific ideas flow from the target publication's references to citations by the automatically generated survey and the visualization of idea flow.

cs.DL↗

arXiv2022

INFINITY: A Simple Yet Effective Unsupervised Framework for Graph-Text Mutual Conversion

Graph-to-text (G2T) generation and text-to-graph (T2G) triple extraction are two essential tasks for constructing and applying knowledge graphs. Existing unsupervised approaches turn out to be suitable candidates for jointly learning the two tasks due to their avoidance of using graph-text parallel data. However, they are composed of multiple modules and still require both entity information and relation type in the training process. To this end, we propose INFINITY, a simple yet effective unsupervised approach that does not require external annotation tools or additional parallel information. It achieves fully unsupervised graph-text mutual conversion for the first time. Specifically, INFINITY treats both G2T and T2G as a bidirectional sequence generation task by fine-tuning only one pretrained seq2seq model. A novel back-translation-based framework is then designed to automatically generate continuous synthetic parallel data. To obtain reasonable graph sequences with structural information from source texts, INFINITY employs reward-based training loss by leveraging the advantage of reward augmented maximum likelihood. As a fully unsupervised framework, INFINITY is empirically verified to outperform state-of-the-art baselines for G2T and T2G tasks.

cs.CL↗

arXiv2022

Disentangled Graph Contrastive Learning for Review-based Recommendation

User review data is helpful in alleviating the data sparsity problem in many recommender systems. In review-based recommendation methods, review data is considered as auxiliary information that can improve the quality of learned user/item or interaction representations for the user rating prediction task. However, these methods usually model user-item interactions in a holistic manner and neglect the entanglement of the latent factors behind them, e.g., price, quality, or appearance, resulting in suboptimal representations and reducing interpretability. In this paper, we propose a Disentangled Graph Contrastive Learning framework for Review-based recommendation (DGCLR), to separately model the user-item interactions based on different latent factors through the textual review data. To this end, we first model the distributions of interactions over latent factors from both semantic information in review data and structural information in user-item graph data, forming several factor graphs. Then a factorized message passing mechanism is designed to learn disentangled user/item representations on the factor graphs, which enable us to further characterize the interactions and adaptively combine the predicted ratings from multiple factors via a devised attention mechanism. Finally, we set two factor-wise contrastive learning objectives to alleviate the sparsity issue and model the user/item and interaction features pertinent to each factor more accurately. Empirical results over five benchmark datasets validate the superiority of DGCLR over the state-of-the-art methods. Further analysis is offered to interpret the learned intent factors and rating prediction in DGCLR.

cs.IR↗

arXiv2022

Geometer: Graph Few-Shot Class-Incremental Learning via Prototype Representation

With the tremendous expansion of graphs data, node classification shows its great importance in many real-world applications. Existing graph neural network based methods mainly focus on classifying unlabeled nodes within fixed classes with abundant labeling. However, in many practical scenarios, graph evolves with emergence of new nodes and edges. Novel classes appear incrementally along with few labeling due to its newly emergence or lack of exploration. In this paper, we focus on this challenging but practical graph few-shot class-incremental learning (GFSCIL) problem and propose a novel method called Geometer. Instead of replacing and retraining the fully connected neural network classifer, Geometer predicts the label of a node by finding the nearest class prototype. Prototype is a vector representing a class in the metric space. With the pop-up of novel classes, Geometer learns and adjusts the attention-based prototypes by observing the geometric proximity, uniformity and separability. Teacher-student knowledge distillation and biased sampling are further introduced to mitigate catastrophic forgetting and unbalanced labeling problem respectively. Experimental results on four public datasets demonstrate that Geometer achieves a substantial improvement of 9.46% to 27.60% over state-of-the-art methods.

cs.AI↗

arXiv2022

Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer

Spatio-temporal graph learning is a key method for urban computing tasks, such as traffic flow, taxi demand and air quality forecasting. Due to the high cost of data collection, some developing cities have few available data, which makes it infeasible to train a well-performed model. To address this challenge, cross-city knowledge transfer has shown its promise, where the model learned from data-sufficient cities is leveraged to benefit the learning process of data-scarce cities. However, the spatio-temporal graphs among different cities show irregular structures and varied features, which limits the feasibility of existing Few-Shot Learning (\emph{FSL}) methods. Therefore, we propose a model-agnostic few-shot learning framework for spatio-temporal graph called ST-GFSL. Specifically, to enhance feature extraction by transfering cross-city knowledge, ST-GFSL proposes to generate non-shared parameters based on node-level meta knowledge. The nodes in target city transfer the knowledge via parameter matching, retrieving from similar spatio-temporal characteristics. Furthermore, we propose to reconstruct the graph structure during meta-learning. The graph reconstruction loss is defined to guide structure-aware learning, avoiding structure deviation among different datasets. We conduct comprehensive experiments on four traffic speed prediction benchmarks and the results demonstrate the effectiveness of ST-GFSL compared with state-of-the-art methods.

cs.LG↗

arXiv2022

On the Similarity between von Neumann Graph Entropy and Structural Information: Interpretation, Computation, and Applications

The von Neumann graph entropy is a measure of graph complexity based on the Laplacian spectrum. It has recently found applications in various learning tasks driven by networked data. However, it is computational demanding and hard to interpret using simple structural patterns. Due to the close relation between Lapalcian spectrum and degree sequence, we conjecture that the structural information, defined as the Shannon entropy of the normalized degree sequence, might be a good approximation of the von Neumann graph entropy that is both scalable and interpretable. In this work, we thereby study the difference between the structural information and von Neumann graph entropy named as {\em entropy gap}. Based on the knowledge that the degree sequence is majorized by the Laplacian spectrum, we for the first time prove the entropy gap is between $0$ and $\log_2 e$ in any undirected unweighted graphs. Consequently we certify that the structural information is a good approximation of the von Neumann graph entropy that achieves provable accuracy, scalability, and interpretability simultaneously. This approximation is further applied to two entropy-related tasks: network design and graph similarity measure, where novel graph similarity measure and fast algorithms are proposed. Our experimental results on graphs of various scales and types show that the very small entropy gap readily applies to a wide range of graphs and weighted graphs. As an approximation of the von Neumann graph entropy, the structural information is the only one that achieves both high efficiency and high accuracy among the prominent methods. It is at least two orders of magnitude faster than SLaQ with comparable accuracy. Our structural information based methods also exhibit superior performance in two entropy-related tasks.

cs.SI↗

arXiv2021

Scientific X-ray

The rapid development of modern science and technology has spawned rich scientific topics to research and endless production of literature in them. Just like X-ray imaging in medicine, can we intuitively identify the development limit and internal evolution pattern of scientific topic from the relationship of massive knowledge? To answer this question, we collect 71431 seminal articles of topics that cover 16 disciplines and their citation data, and extracts the "idea tree" of each topic to restore the structure of the development of 71431 topic networks from scratch. We define the Knowledge Entropy (KE) metric, and the contribution of high knowledge entropy nodes to increase the depth of the idea tree is regarded as the basis for topic development. By observing "X-ray images" of topics, We find two interesting phenomena: (1) Even though the scale of topics may increase unlimitedly, there is an insurmountable cap of topic development: the depth of the idea tree does not exceed 6 jumps, which coincides with the classical "Six Degrees of Separation"! (2) It is difficult for a single article to contribute more than 3 jumps to the depth of its topic, to this end, the continuing increase in the depth of the idea tree needs to be motivated by the influence relay of multiple high knowledge entropy nodes. Through substantial statistical fits, we derive a unified quantitative relationship between the change in topic depth ${ΔD}^t(v)$ and the change in knowledge entropy over time ${KE}^t\left(v\right)$ of the article $v$ driving the increase in depth in the topic: ${ΔD}^t(v) \approx \log \frac{KE^{t}(v)}{\left(t-t_{0}\right)^{1.8803}}$ , which can effectively portray evolution patterns of topics and predict their development potential. The various phenomena found by scientific x-ray may provide a new paradigm for explaining and understanding the evolution of science and technology.

cs.SI↗

arXiv2021

Exploring the Disproportion Between Scientific Productivity and Knowledge Amount

The pursuit of knowledge is the permanent goal of human beings. Scientific literature, as the major medium that carries knowledge between scientists, exhibits explosive growth during the last century. Despite the frequent use of many tangible measures, such as citation, impact factor and g-index, to quantify the influence of papers from different perspectives based on scientific productivity, it has not yet been well understood how the relationship between scientific productivity and knowledge amount turns out to be, i.e., how the knowledge value of papers and knowledge amount vary with development of the discipline. This raises the question of whether high scientific productivity equals large knowledge amount. Here, building on rich literature on academic conferences and journals, we collect 185 million articles covering 19 disciplines published during 1970 to 2020, and establish citation network research area to represent the knowledge flow from the authors of the article being cited to the authors of the articles that cite it under each specific area. As a result, the structure formed during the evolution of each scientific area can implicitly tells how the knowledge flows between nodes and how it behaves as the number of literature (productivity) increases. By leveraging Structural entropy in structured high-dimensional space and Shannon entropy in unstructured probability space, we propose the Quantitative Index of Knowledge (KQI), which is taken as the subtraction between the two types of entropy, to reflect the extent of disorder difference (knowledge amount) caused by structure (order). With the aid of KQI, we find that, although the published literature shows an explosive growth, the amount of knowledge (KQI) contained in it obviously slows down, and there is a threshold after which the growth of knowledge accelerates...

cs.DL↗

arXiv2020

High-Order Relation Construction and Mining for Graph Matching

Graph matching pairs corresponding nodes across two or more graphs. The problem is difficult as it is hard to capture the structural similarity across graphs, especially on large graphs. We propose to incorporate high-order information for matching large-scale graphs. Iterated line graphs are introduced for the first time to describe such high-order information, based on which we present a new graph matching method, called High-order Graph Matching Network (HGMN), to learn not only the local structural correspondence, but also the hyperedge relations across graphs. We theoretically prove that iterated line graphs are more expressive than graph convolution networks in terms of aligning nodes. By imposing practical constraints, HGMN is made scalable to large-scale graphs. Experimental results on a variety of settings have shown that, HGMN acquires more accurate matching results than the state-of-the-art, verifying our method effectively captures the structural similarity across different graphs.

cs.AI↗

arXiv2020

Neighborhood Matters: Influence Maximization in Social Networks with Limited Access

Influence maximization (IM) aims at maximizing the spread of influence by offering discounts to influential users (called seeding). In many applications, due to user's privacy concern, overwhelming network scale etc., it is hard to target any user in the network as one wishes. Instead, only a small subset of users is initially accessible. Such access limitation would significantly impair the influence spread, since IM often relies on seeding high degree users, which are particularly rare in such a small subset due to the power-law structure of social networks. In this paper, we attempt to solve the limited IM in real-world scenarios by the adaptive approach with seeding and diffusion uncertainty considered. Specifically, we consider fine-grained discounts and assume users accept the discount probabilistically. The diffusion process is depicted by the independent cascade model. To overcome the access limitation, we prove the set-wise friendship paradox (FP) phenomenon that neighbors have higher degree in expectation, and propose a two-stage seeding model with the FP embedded, where neighbors are seeded. On this basis, for comparison we formulate the non-adaptive case and adaptive case, both proven to be NP-hard. In the non-adaptive case, discounts are allocated to users all at once. We show the monotonicity of influence spread w.r.t. discount allocation and design a two-stage coordinate descent framework to decide the discount allocation. In the adaptive case, users are sequentially seeded based on observations of existing seeding and diffusion results. We prove the adaptive submodularity and submodularity of the influence spread function in two stages. Then, a series of adaptive greedy algorithms are proposed with constant approximation ratio.

cs.SI↗

arXiv2020

Can We `Feel' the Temperature of Knowledge? Modelling Scientific Popularity Dynamics via Thermodynamics

Just like everything in the nature, scientific topics flourish and perish. While existing literature well captures article's life-cycle via citation patterns, little is known about how scientific popularity and impact evolves for a specific topic. It would be most intuitive if we could `feel' topic's activity just as we perceive the weather by temperature. Here, we conceive knowledge temperature to quantify topic overall popularity and impact through citation network dynamics. Knowledge temperature includes 2 parts. One part depicts lasting impact by assessing knowledge accumulation with an analogy between topic evolution and isobaric expansion. The other part gauges temporal changes in knowledge structure, an embodiment of short-term popularity, through the rate of entropy change with internal energy, 2 thermodynamic variables approximated via node degree and edge number. Our analysis of representative topics with size ranging from 1000 to over 30000 articles reveals that the key to flourishing is topics' ability in accumulating useful information for future knowledge generation. Topics particularly experience temperature surges when their knowledge structure is altered by influential articles. The spike is especially obvious when there appears a single non-trivial novel research focus or merging in topic structure. Overall, knowledge temperature manifests topics' distinct evolutionary cycles.

cs.SI↗

arXiv2020

Joint Inference on Truth/Rumor and Their Sources in Social Networks

In the contemporary era of information explosion, we are often faced with the mixture of massive \emph{truth} (true information) and \emph{rumor} (false information) flooded over social networks. Under such circumstances, it is very essential to infer whether each claim (e.g., news, messages) is a truth or a rumor, and identify their \emph{sources}, i.e., the users who initially spread those claims. While most prior arts have been dedicated to the two tasks respectively, this paper aims to offer the joint inference on truth/rumor and their sources. Our insight is that a joint inference can enhance the mutual performance on both sides. To this end, we propose a framework named SourceCR, which alternates between two modules, i.e., \emph{credibility-reliability training} for truth/rumor inference and \emph{division-querying} for source detection, in an iterative manner. To elaborate, the former module performs a simultaneous estimation of claim credibility and user reliability by virtue of an Expectation Maximization algorithm, which takes the source reliability outputted from the latter module as the initial input. Meanwhile, the latter module divides the network into two different subnetworks labeled via the claim credibility, and in each subnetwork launches source detection by applying querying of theoretical budget guarantee to the users selected via the estimated reliability from the former module. The proposed SourceCR is provably convergent, and algorithmic implementable with reasonable computational complexity. We empirically validate the effectiveness of the proposed framework in both synthetic and real datasets, where the joint inference leads to an up to 35\% accuracy of credibility gain and 29\% source detection rate gain compared with the separate counterparts.

cs.SI↗

arXiv2019

Evolving Influence Maximization in Evolving Networks

Influence Maximization (IM) aims to maximize the number of people that become aware of a product by finding the `best' set of `seed' users to initiate the product advertisement. Unlike prior arts on static social networks containing fixed number of users, we undertake the first study of IM in more realistic evolving networks with temporally growing topology. The task of evolving IM ({\bfseries EIM}), however, is far more challenging over static cases in the sense that seed selection should consider its impact on future users and the probabilities that users influence one another also evolve over time. We address the challenges through $\mathbb{EIM}$, a newly proposed bandit-based framework that alternates between seed nodes selection and knowledge (i.e., nodes' growing speed and evolving influences) learning during network evolution. Remarkably, $\mathbb{EIM}$ involves three novel components to handle the uncertainties brought by evolution:

cs.SI↗

arXiv2018

BLAG: Bandit On Large Action Set Graph

Information diffusion in social networks facilitates rapid and large-scale propagation of content. However, spontaneous diffusion behavior could also lead to the cascading of sensitive information, which is neglected in prior arts. In this paper, we present the first look into adaptive diffusion of sensitive information, which we aim to prevent from widely spreading without incurring much information loss. We undertake the investigation in networks with partially known topology, meaning that some users' ability of forwarding information is unknown. Formulating the problem into a bandit model, we propose BLAG (Bandit on Large Action set Graph), which adaptively diffuses sensitive information towards users with weak forwarding ability that is learnt from tentative transmissions and corresponding feedbacks. BLAG enjoys a low complexity of O(n), and is provably more efficient in the sense of half regret bound compared with prior learning method. Experiments on synthetic and three real datasets further demonstrate the superiority of BLAG in terms of adaptive diffusion of sensitive information over several baselines, with at least 40 percent less information loss, at least 10 times of learning efficiency given limited learning rounds and significantly postponed cascading of sensitive information.

cs.SI↗

arXiv2017

De-anonymizing Social Networks with Overlapping Community Structure

The advent of social networks poses severe threats on user privacy as adversaries can de-anonymize users' identities by mapping them to correlated cross-domain networks. Without ground-truth mapping, prior literature proposes various cost functions in hope of measuring the quality of mappings. However, there is generally a lacking of rationale behind the cost functions, whose minimizer also remains algorithmically unknown. We jointly tackle above concerns under a more practical social network model parameterized by overlapping communities, which, neglected by prior art, can serve as side information for de-anonymization. Regarding the unavailability of ground-truth mapping to adversaries, by virtue of the Minimum Mean Square Error (MMSE), our first contribution is a well-justified cost function minimizing the expected number of mismatched users over all possible true mappings. While proving the NP-hardness of minimizing MMSE, we validly transform it into the weighted-edge matching problem (WEMP), which, as disclosed theoretically, resolves the tension between optimality and complexity: (i) WEMP asymptotically returns a negligible mapping error in large network size under mild conditions facilitated by higher overlapping strength; (ii) WEMP can be algorithmically characterized via the convex-concave based de-anonymization algorithm (CBDA), perfectly finding the optimum of WEMP. Extensive experiments further confirm the effectiveness of CBDA under overlapping communities, in terms of averagely 90% re-identified users in the rare true cross-domain co-author networks when communities overlap densely, and roughly 70% enhanced re-identification ratio compared to non-overlapping cases.

cs.SI↗

arXiv2017

Maximum Value Matters: Finding Hot Topics in Scholarly Fields

Finding hot topics in scholarly fields can help researchers to keep up with the latest concepts, trends, and inventions in their field of interest. Due to the rarity of complete large-scale scholarly data, earlier studies target this problem based on manual topic extraction from a limited number of domains, with their focus solely on a single feature such as coauthorship, citation relations, and etc. Given the compromised effectiveness of such predictions, in this paper we use a real scholarly dataset from Microsoft Academic Graph, which provides more than 12000 topics in the field of Computer Science (CS), including 1200 venues, 14.4 million authors, 30 million papers and their citation relations over the period of 1950 till now. Aiming to find the topics that will trend in CS area, we innovatively formalize a hot topic prediction problem where, with joint consideration of both inter- and intra-topical influence, 17 different scientific features are extracted for comprehensive description of topic status. By leveraging all those 17 features, we observe good accuracy of topic scale forecasting after 5 and 10 years with R2 values of 0.9893 and 0.9646, respectively. Interestingly, our prediction suggests that the maximum value matters in finding hot topics in scholarly fields, primarily from three aspects: (1) the maximum value of each factor, such as authors' maximum h-index and largest citation number, provides three times the amount of information than the average value in prediction; (2) the mutual influence between the most correlated topics serve as the most telling factor in long-term topic trend prediction, interpreting that those currently exhibiting the maximum growth rates will drive the correlated topics to be hot in the future; (3) we predict in the next 5 years the top 100 fastest growing (maximum growth rate) topics that will potentially get the major attention in CS area.

cs.SI↗