Temporal graph neural network has recently received significant attention due to its wide application scenarios, such as bioinformatics, knowledge graphs, and social networks. There are some temporal graph neural networks that achieve remarkable results. However, these works focus on future event prediction and are performed under the assumption that all historical events are observable. In real-world applications, events are not always observable, and estimating event time is as important as predicting future events. In this paper, we propose MTGN, a missing event-aware temporal graph neural network, which uniformly models evolving graph structure and timing of events to support predicting what will happen in the future and when it will happen.MTGN models the dynamic of both observed and missing events as two coupled temporal point processes, thereby incorporating the effects of missing events into the network. Experimental results on several real-world temporal graphs demonstrate that MTGN significantly outperforms existing methods with up to 89% and 112% more accurate time and link prediction. Code can be found on https://github.com/HIT-ICES/TNNLS-MTGN.

For our course project, we aim to reverse the roles of the computer and human, such that the computer will act as an answerer and a human as a questioner. In the past, no such study has been conducted as this problem presented sophisticated challenges of Natural Language Inference and Textual Entailment. However, with the advent of transformer-based machine learning techniques such as BERT [1], RoBERTa [2], GPT-2 [3], and datasets such as BoolQ [4], such a model can be constructed. As this problem has not been formally defined, our goal is to formalize it and present preliminary results regarding the same. Furthermore, while there are several pre-trained question-answering models that select the start and end points of a corpus containing an answer, a simple yes/no answering task is surprisingly challenging and complex. A model for such a task would have to examine entailment as well as investigate if the corpus makes a positive answer to the question unlikely, even if it doesn't directly state a negative answer [4]. Our reverse Akinator model could be used for any sort of factual checker to examine whether a statement is true or not, given a knowledge corpus.

ChatGPT was hailed as one 2022's most impressive technological innovations upon its release last November. The powerful artificial intelligence (AI) chatbot can generate text on almost any topic or theme, from a Shakespearean sonnet reimagined in the style of Megan Thee Stallion, to complex mathematical theorems described in language a 5 year old can understand. Within a week, it had more than a million users. ChatGPT's creator, OpenAI, is now reportedly in talks with investors to raise funds at a $29 billion valuation, including a potential $10 billion investment by Microsoft. That would make OpenAI, which was founded in San Francisco in 2015 with the aim of building superintelligent machines, one of the world's most valuable AI companies.

Clearly, such an imbalance is undesirable, putting those who do not use English at a disadvantage. In this article, we highlight some of the work and initiatives being carried out on low-resource languages. Africa is one of the most linguistically diverse regions in the world. Despite this, African languages are barely represented in technology and research. Lanfrica aims to mitigate the difficulty encountered in the discovery of African language resources by creating a centralised hub.

With the increasing prevalence of scalable file systems in the context of High Performance Computing (HPC), the importance of accurate anomaly detection on runtime logs is increasing. But as it currently stands, many state-of-the-art methods for log-based anomaly detection, such as DeepLog, have encountered numerous challenges when applied to logs from many parallel file systems (PFSes), often due to their irregularity and ambiguity in time-based log sequences. To circumvent these problems, this study proposes ClusterLog, a log pre-processing method that clusters the temporal sequence of log keys based on their semantic similarity. By grouping semantically and sentimentally similar logs, this approach aims to represent log sequences with the smallest amount of unique log keys, intending to improve the ability of a downstream sequence-based model to effectively learn the log patterns. The preliminary results of ClusterLog indicate not only its effectiveness in reducing the granularity of log sequences without the loss of important sequence information but also its generalizability to different file systems' logs.

Obtaining accurate ground and low-lying excited states of electronic systems is crucial in a multitude of important applications. One ab initio method for solving the Schr\"odinger equation that scales favorably for large systems is variational quantum Monte Carlo (QMC). The recently introduced deep QMC approach uses ansatzes represented by deep neural networks and generates nearly exact ground-state solutions for molecules containing up to a few dozen electrons, with the potential to scale to much larger systems where other highly accurate methods are not feasible. In this paper, we extend one such ansatz (PauliNet) to compute electronic excited states. We demonstrate our method on various small atoms and molecules and consistently achieve high accuracy for low-lying states. To highlight the method's potential, we compute the first excited state of the much larger benzene molecule, as well as the conical intersection of ethylene, with PauliNet matching results of more expensive high-level methods.

Foundation models have shown impressive adaptation and scalability in supervised and self-supervised learning problems, but so far these successes have not fully translated to reinforcement learning (RL). In this work, we demonstrate that training an RL agent at scale leads to a general in-context learning algorithm that can adapt to open-ended novel embodied 3D problems as quickly as humans. In a vast space of held-out environment dynamics, our adaptive agent (AdA) displays on-the-fly hypothesis-driven exploration, efficient exploitation of acquired knowledge, and can successfully be prompted with first-person demonstrations. Adaptation emerges from three ingredients: (1) meta-reinforcement learning across a vast, smooth and diverse task distribution, (2) a policy parameterised as a large-scale attention-based memory architecture, and (3) an effective automated curriculum that prioritises tasks at the frontier of an agent's capabilities. We demonstrate characteristic scaling laws with respect to network size, memory length, and richness of the training task distribution. We believe our results lay the foundation for increasingly general and adaptive RL agents that perform well across ever-larger open-ended domains.

Predictive process monitoring is a subfield of process mining that aims to estimate case or event features for running process instances. Such predictions are of significant interest to the process stakeholders. However, most of the state-of-the-art methods for predictive monitoring require the training of complex machine learning models, which is often inefficient. Moreover, most of these methods require a hyper-parameter optimization that requires several repetitions of the training process which is not feasible in many real-life applications. In this paper, we propose an instance selection procedure that allows sampling training process instances for prediction models. We show that our instance selection procedure allows for a significant increase of training speed for next activity and remaining time prediction methods while maintaining reliable levels of prediction accuracy.

Learning classifiers that are robust to adversarial examples has received a great deal of recent attention. A major drawback of the standard robust learning framework is there is an artificial robustness radius $r$ that applies to all inputs. This ignores the fact that data may be highly heterogeneous, in which case it is plausible that robustness regions should be larger in some regions of data, and smaller in others. In this paper, we address this limitation by proposing a new limit classifier, called the neighborhood optimal classifier, that extends the Bayes optimal classifier outside its support by using the label of the closest in-support point. We then argue that this classifier maximizes the size of its robustness regions subject to the constraint of having accuracy equal to the Bayes optimal. We then present sufficient conditions under which general non-parametric methods that can be represented as weight functions converge towards this limit, and show that both nearest neighbors and kernel classifiers satisfy them under certain conditions.

This paper investigates task-oriented communication for edge inference, where a low-end edge device transmits the extracted feature vector of a local data sample to a powerful edge server for processing. It is critical to encode the data into an informative and compact representation for low-latency inference given the limited bandwidth. We propose a learning-based communication scheme that jointly optimizes feature extraction, source coding, and channel coding in a task-oriented manner, i.e., targeting the downstream inference task rather than data reconstruction. Specifically, we leverage an information bottleneck (IB) framework to formalize a rate-distortion tradeoff between the informativeness of the encoded feature and the inference performance. As the IB optimization is computationally prohibitive for the high-dimensional data, we adopt a variational approximation, namely the variational information bottleneck (VIB), to build a tractable upper bound. To reduce the communication overhead, we leverage a sparsity-inducing distribution as the variational prior for the VIB framework to sparsify the encoded feature vector. Furthermore, considering dynamic channel conditions in practical communication systems, we propose a variable-length feature encoding scheme based on dynamic neural networks to adaptively adjust the activated dimensions of the encoded feature to different channel conditions. Extensive experiments evidence that the proposed task-oriented communication system achieves a better rate-distortion tradeoff than baseline methods and significantly reduces the feature transmission latency in dynamic channel conditions.