Controversial AI tool ChatGPT has already been banned in schools across the world over fears it encourages cheating and laziness. But the International Baccalaureate (IB), which offers an alternative to A-levels, is bucking this trend by permitting the use of ChatGPT to write essays. Students undertaking IB programmes will be able to quote passages generated by the chatbot - as long as they do not try to pass it off as their own words. Created by San Francisco-based company OpenAI, the tool has been trained on a massive amount of text so it can generate human-like responses to questions. A university student has already used ChatGPT to write a 2,000-word essay that got a 2:2 grade, although the lecturer called the language used'fishy'.

Tesla has applied for a set of patents that are set to significantly improve virtualization, recognition, and Full Self Driving overall. Tesla has worked tirelessly to improve full self-driving technology in the first two months of the year. Most recently, Tesla pushed its most significant improvement to employees, v11.3. Still, with new patented technology, the software is set to continue to improve dramatically this year. The two patents, focusing on virtualization and machine learning, appeared in the U.S. Patent Office database late last week.

If you read my work you probably know that I publish my articles first and foremost in my AI newsletter, The Algorithmic Bridge. What you may not know is that every Sunday I publish a special column I call "what you may have missed," where I review everything that has happened during the week with analyses that help you make sense of the news. Semafor reported two weeks ago that, if everything goes according to the plan, Microsoft will close a $10B investment deal with OpenAI before the end of January (Satya Nadella, Microsoft's CEO, announced the extended partnership officially on Monday). There's been some misinformation about the deal which implied that OpenAI execs weren't sure about the company's long-term viability. Leo L'Orange, who writes The Neuron, explains that "once $92 billion in profit plus $13 billion in initial investment are repaid to Microsoft and once the other venture investors earn $150 billion, all of the equity reverts back to OpenAI."

Interactive exploration of large, multidimensional datasets plays a very important role in various scientific fields. It makes it possible not only to identify important structural features and forms, such as clusters of vertices and their connection patterns, but also to evaluate their interrelationships in terms of position, distance, shape and connection density. We argue that the visualization of multidimensional data is well approximated by the problem of two-dimensional embedding of undirected nearest-neighbor graphs. The size of complex networks is a major challenge for today's computer systems and still requires more efficient data embedding algorithms. Existing reduction methods are too slow and do not allow interactive manipulation. We show that high-quality embeddings are produced with minimal time and memory complexity. We present very efficient IVHD algorithms (CPU and GPU) and compare them with the latest and most popular dimensionality reduction methods. We show that the memory and time requirements are dramatically lower than for base codes. At the cost of a slight degradation in embedding quality, IVHD preserves the main structural properties of the data well with a much lower time budget. We also present a meta-algorithm that allows the use of any unsupervised data embedding method in a supervised manner.

Large-scale deep neural networks consume expensive training costs, but the training results in less-interpretable weight matrices constructing the networks. Here, we propose a mode decomposition learning that can interpret the weight matrices as a hierarchy of latent modes. These modes are akin to patterns in physics studies of memory networks, but the least number of modes increases only logarithmically with the network width, and becomes even a constant when the width further grows. The mode decomposition learning not only saves a significant large amount of training costs, but also explains the network performance with the leading modes, displaying a striking piecewise power-law behavior. The modes specify a progressively compact latent space across the network hierarchy, making a more disentangled subspaces compared to standard training. Our mode decomposition learning is also studied in an analytic on-line learning setting, which reveals multi-stage of learning dynamics with a continuous specialization of hidden nodes. Therefore, the proposed mode decomposition learning points to a cheap and interpretable route towards the magical deep learning.

We propose two frameworks to deal with problem settings in which both structured and unstructured data are available. Structured data problems are best solved by traditional machine learning models such as boosting and tree-based algorithms, whereas deep learning has been widely applied to problems dealing with images, text, audio, and other unstructured data sources. However, for the setting in which both structured and unstructured data are accessible, it is not obvious what the best modeling approach is to enhance performance on both data sources simultaneously. Our proposed frameworks allow joint learning on both kinds of data by integrating the paradigms of boosting models and deep neural networks. The first framework, the boosted-feature-vector deep learning network, learns features from the structured data using gradient boosting and combines them with embeddings from unstructured data via a two-branch deep neural network. Secondly, the two-weak-learner boosting framework extends the boosting paradigm to the setting with two input data sources. We present and compare first- and second-order methods of this framework. Our experimental results on both public and real-world datasets show performance gains achieved by the frameworks over selected baselines by magnitudes of 0.1% - 4.7%.

Knowledge distillation is an approach to transfer information on representations from a teacher to a student by reducing their difference. A challenge of this approach is to reduce the flexibility of the student's representations inducing inaccurate learning of the teacher's knowledge. To resolve it in transferring, we investigate distillation of structures of representations specified to three types: intra-feature, local inter-feature, global inter-feature structures. To transfer them, we introduce feature structure distillation methods based on the Centered Kernel Alignment, which assigns a consistent value to similar features structures and reveals more informative relations. In particular, a memory-augmented transfer method with clustering is implemented for the global structures. The methods are empirically analyzed on the nine tasks for language understanding of the GLUE dataset with Bidirectional Encoder Representations from Transformers (BERT), which is a representative neural language model. In the results, the proposed methods effectively transfer the three types of structures and improve performance compared to state-of-the-art distillation methods. Indeed, the code for the methods is available in https://github.com/maroo-sky/FSD.

Data-free Knowledge Distillation (DFKD) has gained popularity recently, with the fundamental idea of carrying out knowledge transfer from a Teacher neural network to a Student neural network in the absence of training data. However, in the Adversarial DFKD framework, the student network's accuracy, suffers due to the non-stationary distribution of the pseudo-samples under multiple generator updates. To this end, at every generator update, we aim to maintain the student's performance on previously encountered examples while acquiring knowledge from samples of the current distribution. Thus, we propose a meta-learning inspired framework by treating the task of Knowledge-Acquisition (learning from newly generated samples) and Knowledge-Retention (retaining knowledge on previously met samples) as meta-train and meta-test, respectively. Hence, we dub our method as Learning to Retain while Acquiring. Moreover, we identify an implicit aligning factor between the Knowledge-Retention and Knowledge-Acquisition tasks indicating that the proposed student update strategy enforces a common gradient direction for both tasks, alleviating interference between the two objectives. Finally, we support our hypothesis by exhibiting extensive evaluation and comparison of our method with prior arts on multiple datasets.

Graph, such as citation networks, social networks, and transportation networks, are prevalent in the real world. Graph Neural Networks (GNNs) have gained widespread attention for their robust expressiveness and exceptional performance in various graph applications. However, the efficacy of GNNs is heavily reliant on sufficient data labels and complex network models, with the former obtaining hardly and the latter computing costly. To address the labeled data scarcity and high complexity of GNNs, Knowledge Distillation (KD) has been introduced to enhance existing GNNs. This technique involves transferring the soft-label supervision of the large teacher model to the small student model while maintaining prediction performance. This survey offers a comprehensive overview of Graph-based Knowledge Distillation methods, systematically categorizing and summarizing them while discussing their limitations and future directions. This paper first introduces the background of graph and KD. It then provides a comprehensive summary of three types of Graph-based Knowledge Distillation methods, namely Graph-based Knowledge Distillation for deep neural networks (DKD), Graph-based Knowledge Distillation for GNNs (GKD), and Self-Knowledge Distillation based Graph-based Knowledge Distillation (SKD). Each type is further divided into knowledge distillation methods based on the output layer, middle layer, and constructed graph. Subsequently, various algorithms' ideas are analyzed and compared, concluding with the advantages and disadvantages of each algorithm supported by experimental results. In addition, the applications of graph-based knowledge distillation in CV, NLP, RS, and other fields are listed. Finally, the graph-based knowledge distillation is summarized and prospectively discussed. We have also released related resources at https://github.com/liujing1023/Graph-based-Knowledge-Distillation.

In deep learning, different kinds of deep networks typically need different optimizers, which have to be chosen after multiple trials, making the training process inefficient. To relieve this issue and consistently improve the model training speed across deep networks, we propose the ADAptive Nesterov momentum algorithm, Adan for short. Adan first reformulates the vanilla Nesterov acceleration to develop a new Nesterov momentum estimation (NME) method, which avoids the extra overhead of computing gradient at the extrapolation point. Then Adan adopts NME to estimate the gradient's first- and second-order moments in adaptive gradient algorithms for convergence acceleration. Besides, we prove that Adan finds an $\epsilon$-approximate first-order stationary point within $O(\epsilon^{-3.5})$ stochastic gradient complexity on the non-convex stochastic problems (e.g., deep learning problems), matching the best-known lower bound. Extensive experimental results show that Adan consistently surpasses the corresponding SoTA optimizers on vision, language, and RL tasks and sets new SoTAs for many popular networks and frameworks, e.g., ResNet, ConvNext, ViT, Swin, MAE, DETR, GPT-2, Transformer-XL, and BERT. More surprisingly, Adan can use half of the training cost (epochs) of SoTA optimizers to achieve higher or comparable performance on ViT, GPT-2, MAE, e.t.c., and also shows great tolerance to a large range of minibatch size, e.g., from 1k to 32k. Code is released at https://github.com/sail-sg/Adan, and has been used in multiple popular deep learning frameworks or projects.