Despite its success in the image domain, adversarial training did not (yet) stand out as an effective defense for Graph Neural Networks (GNNs) against graph structure perturbations. In the pursuit of fixing adversarial training (1) we show and overcome fundamental theoretical as well as practical limitations of the adopted graph learning setting in prior work; (2) we reveal that flexible GNNs based on learnable graph diffusion are able to adjust to adversarial perturbations, while the learned message passing scheme is naturally interpretable; (3) we introduce the first attack for structure perturbations that, while targeting multiple nodes at once, is capable of handling global (graph-level) as well as local (node-level) constraints. Including these contributions, we demonstrate that adversarial training is a state-of-the-art defense against adversarial structure perturbations.

This paper addresses the challenges of storage and communication costs for large-scale datasets in resource-constrained edge devices by proposing a novel dataset quantization approach to reduce intra-sample redundancy. Unlike traditional dataset pruning and distillation methods that focus on inter-sample redundancy, the proposed method compresses each image by reducing redundant or less informative content within samples while preserving essential features. It first applies linear symmetric quantization to obtain an initial quantization range and scale for each sample. Then, an adaptive quantization allocation algorithm is introduced to distribute different quantization ratios for samples with varying precision requirements, maintaining a constant total compression ratio. The main contributions include: (1) being the first to use limited bits to represent datasets for storage reduction; (2) introducing a dataset-level quantization algorithm with adaptive ratio allocation; and (3) validating the method's effectiveness through extensive experiments on CIFAR-10, CIFAR-100, and ImageNet-1K. Results show that the method maintains model training performance while achieving significant dataset compression, outperforming traditional quantization and dataset pruning baselines under the same compression ratios.

Despite its success in the image domain, adversarial training did not (yet) stand out as an effective defense for Graph Neural Networks (GNNs) against graph structure perturbations. In the pursuit of fixing adversarial training (1) we show and overcome fundamental theoretical as well as practical limitations of the adopted graph learning setting in prior work; (2) we reveal that flexible GNNs based on learnable graph diffusion are able to adjust to adversarial perturbations, while the learned message passing scheme is naturally interpretable; (3) we introduce the first attack for structure perturbations that, while targeting multiple nodes at once, is capable of handling global (graph-level) as well as local (node-level) constraints. Including these contributions, we demonstrate that adversarial training is a state-of-the-art defense against adversarial structure perturbations.

The stakeholders' needs in sentiment analysis for various issues, whether positive or negative, are speed and accuracy. One new challenge in sentiment analysis tasks is the limited training data, which often leads to suboptimal machine learning models and poor performance on test data. This paper discusses the problem of text classification based on limited training data (300 to 600 samples) into three classes: positive, negative, and neutral. A benchmark dataset is provided for training and testing data on the issue of Kaesang Pangarep's appointment as Chairman of PSI. External data for aggregation and augmentation purposes are provided, consisting of two datasets: the topic of Covid Vaccination sentiment and an open topic. The official score used is the F1-score, which balances precision and recall among the three classes, positive, negative, and neutral. A baseline score is provided as a reference for researchers for unoptimized classification methods. The optimized score is provided as a reference for the target score to be achieved by any proposed method. Both scoring (baseline and optimized) use the SVM method, which is widely reported as the state-of-the-art in conventional machine learning methods. The F1-scores achieved by the baseline and optimized methods are 40.83% and 51.28%, respectively.

Square Enix wants a hit Final Fantasy game that's just as popular as any game in the storied history. It's taken seven years to get from the tepidly-received Final Fantasy XV to Final Fantasy XVI, and the company continues to wrestle with what a FF game is in 2023. The company courted nostalgia with FF7 Remake (and the Pixel Remaster series). At the same time, its MMORPG, Final Fantasy XIV, continues to be a huge success – but what about the prestige title? It has a plan, and it involves giant-summoned monster battles with different styles of play, a single controllable protagonist with guest-star allies, a support dog that grows up with you, horny antagonists, wicked moms and several bleak plot twists to help establish the plot and characters relatively early on.

Artificial intelligence (AI) is an excellent and rapidly growing field that involves the development of algorithms and systems that continuously tend to perform tasks that typically require human intelligence. AI systems can process vast amounts of data, identify patterns, make predictions and automate repetitive tasks. Recent years have seen a rapid advancement in AI capabilities, resulting in its adoption across various manufacturing and finance industries. Despite the impressive capabilities of AI, it is essential to recognize that it still has limitations. While AI systems can process vast amounts of data and make predictions, they need more independent thought and creativity, often essential for scientific exploration and discovery.

With multilingual machine translation (MMT) models continuing to grow in size and number of supported languages, it is natural to reuse and upgrade existing models to save computation as data becomes available in more languages. However, adding new languages requires updating the vocabulary, which complicates the reuse of embeddings. The question of how to reuse existing models while also making architectural changes to provide capacity for both old and new languages has also not been closely studied. In this work, we introduce three techniques that help speed up effective learning of the new languages and alleviate catastrophic forgetting despite vocabulary and architecture mismatches. Our results show that by (1) carefully initializing the network, (2) applying learning rate scaling, and (3) performing data up-sampling, it is possible to exceed the performance of a same-sized baseline model with 30% computation and recover the performance of a larger model trained from scratch with over 50% reduction in computation. Furthermore, our analysis reveals that the introduced techniques help learn the new directions more effectively and alleviate catastrophic forgetting at the same time. We hope our work will guide research into more efficient approaches to growing languages for these MMT models and ultimately maximize the reuse of existing models.

The paper describes the University of Cape Town's submission to the constrained track of the WMT22 Shared Task: Large-Scale Machine Translation Evaluation for African Languages. Our system is a single multilingual translation model that translates between English and 8 South / South East African Languages, as well as between specific pairs of the African languages. We used several techniques suited for low-resource machine translation (MT), including overlap BPE, back-translation, synthetic training data generation, and adding more translation directions during training. Our results show the value of these techniques, especially for directions where very little or no bilingual training data is available.

Kevin Markarian is the cofounder of Roopler, an AI-driven lead generation platform built for the real estate industry. Artificial intelligence is rapidly upending how people do business across industries, and yet skeptics still abound. But is there really a reason to fear AI? AI will change how we work and do business, and its impact is already being felt. Still, that doesn't mean it is something to fear. On the contrary, business managers and leaders who embrace AI and harness its potential now have everything to gain.

The annual meeting of the North American chapter of the Association for Computational Linguistics (NAACL) introduced an industry track in 2018, and at this year's conference, which begins next week, one of the industry track chairs is Amazon principal research scientist Rashmi Gangadharaiah. "The NAACL industry track inspired industry tracks at other conferences such as COLING and EMNLP," Gangadharaiah says. "The industry track provides a forum for researchers in the industry to exchange ideas and discuss successful deployments of ML [machine learning] and NLP [natural-language processing] technologies, as well as share challenges that arise in deploying such systems in real-world settings." For instance, Gangadharaiah explains, "academic research is often done in very controlled settings. It's not a negative thing: people have to do research, and it's useful to start in a controlled setting. But when we put such systems in real-world situations, we typically have to worry about latency, memory, and space. It's not always accuracy that we go for. So I think it makes it more interesting that way."