Deep learning on graphs: successes, challenges, and next steps

TL;DR This is the first in a [series of posts] where I will discuss the evolution and future trends in the field of deep learning on graphs.

complex social network

Deep learning on graphs, also known as Geometric deep learning (GDL) [1], Graph representation learning (GRL), or relational inductive biases [2], has recently become one of the hottest topics in machine learning. While early works on graph learning go back at least a decade [3] if not two [4], it is undoubtedly the past few years’ progress that has taken these methods from a niche into the spotlight of the ML community and even to the popular science press (with Quanta Magazine running a series of excellent articles on geometric deep learning for the study of manifoldsdrug discovery, and protein science).

Graphs are powerful mathematical abstractions that can describe complex systems of relations and interactions in fields ranging from biology and high-energy physics to social science and economics. Since the amount of graph-structured data produced in some of these fields nowadays is enormous (prominent examples being social networks like Twitter and Facebook), it is very tempting to try to apply deep learning techniques that have been remarkably successful in other data-rich settings.

There are multiple flavours to graph learning problems that are largely application-dependent. One dichotomy is between node-wise and graph-wise problems, where in the former one tries to predict properties of individual nodes in the graph (e.g. identify malicious users in a social network), while in the latter one tries to make a prediction about the entire graph (e.g. predict solubility of a molecule). Furthermore, like in traditional ML problems, we can distinguish between supervised and unsupervised (or self-supervised) settings, as well as transductive and inductive problems.

Similarly to convolutional neural networks used in image analysis and computer vision, the key to efficient learning on graphs is designing local operations with shared weights that do message passing [5] between every node and its neighbours. A major difference compared to classical deep neural networks dealing with grid-structured data is that on graphs such operations are permutation-invariant, i.e. independent of the order of neighbour nodes, as there is usually no canonical way of ordering them.

Despite their promise and a series of success stories of graph representation learning (among which I can selfishly list the [acquisition by Twitter] of the graph-based fake news detection startup Fabula AI I have founded together with my students), we have not witnessed so far anything close to the smashing success convolutional networks have had in computer vision. In the following, I will try to outline my views on the possible reasons and how the field could progress in the next few years.

**Standardised benchmarks **like ImageNet were surely one of the key success factors of deep learning in computer vision, with some [6] even arguing that data was more important than algorithms for the deep learning revolution. We have nothing similar to ImageNet in scale and complexity in the graph learning community yet. The [Open Graph Benchmark] launched in 2019 is perhaps the first attempt toward this goal trying to introduce challenging graph learning tasks on interesting real-world graph-structured datasets. One of the hurdles is that tech companies producing diverse and rich graphs from their users’ activity are reluctant to share these data due to concerns over privacy laws such as GDPR. A notable exception is Twitter that made a dataset of 160 million tweets with corresponding user engagement graphs available to the research community under certain privacy-preserving restrictions as part of the [RecSys Challenge]. I hope that many companies will follow suit in the future.

**Software libraries **available in the public domain played a paramount role in “democratising” deep learning and making it a popular tool. If until recently, graph learning implementations were primarily a collection of poorly written and scarcely tested code, nowadays there are libraries such as [PyTorch Geometric] or [Deep Graph Library (DGL)] that are professionally written and maintained with the help of industry sponsorship. It is not uncommon to see an implementation of a new graph deep learning architecture weeks after it appears on arxiv.

Scalability is one of the key factors limiting industrial applications that often need to deal with very large graphs (think of Twitter social network with hundreds of millions of nodes and billions of edges) and low latency constraints. The academic research community has until recently almost ignored this aspect, with many models described in the literature completely inadequate for large-scale settings. Furthermore, graphics hardware (GPU), whose happy marriage with classical deep learning architectures was one of the primary forces driving their mutual success, is not necessarily the best fit for graph-structured data. In the long run, we might need specialised hardware for graphs [7].

**Dynamic graphs **are another aspect that is scarcely addressed in the literature. While graphs are a common way of modelling complex systems, such an abstraction is often too simplistic as real-world systems are dynamic and evolve in time. Sometimes it is the temporal behaviour that provides crucial insights about the system. Despite some recent progress, designing graph neural network models capable of efficiently dealing with continuous-time graphs represented as a stream of node- or edge-wise events is still an open research question.

#deep-learning #representation-learning #network-science #graph-neural-networks #geometric-deep-learning #deep learning

What is GEEK

Buddha Community

Deep learning on graphs: successes, challenges, and next steps

Deep learning on graphs: successes, challenges, and next steps

TL;DR This is the first in a [series of posts] where I will discuss the evolution and future trends in the field of deep learning on graphs.

complex social network

Deep learning on graphs, also known as Geometric deep learning (GDL) [1], Graph representation learning (GRL), or relational inductive biases [2], has recently become one of the hottest topics in machine learning. While early works on graph learning go back at least a decade [3] if not two [4], it is undoubtedly the past few years’ progress that has taken these methods from a niche into the spotlight of the ML community and even to the popular science press (with Quanta Magazine running a series of excellent articles on geometric deep learning for the study of manifoldsdrug discovery, and protein science).

Graphs are powerful mathematical abstractions that can describe complex systems of relations and interactions in fields ranging from biology and high-energy physics to social science and economics. Since the amount of graph-structured data produced in some of these fields nowadays is enormous (prominent examples being social networks like Twitter and Facebook), it is very tempting to try to apply deep learning techniques that have been remarkably successful in other data-rich settings.

There are multiple flavours to graph learning problems that are largely application-dependent. One dichotomy is between node-wise and graph-wise problems, where in the former one tries to predict properties of individual nodes in the graph (e.g. identify malicious users in a social network), while in the latter one tries to make a prediction about the entire graph (e.g. predict solubility of a molecule). Furthermore, like in traditional ML problems, we can distinguish between supervised and unsupervised (or self-supervised) settings, as well as transductive and inductive problems.

Similarly to convolutional neural networks used in image analysis and computer vision, the key to efficient learning on graphs is designing local operations with shared weights that do message passing [5] between every node and its neighbours. A major difference compared to classical deep neural networks dealing with grid-structured data is that on graphs such operations are permutation-invariant, i.e. independent of the order of neighbour nodes, as there is usually no canonical way of ordering them.

Despite their promise and a series of success stories of graph representation learning (among which I can selfishly list the [acquisition by Twitter] of the graph-based fake news detection startup Fabula AI I have founded together with my students), we have not witnessed so far anything close to the smashing success convolutional networks have had in computer vision. In the following, I will try to outline my views on the possible reasons and how the field could progress in the next few years.

**Standardised benchmarks **like ImageNet were surely one of the key success factors of deep learning in computer vision, with some [6] even arguing that data was more important than algorithms for the deep learning revolution. We have nothing similar to ImageNet in scale and complexity in the graph learning community yet. The [Open Graph Benchmark] launched in 2019 is perhaps the first attempt toward this goal trying to introduce challenging graph learning tasks on interesting real-world graph-structured datasets. One of the hurdles is that tech companies producing diverse and rich graphs from their users’ activity are reluctant to share these data due to concerns over privacy laws such as GDPR. A notable exception is Twitter that made a dataset of 160 million tweets with corresponding user engagement graphs available to the research community under certain privacy-preserving restrictions as part of the [RecSys Challenge]. I hope that many companies will follow suit in the future.

**Software libraries **available in the public domain played a paramount role in “democratising” deep learning and making it a popular tool. If until recently, graph learning implementations were primarily a collection of poorly written and scarcely tested code, nowadays there are libraries such as [PyTorch Geometric] or [Deep Graph Library (DGL)] that are professionally written and maintained with the help of industry sponsorship. It is not uncommon to see an implementation of a new graph deep learning architecture weeks after it appears on arxiv.

Scalability is one of the key factors limiting industrial applications that often need to deal with very large graphs (think of Twitter social network with hundreds of millions of nodes and billions of edges) and low latency constraints. The academic research community has until recently almost ignored this aspect, with many models described in the literature completely inadequate for large-scale settings. Furthermore, graphics hardware (GPU), whose happy marriage with classical deep learning architectures was one of the primary forces driving their mutual success, is not necessarily the best fit for graph-structured data. In the long run, we might need specialised hardware for graphs [7].

**Dynamic graphs **are another aspect that is scarcely addressed in the literature. While graphs are a common way of modelling complex systems, such an abstraction is often too simplistic as real-world systems are dynamic and evolve in time. Sometimes it is the temporal behaviour that provides crucial insights about the system. Despite some recent progress, designing graph neural network models capable of efficiently dealing with continuous-time graphs represented as a stream of node- or edge-wise events is still an open research question.

#deep-learning #representation-learning #network-science #graph-neural-networks #geometric-deep-learning #deep learning

Marget D

Marget D

1618317562

Top Deep Learning Development Services | Hire Deep Learning Developer

View more: https://www.inexture.com/services/deep-learning-development/

We at Inexture, strategically work on every project we are associated with. We propose a robust set of AI, ML, and DL consulting services. Our virtuoso team of data scientists and developers meticulously work on every project and add a personalized touch to it. Because we keep our clientele aware of everything being done associated with their project so there’s a sense of transparency being maintained. Leverage our services for your next AI project for end-to-end optimum services.

#deep learning development #deep learning framework #deep learning expert #deep learning ai #deep learning services

John  Smith

John Smith

1657107416

Find the Best Restaurant Mobile App Development Company in Abu Dhbai

The era of mobile app development has completely changed the scenario for businesses in regions like Abu Dhabi. Restaurants and food delivery businesses are experiencing huge benefits via smart business applications. The invention and development of the food ordering app have helped all-scale businesses reach new customers and boost sales and profit. 

As a result, many business owners are searching for the best restaurant mobile app development company in Abu Dhabi. If you are also searching for the same, this article is helpful for you. It will let you know the step-by-step process to hire the right team of restaurant mobile app developers. 

Step-by-Step Process to Find the Best Restaurant App Development Company

Searching for the top mobile app development company in Abu Dhabi? Don't know the best way to search for professionals? Don't panic! Here is the step-by-step process to hire the best professionals. 

#Step 1 – Know the Company's Culture

Knowing the organization's culture is very crucial before finalizing a food ordering app development company in Abu Dhabi. An organization's personality is shaped by its common beliefs, goals, practices, or company culture. So, digging into the company culture reveals the core beliefs of the organization, its objectives, and its development team. 

Now, you might be wondering, how will you identify the company's culture? Well, you can take reference from the following sources – 

  • Social media posts 
  • App development process
  • About us Page
  • Client testimonials

#Step 2 - Refer to Clients' Reviews

Another best way to choose the On-demand app development firm for your restaurant business is to refer to the clients' reviews. Reviews are frequently available on the organization's website with a tag of "Reviews" or "Testimonials." It's important to read the reviews as they will help you determine how happy customers are with the company's app development process. 

You can also assess a company's abilities through reviews and customer testimonials. They can let you know if the mobile app developers create a valuable app or not. 

#Step 3 – Analyze the App Development Process

Regardless of the company's size or scope, adhering to the restaurant delivery app development process will ensure the success of your business application. Knowing the processes an app developer follows in designing and producing a top-notch app will help you know the working process. Organizations follow different app development approaches, so getting well-versed in the process is essential before finalizing any mobile app development company. 

#Step 4 – Consider Previous Experience

Besides considering other factors, considering the previous experience of the developers is a must. You can obtain a broad sense of the developer's capacity to assist you in creating a unique mobile application for a restaurant business.

You can also find out if the developers' have contributed to the creation of other successful applications or not. It will help you know the working capacity of a particular developer or organization. Prior experience is essential to evaluating their work. For instance, whether they haven't previously produced an app similar to yours or not. 

#Step 5 – Check for Their Technical Support

As you expect a working and successful restaurant mobile app for your business, checking on this factor is a must. A well-established organization is nothing without a good technical support team. So, ensure whatever restaurant mobile app development company you choose they must be well-equipped with a team of dedicated developers, designers, and testers. 

Strong tech support from your mobile app developers will help you identify new bugs and fix them bugs on time. All this will ensure the application's success. 

#Step 6 – Analyze Design Standards

Besides focusing on an organization's development, testing, and technical support, you should check the design standards. An appealing design is crucial in attracting new users and keeping the existing ones stick to your services. So, spend some time analyzing the design standards of an organization. Now, you might be wondering, how will you do it? Simple! By looking at the organization's portfolio. 

Whether hiring an iPhone app development company or any other, these steps apply to all. So, don't miss these steps. 

#Step 7 – Know Their Location

Finally, the last yet very crucial factor that will not only help you finalize the right person for your restaurant mobile app development but will also decide the mobile app development cost. So, you have to choose the location of the developers wisely, as it is a crucial factor in defining the cost. 

Summing Up!!!

Restaurant mobile applications have taken the food industry to heights none have ever considered. As a result, the demand for restaurant mobile app development companies has risen greatly, which is why businesses find it difficult to finalize the right person. But, we hope that after referring to this article, it will now be easier to hire dedicated developers under the desired budget. So, begin the hiring process now and get a well-craft food ordering app in hand. 

Mikel  Okuneva

Mikel Okuneva

1603735200

Top 10 Deep Learning Sessions To Look Forward To At DVDC 2020

The Deep Learning DevCon 2020, DLDC 2020, has exciting talks and sessions around the latest developments in the field of deep learning, that will not only be interesting for professionals of this field but also for the enthusiasts who are willing to make a career in the field of deep learning. The two-day conference scheduled for 29th and 30th October will host paper presentations, tech talks, workshops that will uncover some interesting developments as well as the latest research and advancement of this area. Further to this, with deep learning gaining massive traction, this conference will highlight some fascinating use cases across the world.

Here are ten interesting talks and sessions of DLDC 2020 that one should definitely attend:

Also Read: Why Deep Learning DevCon Comes At The Right Time


Adversarial Robustness in Deep Learning

By Dipanjan Sarkar

**About: **Adversarial Robustness in Deep Learning is a session presented by Dipanjan Sarkar, a Data Science Lead at Applied Materials, as well as a Google Developer Expert in Machine Learning. In this session, he will focus on the adversarial robustness in the field of deep learning, where he talks about its importance, different types of adversarial attacks, and will showcase some ways to train the neural networks with adversarial realisation. Considering abstract deep learning has brought us tremendous achievements in the fields of computer vision and natural language processing, this talk will be really interesting for people working in this area. With this session, the attendees will have a comprehensive understanding of adversarial perturbations in the field of deep learning and ways to deal with them with common recipes.

Read an interview with Dipanjan Sarkar.

Imbalance Handling with Combination of Deep Variational Autoencoder and NEATER

By Divye Singh

**About: **Imbalance Handling with Combination of Deep Variational Autoencoder and NEATER is a paper presentation by Divye Singh, who has a masters in technology degree in Mathematical Modeling and Simulation and has the interest to research in the field of artificial intelligence, learning-based systems, machine learning, etc. In this paper presentation, he will talk about the common problem of class imbalance in medical diagnosis and anomaly detection, and how the problem can be solved with a deep learning framework. The talk focuses on the paper, where he has proposed a synergistic over-sampling method generating informative synthetic minority class data by filtering the noise from the over-sampled examples. Further, he will also showcase the experimental results on several real-life imbalanced datasets to prove the effectiveness of the proposed method for binary classification problems.

Default Rate Prediction Models for Self-Employment in Korea using Ridge, Random Forest & Deep Neural Network

By Dongsuk Hong

About: This is a paper presentation given by Dongsuk Hong, who is a PhD in Computer Science, and works in the big data centre of Korea Credit Information Services. This talk will introduce the attendees with machine learning and deep learning models for predicting self-employment default rates using credit information. He will talk about the study, where the DNN model is implemented for two purposes — a sub-model for the selection of credit information variables; and works for cascading to the final model that predicts default rates. Hong’s main research area is data analysis of credit information, where she is particularly interested in evaluating the performance of prediction models based on machine learning and deep learning. This talk will be interesting for the deep learning practitioners who are willing to make a career in this field.


#opinions #attend dldc 2020 #deep learning #deep learning sessions #deep learning talks #dldc 2020 #top deep learning sessions at dldc 2020 #top deep learning talks at dldc 2020

野村  陽一

野村 陽一

1593880440

Using substructures for provably expressive graph neural networks

TL;DR: In this post, I discuss how to design local and computationally efficient provably powerful graph neural networks that are not based on the Weisfeiler-Lehman tests hierarchy. This is the second in the series of posts on the expressivity of graph neural networks. See Part 1 describing the relation between graph neural networks and the Weisfeiler-Lehman graph isomorphism test. In Part 3, I will argue why we should abandon the graph isomorphism problem altogether.

Recent groundbreaking papers [1–2] established the connection between graph neural networks and the graph isomorphism tests, observing the analogy between the message passing mechanism and the Weisfeiler-Lehman (WL) test [3]. WL test is a general name for a hierarchy of graph-theoretical polynomial-time iterative algorithms for determining graph isomorphism. The k-WL test recolours k-tuples of vertices of a graph at each step according to some neighbourhood aggregation rules and stops upon reaching a stable colouring. If the histograms of colours of the two graphs are not the same, the graphs are deemed not isomorphic; otherwise, the graphs are possibly (but not necessarily) isomorphic.

Message passing neural networks are at most as powerful as the 1-WL test (also known as node colour refinement), and thus unable to distinguish between even very simple instances of non-isomorphic graphs. For example, message passing neural networks cannot count triangles [4], a motif known to play an important role in social networks where it is associated with the clustering coefficient indicative of how “tightly knit” the users are [5]. It is possible to design more expressive graph neural networks that replicate the increasingly more powerful k-WL tests [2,6]. However, such architectures result in high complexity and large number of parameters, but most importantly, typically require non-local operations that make them impractical.

Examples of non-isomorphic graphs that cannot be distinguished by 1-WL but can be distinguished by 3-WL due to its capability of counting triangles.

Thus, provably powerful graph neural networks based on the Weisfeiler-Lehman hierarchy are either not very powerful but practical, or powerful but impractical [7]. I argue that there is a different simple way to design efficient and provably powerful graph neural networks, which we proposed in a new paper with Giorgos Bouritsas and Fabrizio Frasca [8].

**Graph Substructure Networks. **The idea is actually very simple and conceptually similar to positional encoding or graphlet descriptors [9]: we make the message passing mechanism aware of the local graph structure, allowing for computing messages differently depending on the topological relationship between the endpoint nodes. This is done by passing to message passing functions additional structural descriptors associated with each node [10], which are constructed by subgraph isomorphism counting. In this way, we can partition the nodes of the graph into different equivalence classes reflecting topological characteristics that are shared both between nodes in each graph individually and across different graphs.

We call this architecture Graph Substructure Network (GSN). It has the same algorithmic design and memory and computational complexity as standard message passing neural networks, with an additional pre-computation step in which the structural descriptors are constructed. The choice of the substructures to count is crucial both to the expressive power of GSNs and the computational complexity of the pre-computation step.

The worst-case complexity of counting substructures of size k in a graph with n nodes is 𝒪(nᵏ). Thus, it is similar to high-order graph neural network models or Morris [2] and Maron [6]. However, GSN has several advantages over these methods. First, for some types of substructures such as paths and cycles the counting can be done with significantly lower complexity. Secondly, the computationally expensive step is done only once as preprocessing and thus does not affect network training and inference that remain linear, the same way as in message-passing neural networks. The memory complexity in training and inference is linear as well. Thirdly and most importantly, the expressive power of GSN is different from k-WL tests and in some cases is stronger.

How powerful are GSNs? The substructure counting endows GSN with more expressive power than the standard message-passing neural networks. First, it is important to clarify that the expressive power of GSN depends on the graph substructures used. Same way as we have a hierarchy of k-WL tests, we might have different variants of GSNs based on counting one or more structures. Using structures more complex than star graphs, GSNs can be made strictly more powerful than 1-WL (or the equivalent 2-WL) and thus also more powerful than standard message passing architectures. With 4-cliques, GSN is at least no less powerful than 3-WL, as shown by the following example of strongly regular graphs on which GSN succeeds while 3-WL fails:

Example of non-isomorphic strongly regular graphs with 16 vertices and node degree 6, where every two adjacent vertices have 2 mutual neighbours, and every two non-adjacent vertices also have 2 mutual neighbours. The 3-WL test fails on this example, while GSN with 4-clique structure can distinguish between them. In the graph on the left (known as the Rook’s graph) each node participates in exactly one 4-clique. The graph on the right (Shrikhande graph) has maximum cliques of size 3 (triangles). Figure from [8].

More generally speaking, for various substructures of 𝒪(1) size, as long as they cannot be counted by 3-WL, there exist graphs where GSN succeeds and 3-WL fails [11]. While we could not find examples to the contrary, they might in principle exist — that is why our statement about the power of GSN is of a weak form, “at least not less powerful”.

This holds for larger k as well; a generalisation of strongly regular graphs in the above figure, called k-isoregular, are instances on which the (k+1)-WL test fails [12]. These examples can also be distinguished by GSN with appropriate structures. The expressive power of GSNs can thus be captured by the following figure:

GSN is outside the Weisfeiler-Lehman hierarchy. With the appropriate structure (e.g. cliques or cycles of certain size), it is likely to be made at least not less powerful than k-WL.

How powerful can GSN be in principle? This is still an open question. The Graph Reconstruction Conjecture [13] postulates the possibility of recovering a graph from all its node-deleted substructures. Thus, if the Reconstruction Conjecture is correct, a GSN with substructures of size _n_−1 would be able to correctly test isomorphism of any graphs. However, the Reconstruction Conjecture is currently proven only for graphs of size _n≤_11 [14], and second, such large structures would be impractical.

The more interesting question is whether a similar result exists for “small” structures (of 𝒪(1) size independent of the number of nodes n). Our empirical results show that GSN with small substructures such as cyclespaths, and cliques work for strongly regular graphs, which are known to be a tough nut for the Weisfeiler-Lehman tests.

#geometric-deep-learning #deep-learning #graph-neural-networks #graph-theory #machine-learning #deep learning