Enterprise machine learning deployments are limited by two consequences of outdated data management practices widely used today. The first is the protracted time-to-insight that stems from antiquated data replication approaches. The second is the lack of unified, contextualized data that spans the organization horizontally. Excessive data replication and the resulting "second-order effects" are creating enormous efficiencies and waste for data scientists in most organizations. According to IDC, over 60 zettabytes of data were produced last year, and this is forecast to increase at a CAGR of 23 percent until 2025.

I have already demonstrated how to create a knowledge graph out of a Wikipedia page. However, since the post got a lot of attention, I've decided to explore other domains where using NLP techniques to construct a knowledge graph makes sense. In my opinion, the biomedical field is a prime example where representing the data as a graph makes sense as you are often analyzing interactions and relations between genes, diseases, drugs, proteins, and more. In the above visualization, we have ascorbic acid, also known as vitamin C, and some of its relations to other concepts. For example, it shows that vitamin C could be used to treat chronic gastritis.

Neuro-Symbolic AI, which is alternatively called composite AI, is a relatively new term for a well-established concept with enormous significance for almost any enterprise application of Artificial Intelligence. By combining AI's statistical foundation (exemplified by machine learning) with its knowledge foundation (exemplified by knowledge graphs and rules), organizations get the most effective cognitive analytics results with the least amount of headaches--and cost. Pairing these two historical pillars of AI is essential to maximizing investments in these technologies and in data themselves. By itself, rules-based symbolic reasoning doesn't improve over time. Together, these AI approaches create total machine intelligence with logic-based systems that get better with each application.

While the natural language processing (NLP) field has been growing at an exponential rate for the last two years -- thanks to the development of transfer-based models -- their applications have been limited in scope for the job search field. LinkedIn, the leading company in job search and recruitment, is a good example. While I hold a Ph.D. in Material Science and a Master in Physics, I am receiving job recommendations such as Technical Program Manager at MongoDB and a Go Developer position at Toptal which are both web developing companies that are not relevant to my background. This feeling of irrelevancy is shared by many users and is a cause of big frustration. Job seekers should have access to the best tools to help them find the perfect match to their profile without wasting time in irrelevant recommendations and manual searches...

If you are an experienced reader of such digests (or previous posts) then you know pretty well the abundance of KG-augmented LMs published at every conference and uploaded to arxiv weekly. If you feel lost -- I can assure you're not the only one. This year, we finally have a sound framework and taxonomy of various KG LM approaches! The authors define 3 big families: 1 no KG supervision, probing knowledge encoded in LM params with cloze-style prompts; 2 KG supervision with entities and IDs; 3 KG supervision with relation templates and surface forms. Each family has a few branches For instance, let's have a look at 4 entity-aware models illustrated below.

Medical report generation, which aims to automatically generate a long and coherent report of a given medical image, has been receiving growing research interests. Existing approaches mainly adopt a supervised manner and heavily rely on coupled image-report pairs. However, in the medical domain, building a large-scale image-report paired dataset is both time-consuming and expensive. To relax the dependency on paired data, we propose an unsupervised model Knowledge Graph Auto-Encoder (KGAE) which accepts independent sets of images and reports in training. KGAE consists of a pre-constructed knowledge graph, a knowledge-driven encoder and a knowledge-driven decoder. The knowledge graph works as the shared latent space to bridge the visual and textual domains; The knowledge-driven encoder projects medical images and reports to the corresponding coordinates in this latent space and the knowledge-driven decoder generates a medical report given a coordinate in this space. Since the knowledge-driven encoder and decoder can be trained with independent sets of images and reports, KGAE is unsupervised. The experiments show that the unsupervised KGAE generates desirable medical reports without using any image-report training pairs. Moreover, KGAE can also work in both semi-supervised and supervised settings, and accept paired images and reports in training. By further fine-tuning with image-report pairs, KGAE consistently outperforms the current state-of-the-art models on two datasets.

In this section, we will introduce KG by asking some simple but intuitive questions about KG. In fact, we will cover the what, why, and how of the knowledge graph. We will also go through some real-world examples. This is the very first and a valid question anyone will ask when introduced to KG. We will try to go through some points wherein we compare KG with normal graphs and even other ways of storing information. The aim is to highlight the major advantages of using KG.

We study the problem of generating data poisoning attacks against Knowledge Graph Embedding (KGE) models for the task of link prediction in knowledge graphs. To poison KGE models, we propose to exploit their inductive abilities which are captured through the relationship patterns like symmetry, inversion and composition in the knowledge graph. Specifically, to degrade the model's prediction confidence on target facts, we propose to improve the model's prediction confidence on a set of decoy facts. Thus, we craft adversarial additions that can improve the model's prediction confidence on decoy facts through different inference patterns. Our experiments demonstrate that the proposed poisoning attacks outperform state-of-art baselines on four KGE models for two publicly available datasets. We also find that the symmetry pattern based attacks generalize across all model-dataset combinations which indicates the sensitivity of KGE models to this pattern.

Nowadays, Knowledge graphs (KGs) have been playing a pivotal role in AI-related applications. Despite the large sizes, existing KGs are far from complete and comprehensive. In order to continuously enrich KGs, automatic knowledge construction and update mechanisms are usually utilized, which inevitably bring in plenty of noise. However, most existing knowledge graph embedding (KGE) methods assume that all the triple facts in KGs are correct, and project both entities and relations into a low-dimensional space without considering noise and knowledge conflicts. This will lead to low-quality and unreliable representations of KGs. To this end, in this paper, we propose a general multi-task reinforcement learning framework, which can greatly alleviate the noisy data problem. In our framework, we exploit reinforcement learning for choosing high-quality knowledge triples while filtering out the noisy ones. Also, in order to take full advantage of the correlations among semantically similar relations, the triple selection processes of similar relations are trained in a collective way with multi-task learning. Moreover, we extend popular KGE models TransE, DistMult, ConvE and RotatE with the proposed framework. Finally, the experimental validation shows that our approach is able to enhance existing KGE models and can provide more robust representations of KGs in noisy scenarios.

With the rapid development of the mobile communication technology, mobile trajectories of humans are massively collected by Internet service providers (ISPs) and application service providers (ASPs). On the other hand, the rising paradigm of knowledge graph (KG) provides us a promising solution to extract structured "knowledge" from massive trajectory data. In this paper, we focus on modeling users' spatio-temporal mobility patterns based on knowledge graph techniques, and predicting users' future movement based on the "knowledge'' extracted from multiple sources in a cohesive manner. Specifically, we propose a new type of knowledge graph, i.e., spatio-temporal urban knowledge graph (STKG), where mobility trajectories, category information of venues, and temporal information are jointly modeled by the facts with different relation types in STKG. The mobility prediction problem is converted to the knowledge graph completion problem in STKG. Further, a complex embedding model with elaborately designed scoring functions is proposed to measure the plausibility of facts in STKG to solve the knowledge graph completion problem, which considers temporal dynamics of the mobility patterns and utilizes PoI categories as the auxiliary information and background knowledge. Extensive evaluations confirm the high accuracy of our model in predicting users' mobility, i.e., improving the accuracy by 5.04% compared with the state-of-the-art algorithms. In addition, PoI categories as the background knowledge and auxiliary information are confirmed to be helpful by improving the performance by 3.85% in terms of accuracy. Additionally, experiments show that our proposed method is time-efficient by reducing the computational time by over 43.12% compared with existing methods.