Learning from a sequence of tasks for a lifetime is essential for an agent towards artificial general intelligence. This requires the agent to continuously learn and memorize new knowledge without interference. This paper first demonstrates a fundamental issue of lifelong learning using neural networks, named anterograde forgetting, i.e., preserving and transferring memory may inhibit the learning of new knowledge. This is attributed to the fact that the learning capacity of a neural network will be reduced as it keeps memorizing historical knowledge, and the fact that conceptual confusion may occur as it transfers irrelevant old knowledge to the current task. This work proposes a general framework named Cycled Memory Networks (CMN) to address the anterograde forgetting in neural networks for lifelong learning. The CMN consists of two individual memory networks to store short-term and long-term memories to avoid capacity shrinkage. A transfer cell is designed to connect these two memory networks, enabling knowledge transfer from the long-term memory network to the short-term memory network to mitigate the conceptual confusion, and a memory consolidation mechanism is developed to integrate short-term knowledge into the long-term memory network for knowledge accumulation. Experimental results demonstrate that the CMN can effectively address the anterograde forgetting on several task-related, task-conflict, class-incremental and cross-domain benchmarks.

Since conventional approaches could not adapt to dynamic traffic conditions, reinforcement learning (RL) has attracted more attention to help solve the traffic signal control (TSC) problem. However, existing RL-based methods are rarely deployed considering that they are neither cost-effective in terms of computing resources nor more robust than traditional approaches, which raises a critical research question: how to construct an adaptive controller for TSC with less training and reduced complexity based on RL-based approach? To address this question, in this paper, we (1) innovatively specify the traffic movement representation as a simple but efficient pressure of vehicle queues in a traffic network, namely efficient pressure (EP); (2) build a traffic signal settings protocol, including phase duration, signal phase number and EP for TSC; (3) design a TSC approach based on the traditional max pressure (MP) approach, namely efficient max pressure (Efficient-MP) using the EP to capture the traffic state; and (4) develop a general RL-based TSC algorithm template: efficient Xlight (Efficient-XLight) under EP. Through comprehensive experiments on multiple real-world datasets in our traffic signal settings' protocol for TSC, we demonstrate that efficient pressure is complementary to traditional and RL-based modeling to design better TSC methods. Our code is released on Github.

Cold-start problem is a fundamental challenge for recommendation tasks. The recent self-supervised learning (SSL) on Graph Neural Networks (GNNs) model, PT-GNN, pre-trains the GNN model to reconstruct the cold-start embeddings and has shown great potential for cold-start recommendation. However, due to the over-smoothing problem, PT-GNN can only capture up to 3-order relation, which can not provide much useful auxiliary information to depict the target cold-start user or item. Besides, the embedding reconstruction task only considers the intra-correlations within the subgraph of users and items, while ignoring the inter-correlations across different subgraphs. To solve the above challenges, we propose a multi-strategy based pre-training method for cold-start recommendation (MPT), which extends PT-GNN from the perspective of model architecture and pretext tasks to improve the cold-start recommendation performance. Specifically, in terms of the model architecture, in addition to the short-range dependencies of users and items captured by the GNN encoder, we introduce a Transformer encoder to capture long-range dependencies. In terms of the pretext task, in addition to considering the intra-correlations of users and items by the embedding reconstruction task, we add embedding contrastive learning task to capture inter-correlations of users and items. We train the GNN and Transformer encoders on these pretext tasks under the meta-learning setting to simulate the real cold-start scenario, making the model easily and rapidly being adapted to new cold-start users and items. Experiments on three public recommendation datasets show the superiority of the proposed MPT model against the vanilla GNN models, the pre-training GNN model on user/item embedding inference and the recommendation task.

We study the problem of recommending items to occasional groups (a.k.a. cold-start groups), where the occasional groups are formed ad-hoc and have few or no historical interacted items. Due to the extreme sparsity issue of the occasional groups' interactions with items, it is difficult to learn high-quality embeddings for these occasional groups. Despite the recent advances on Graph Neural Networks (GNNs) incorporate high-order collaborative signals to alleviate the problem, the high-order cold-start neighbors are not explicitly considered during the graph convolution in GNNs. This paper proposes a self-supervised graph learning paradigm, which jointly trains the backbone GNN model to reconstruct the group/user/item embeddings under the meta-learning setting, such that it can directly improve the embedding quality and can be easily adapted to the new occasional groups. To further reduce the impact from the cold-start neighbors, we incorporate a self-attention-based meta aggregator to enhance the aggregation ability of each graph convolution step. Besides, we add a contrastive learning (CL) adapter to explicitly consider the correlations between the group and non-group members. Experimental results on three public recommendation datasets show the superiority of our proposed model against the state-of-the-art group recommendation methods.

Good training data is a prerequisite to develop useful Machine Learning applications. However, in many domains existing data sets cannot be shared due to privacy regulations (e.g., from medical studies). This work investigates a simple yet unconventional approach for anonymized data synthesis to enable third parties to benefit from such anonymized data. We explore the feasibility of learning implicitly from visually unrealistic, task-relevant stimuli, which are synthesized by exciting the neurons of a trained deep neural network. As such, neuronal excitation can be used to generate synthetic stimuli. The stimuli data is used to train new classification models. Furthermore, we extend this framework to inhibit representations that are associated with specific individuals. We use sleep monitoring data from both an open and a large closed clinical study, and Electroencephalogram sleep stage classification data, to evaluate whether (1) end-users can create and successfully use customized classification models, and (2) the identity of participants in the study is protected. Extensive comparative empirical investigation shows that different algorithms trained on the stimuli are able to generalize successfully on the same task as the original model. Architectural and algorithmic similarity between new and original models play an important role in performance. For similar architectures, the performance is close to that of using the original data (e.g., Accuracy difference of 0.56%-3.82%, Kappa coefficient difference of 0.02-0.08). Further experiments show that the stimuli can provide state-ofthe-art resilience against adversarial association and membership inference attacks.

This work examines adaptive distributed learning strategies designed to operate under communication constraints. We consider a network of agents that must solve an online optimization problem from continual observation of streaming data. The agents implement a distributed cooperative strategy where each agent is allowed to perform local exchange of information with its neighbors. In order to cope with communication constraints, the exchanged information must be unavoidably compressed. We propose a diffusion strategy nicknamed as ACTC (Adapt-Compress-Then-Combine), which relies on the following steps: i) an adaptation step where each agent performs an individual stochastic-gradient update with constant step-size; ii) a compression step that leverages a recently introduced class of stochastic compression operators; and iii) a combination step where each agent combines the compressed updates received from its neighbors. The distinguishing elements of this work are as follows. First, we focus on adaptive strategies, where constant (as opposed to diminishing) step-sizes are critical to respond in real time to nonstationary variations. Second, we consider the general class of directed graphs and left-stochastic combination policies, which allow us to enhance the interplay between topology and learning. Third, in contrast with related works that assume strong convexity for all individual agents' cost functions, we require strong convexity only at a network level, a condition satisfied even if a single agent has a strongly-convex cost and the remaining agents have non-convex costs. Fourth, we focus on a diffusion (as opposed to consensus) strategy. Under the demanding setting of compressed information, we establish that the ACTC iterates fluctuate around the desired optimizer, achieving remarkable savings in terms of bits exchanged between neighboring agents.

Benchmark datasets play a central role in the organization of machine learning research. They coordinate researchers around shared research problems and serve as a measure of progress towards shared goals. Despite the foundational role of benchmarking practices in this field, relatively little attention has been paid to the dynamics of benchmark dataset use and reuse, within or across machine learning subcommunities. In this paper, we dig into these dynamics. We study how dataset usage patterns differ across machine learning subcommunities and across time from 2015-2020. We find increasing concentration on fewer and fewer datasets within task communities, significant adoption of datasets from other tasks, and concentration across the field on datasets that have been introduced by researchers situated within a small number of elite institutions. Our results have implications for scientific evaluation, AI ethics, and equity/access within the field.

A strong cyber defense system should be able to detect, monitor, and promptly leverage defence mechanisms to the cyber threats including evolving and intelligent attacks Hou et al. [2020], Brundage et al. [2018], Jang-Jaccard and Nepal [2014], Camp et al. [2019]. However, traditional defensive techniques cannot avoid the novel and evolving attacks which can leverage AI technology to plan and launch various attacks. AI-powered attacks can be categorized based on AI-aided and AI-embedded attacks. AI-aided attacks are those that leverage AI to launch the attacks effectively. In this type, the intelligent attackers use AI techniques. However, in AI-embedded attacks, the threats are weaponized by AI themselves such as Deep locker Stoecklin [2018] while in the AI-aided attacks, the attackers could launch various AI-based techniques to detect and recognize the target network, vulnerabilities, and valuable targets Kaloudi and Li [2020]. In fact, they utilize various AI techniques as a tool for various purposes. In Kaloudi and Li [2020], the authors investigated the AI-powered cyber attacks and mapped them onto a proposed framework with new threats including the classification of several aspects of threats that use AI during the cyber-attack life cycle.

We introduce REDO, a class-agnostic framework to REconstruct the Dynamic Objects from RGBD or calibrated videos. Compared to prior work, our problem setting is more realistic yet more challenging for three reasons: 1) due to occlusion or camera settings an object of interest may never be entirely visible, but we aim to reconstruct the complete shape; 2) we aim to handle different object dynamics including rigid motion, non-rigid motion, and articulation; 3) we aim to reconstruct different categories of objects with one unified framework. To address these challenges, we develop two novel modules. First, we introduce a canonical 4D implicit function which is pixel-aligned with aggregated temporal visual cues. Second, we develop a 4D transformation module which captures object dynamics to support temporal propagation and aggregation. We study the efficacy of REDO in extensive experiments on synthetic RGBD video datasets SAIL-VOS 3D and DeformingThings4D++, and on real-world video data 3DPW. We find REDO outperforms state-of-the-art dynamic reconstruction methods by a margin. In ablation studies we validate each developed component.

This is a strange and exciting time for computer-generated music. The idea of computer-generated musical composition has captured the public imagination, as far back as Kurzweil's demonstration of a pattern-based composer on live TV in 1965[1]. Since then, improvements in technology and composition tools have created whole musical genres based around computer-generated compositions, and have resulted in a vast library of algorithmic compositional techniques. Furthermore, in the past few decades, interactive media such as games and virtual reality have resulted in a demand for music that can adapt to dynamic circumstances presented within the interactive medium. Finally, the advent of ML music models such as Google Magenta's MusicVAE[6] now allow us to extract and replicate compositional features from otherwise complex datasets. These models allow computational composers to parameterize abstract variables such as style and mood. By leveraging these models and combining them with procedural algorithms from the last few decades, it is possible to create a dynamic song that composes music in real-time to accompany interactive experiences [10]. Malakai is a tool that helps users of varying skill levels create, listen to, remix and share such dynamic songs. Using Malakai, a Composer can create a dynamic song that can be interacted with by a Listener.