Graph Neural Networks (GNNs) excel at handling graph data but remain vulnerable to adversarial attacks. Existing defense methods typically rely on assumptions like graph sparsity and homophily to either preprocess the graph or guide structure learning. However, preprocessing methods often struggle to accurately distinguish between normal edges and adversarial perturbations, leading to suboptimal results due to the loss of valuable edge information. Robust graph neural network models train directly on graph data affected by adversarial perturbations, without preprocessing. This can cause the model to get stuck in poor local optima, negatively affecting its performance. To address these challenges, we propose Perseus, a novel adversarial defense method based on curriculum learning. Perseus assesses edge difficulty using global homophily and applies a curriculum learning strategy to adjust the learning order, guiding the model to learn the full graph structure while adaptively focusing on common data patterns. This approach mitigates the impact of adversarial perturbations. Experiments show that models trained with Perseus achieve superior performance and are significantly more robust to adversarial attacks.

Training large AI models on numerous GPUs consumes a massive amount of energy. We observe that not all energy consumed during training directly contributes to end-to-end training throughput, and a significant portion can be removed without slowing down training, which we call energy bloat. In this work, we identify two independent sources of energy bloat in large model training, intrinsic and extrinsic, and propose Perseus, a unified optimization framework that mitigates both. Perseus obtains the "iteration time-energy" Pareto frontier of any large model training job using an efficient iterative graph cut-based algorithm and schedules energy consumption of its forward and backward computations across time to remove intrinsic and extrinsic energy bloat. Evaluation on large models like GPT-3 and Bloom shows that Perseus reduces energy consumption of large model training by up to 30%, enabling savings otherwise unobtainable before.

The olfactory search POMDP (partially observable Markov decision process) is a sequential decision-making problem designed to mimic the task faced by insects searching for a source of odor in turbulence, and its solutions have applications to sniffer robots. As exact solutions are out of reach, the challenge consists in finding the best possible approximate solutions while keeping the computational cost reasonable. We provide a quantitative benchmarking of a solver based on deep reinforcement learning against traditional POMDP approximate solvers. We show that deep reinforcement learning is a competitive alternative to standard methods, in particular to generate lightweight policies suitable for robots.

Cross-Lingual Summarization (CLS) aims at generating summaries in one language for the given documents in another language. CLS has attracted wide research attention due to its practical significance in the multi-lingual world. Though great contributions have been made, existing CLS works typically focus on short documents, such as news articles, short dialogues and guides. Different from these short texts, long documents such as academic articles and business reports usually discuss complicated subjects and consist of thousands of words, making them non-trivial to process and summarize. To promote CLS research on long documents, we construct Perseus, the first long-document CLS dataset which collects about 94K Chinese scientific documents paired with English summaries. The average length of documents in Perseus is more than two thousand tokens. As a preliminary study on long-document CLS, we build and evaluate various CLS baselines, including pipeline and end-to-end methods. Experimental results on Perseus show the superiority of the end-to-end baseline, outperforming the strong pipeline models equipped with sophisticated machine translation systems. Furthermore, to provide a deeper understanding, we manually analyze the model outputs and discuss specific challenges faced by current approaches. We hope that our work could benchmark long-document CLS and benefit future studies.

Building trustworthy AI systems is a cornerstone to apply AI technologies in practice and therefore we need to explore methods, build tools, and incorporate different perspectives when developing novel AI applications. Based on the definition of the High Level Expert Group of the European Union, trustworthy AI should be lawful, ethical, and robust. While guidelines exist, research on implementation methodologies are currently under development and this PhD position will contribute to develop principles for creating trustworthy AI applications. Together with partners in the NorwAI SFI the candidate will work on the creation for guidelines for a sustainable and beneficial use of AI, explore privacy-preserving technologies and create explainable, interpretable and transparent prototypes to be tested in industrial settings. This PhD project is a part of the PERSEUS doctoral programme: A collaboration between NTNU- Norway's largest university, 11 top-level academic partners in 8 European countries, and 8 industrial partners within sectors of high societal relevance.

In this study I proposed a filtering beliefs method for improving performance of Partially Observable Markov Decision Processes(POMDPs), which is a method wildly used in autonomous robot and many other domains concerning control policy. My method search and compare every similar belief pair. Because a similar belief have insignificant influence on control policy, the belief is filtered out for reducing training time. The empirical results show that the proposed method outperforms the point-based approximate POMDPs in terms of the quality of training results as well as the efficiency of the method.

With its single-player story campaign, the first-person shooting game, which is out today for PlayStation 4, PS5, Xbox One, Xbox Series X and S, and PCs on Battle.net Somehow, the Russians swiped a U.S. nuke in 1968 and now that mistake has come back to haunt the Reagan Administration. That trip back in time nets intelligence needed to track Perseus, a Soviet mastermind who aims to use the bomb to attack the U.S. The search takes your character across the globe with stops in a Berlin still separated by the wall, Cuba, the Ukraine, Russia, and even into the heart of KGB headquarters. That nerve-wracking mission within the security agency is only one of many mind games awaiting players in this highly-entertaining sequel to 2010's "Call of Duty: Black Ops." In that earlier game, you played primarily as Alex Mason, a CIA operator who we learned was brainwashed by the Soviets.

Adaptive management is applied in conservation and natural resource management, and consists of making sequential decisions when the transition matrix is uncertain. Informally described as ’learning by doing’, this approach aims to trade off between decisions that help achieve the objective and decisions that will yield a better knowledge of the true transition matrix. When the true transition matrix is assumed to be an element of a finite set of possible matrices, solving a mixed observability Markov decision process (MOMDP) leads to an optimal trade-off but is very computationally demanding. Under the assumption (common in adaptive management) that the true transition matrix is stationary, we propose a polynomial-time algorithm to find a lower bound of the value function. In the corners of the domain of the value function (belief space), this lower bound is provably equal to the optimal value function. We also show that under further assumptions, it is a linear approximation of the optimal value function in a neighborhood around the corners. We evaluate the benefits of our approach by using it to initialize the solvers MO-SARSOP and Perseus on a novel computational sustainability problem and a recent adaptive management data challenge. Our approach leads to an improved initial value function and translates into significant computational gains for both solvers.

Partially observable Markov decision processes (POMDPs) form an attractive and principled framework for agent planning under uncertainty. Point-based approximate techniques for POMDPs compute a policy based on a finite set of points collected in advance from the agents belief space. We present a randomized point-based value iteration algorithm called Perseus. The algorithm performs approximate value backup stages, ensuring that in each backup stage the value of each point in the belief set is improved; the key observation is that a single backup may improve the value of many belief points. Contrary to other point-based methods, Perseus backs up only a (randomly selected) subset of points in the belief set, sufficient for improving the value of each belief point in the set. We show how the same idea can be extended to dealing with continuous action spaces. Experimental results show the potential of Perseus in large scale POMDP problems.

In many real-world situations we are charged with detecting change as soon as possible. Important examples include detecting medical conditions, detecting security breaches, and updating caches of distributed databases. In those situations, sensing can be expensive, but it is also important to detect change in a timely manner. In this paper we present tractable greedy algorithms and prove that they solve this decision problem either optimally or approximate the optimal solution in many cases. Our problem model is a POMDP that includes a cost for sensing, a cost for delayed detection, a reward for successful detection, and no-cost partial observations. Making optimal decisions is difficult in general. We show that our tractable greedy approach finds optimal policies for sensing both a single variable and multiple correlated variables. Further, we provide approximations for the optimal solution to multiple hidden or observed variables per step. Our algorithms outperform previous algorithms in experiments over simulated data and live Wikipedia WWW pages.