In this paper we provide a comprehensive introduction to knowledge graphs,
which have recently garnered significant attention from both industry and
academia in scenarios that require exploiting diverse, dynamic, large-scale
collections of data. After some opening remarks, we motivate and contrast
various graph-based data models and query languages that are used for knowledge
graphs. We discuss the roles of schema, identity, and context in knowledge
graphs. We explain how knowledge can be represented and extracted using a
combination of deductive and inductive techniques. We summarise methods for the
creation, enrichment, quality assessment, refinement, and publication of
knowledge graphs. We provide an overview of prominent open knowledge graphs and
enterprise knowledge graphs, their applications, and how they use the
aforementioned techniques. We conclude with high-level future research
directions for knowledge graphs.

Knowledge Graphs

How do humans recognize the action "opening a book" ? We argue that there are two important cues: modeling temporal shape dynamics and modeling functional relationships between humans and objects. In this paper, we propose to represent videos as space-time region graphs which capture these two important cues. Our graph nodes are defined by the object region proposals from different frames in a long range video. These nodes are connected by two types of relations: (i) similarity relations capturing the long range dependencies between correlated objects and (ii) spatial-temporal relations capturing the interactions between nearby objects. We perform reasoning on this graph representation via Graph Convolutional Networks. We achieve state-of-the-art results on both Charades and Something-Something datasets. Especially for Charades, we obtain a huge 4.4% gain when our model is applied in complex environments.

Videos as Space-Time Region Graphs.

Graph Neural Networks (GNNs) have recently become increasingly popular due to their ability to learn complex systems of relations or interactions arising in a broad spectrum of problems ranging from biology and particle physics to social networks and recommendation systems Despite the plethora of different models for deep learning on graphs, few approaches have been proposed thus far for dealing with graphs that present some sort of dynamic nature (eg evolving features or connectivity over time) In this paper, we present Temporal Graph Networks (TGNs), a generic, efficient framework for deep learning on dynamic graphs represented as sequences of timed events Thanks to a novel combination of memory modules and graph-based operators, TGNs are able to significantly outperform previous approaches being at the same time more computationally efficient We furthermore show that several previous models for learning on dynamic graphs can be cast as specific instances of our framework We perform a detailed ablation study of different components of our framework and devise the best configuration that achieves state-of-the-art performance on several transductive and inductive prediction tasks for dynamic graphs

Temporal Graph Networks for Deep Learning on Dynamic Graphs.

Time is an important feature in many applications involving events that occur synchronously and/or asynchronously. To effectively consume time information, recent studies have focused on designing new architectures. In this paper, we take an orthogonal but complementary approach by providing a model-agnostic vector representation for time, called Time2Vec, that can be easily imported into many existing and future architectures and improve their performances. We show on a range of models and problems that replacing the notion of time with its Time2Vec representation improves the performance of the final model.

/pdf/time2vec-learning-a-vector-representation-of-time-4rb3ehlj4p.pdf

Time2Vec: Learning a Vector Representation of Time

Dynamic networks are used in a wide range of fields, including social network analysis, recommender systems and epidemiology. Representing complex networks as structures changing over time allow network models to leverage not only structural but also temporal patterns. However, as dynamic network literature stems from diverse fields and makes use of inconsistent terminology, it is challenging to navigate. Meanwhile, graph neural networks (GNNs) have gained a lot of attention in recent years for their ability to perform well on a range of network science tasks, such as link prediction and node classification. Despite the popularity of graph neural networks and the proven benefits of dynamic network models, there has been little focus on graph neural networks for dynamic networks. To address the challenges resulting from the fact that this research crosses diverse fields as well as to survey dynamic graph neural networks, this work is split into two main parts. First, to address the ambiguity of the dynamic network terminology we establish a foundation of dynamic networks with consistent, detailed terminology and notation. Second, we present a comprehensive survey of dynamic graph neural network models using the proposed terminology.

Foundations and Modeling of Dynamic Networks Using Dynamic Graph Neural Networks: A Survey

Graphs arise naturally in many real-world applications including social networks, recommender systems, ontologies, biology, and computational finance. Traditionally, machine learning models for graphs have been mostly designed for static graphs. However, many applications involve evolving graphs. This introduces important challenges for learning and inference since nodes, attributes, and edges change over time. In this survey, we review the recent advances in representation learning for dynamic graphs, including dynamic knowledge graphs. We describe existing models from an encoder-decoder perspective, categorize these encoders and decoders based on the techniques they employ, and analyze the approaches in each category. We also review several prominent applications and widely used datasets and highlight directions for future research.

/pdf/representation-learning-for-dynamic-graphs-a-survey-4m96gz6yb9.pdf

Representation Learning for Dynamic Graphs: A Survey

Graphs arise naturally in many real-world applications including social networks, recommender systems, ontologies, biology, and computational finance. Traditionally, machine learning models for graphs have been mostly designed for static graphs. However, many applications involve evolving graphs. This introduces important challenges for learning and inference since nodes, attributes, and edges change over time. In this survey, we review the recent advances in representation learning for dynamic graphs, including dynamic knowledge graphs. We describe existing models from an encoder-decoder perspective, categorize these encoders and decoders based on the techniques they employ, and analyze the approaches in each category. We also review several prominent applications and widely used datasets, and highlight directions for future research.

Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey.

The input to the token swapping problem is a graph with vertices $v_1, v_2, \ldots, v_n$, and $n$ tokens with labels $1, 2, \ldots, n$, one on each vertex. The goal is to get token $i$ to vertex $v_i$ for all $i= 1, \ldots, n$ using a minimum number of swaps, where a swap exchanges the tokens on the endpoints of an edge. We present some results about token swapping on a tree, also known as "sorting with a transposition tree": 
1. An optimum swap sequence may need to perform a swap on a leaf vertex that has the correct token (a "happy leaf"), disproving a conjecture of Vaughan. 
2. Any algorithm that fixes happy leaves -- as all known approximation algorithms for the problem do -- has approximation factor at least $4/3$. Furthermore, the two best-known 2-approximation algorithms have approximation factor exactly 2. 
3. A generalized problem -- weighted coloured token swapping -- is NP-complete on trees, even when they are restricted to be subdivided stars, but solvable in polynomial time on paths and stars. In this version, tokens and vertices have colours, and colours have weights. The goal is to get every token to a vertex of the same colour, and the cost of a swap is the sum of the weights of the two tokens involved.

Token Swapping on Trees

We consider problems in which a simple path of fixed length, in an undirected graph, is to be shifted from a start position to a goal position by moves that add an edge to either end of the path and remove an edge from the other end. We show that this problem may be solved in linear time in trees, and is fixed-parameter tractable when parameterized either by the cyclomatic number of the input graph or by the length of the path. However, it is $\mathsf {PSPACE}$-complete for paths of unbounded length in graphs of bounded bandwidth.

/pdf/reconfiguring-undirected-paths-2oll1p88ak.pdf

Kshitij Jain

Papers

Representation Learning for Dynamic Graphs: A Survey

Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey.

Representation Learning for Dynamic Graphs: A Survey

Token Swapping on Trees

Reconfiguring Undirected Paths