Tour itinerary planning and recommendation are challenging tasks for tourists in unfamiliar countries. Many tour recommenders only consider broad POI categories and do not align well with users' preferences and other locational constraints. We propose an algorithm to recommend personalized tours using POI-embedding methods, which provides a finer representation of POI types. Our recommendation algorithm will generate a sequence of POIs that optimizes time and locational constraints, as well as user's preferences based on past trajectories from similar tourists. Our tour recommendation algorithm is modelled as a word embedding model in natural language processing, coupled with an iterative algorithm for generating itineraries that satisfies time constraints. Using a Flickr dataset of 4 cities, preliminary experimental results show that our algorithm is able to recommend a relevant and accurate itinerary, based on measures of recall, precision and F1-scores.

Fairness and explainability are two important and closely related requirements of decision making systems. While fairness and explainability of decision making systems have been extensively studied independently, only little effort has been put into studying fairness of explanations on their own. Current explanations can be unfair to an individual: an example is given by counterfactual explanations which propose different actions to change the output class to two similar individuals. In this work we formally and empirically study individual fairness and its mathematical formalization as robustness for counterfactual explanations as a prominent instance of contrasting explanations. In addition, we propose to use plausible counterfactuals instead of closest counterfactuals for improving the individual fairness of counterfactual explanations.

Why universities will need to digitalise to survive Dave Sherwood 27 February 2021 Universities, and the role they play in society, are under threat from the impact of the ongoing pandemic. While rarely a sector in financial crisis, university leaders in seven of the higher education systems in Europe now predict a fall in core national funding as a result of COVID-19, compounding the huge hits universities have taken on rental and commercial services and contractual research. Fourteen national university sectors in Europe have also predicted a fall in income from international students, with travel restrictions limiting student mobility. Estimates of losses to the United Kingdom university sector range from £3 billion (US4.2 billion) to £19 billion (US$26.7 billion) per year as a result of the coronavirus, while the picture is no less bleak across the pond. The University of Michigan alone anticipates losses of up to US$1 billion this year across its three campuses.

If you're a marketer, odds are that you're not just trying to sell more products and services. You're also trying to live and communicate values that make our world a little better, with the fight against societal systemic racism, sexism and other kinds of discrimination at the top of the list. You're also surely eager to take advantage of the latest marketing technology, especially artificial intelligence (AI). AI can allow for highly customized campaigns and let you monitor and adjust them in real time. These two priorities should work well together.

In real-world applications of large-scale time series, one often encounters the situation where the temporal patterns of time series, while drifting over time, differ from one another in the same dataset. In this paper, we provably show under such heterogeneity, training a forecasting model with commonly used stochastic optimizers (e.g. SGD) potentially suffers large gradient variance, and thus requires long time training. To alleviate this issue, we propose a sampling strategy named Subgroup Sampling, which mitigates the large variance via sampling over pre-grouped time series. We further introduce SCott, a variance reduced SGD-style optimizer that co-designs subgroup sampling with the control variate method. In theory, we provide the convergence guarantee of SCott on smooth non-convex objectives. Empirically, we evaluate SCott and other baseline optimizers on both synthetic and real-world time series forecasting problems, and show SCott converges faster with respect to both iterations and wall clock time. Additionally, we show two SCott variants that can speed up Adam and Adagrad without compromising generalization of forecasting models.

We propose and analyze algorithms to solve a range of learning tasks under user-level differential privacy constraints. Rather than guaranteeing only the privacy of individual samples, user-level DP protects a user's entire contribution ($m \ge 1$ samples), providing more stringent but more realistic protection against information leaks. We show that for high-dimensional mean estimation, empirical risk minimization with smooth losses, stochastic convex optimization, and learning hypothesis class with finite metric entropy, the privacy cost decreases as $O(1/\sqrt{m})$ as users provide more samples. In contrast, when increasing the number of users $n$, the privacy cost decreases at a faster $O(1/n)$ rate. We complement these results with lower bounds showing the worst-case optimality of our algorithm for mean estimation and stochastic convex optimization. Our algorithms rely on novel techniques for private mean estimation in arbitrary dimension with error scaling as the concentration radius $\tau$ of the distribution rather than the entire range. Under uniform convergence, we derive an algorithm that privately answers a sequence of $K$ adaptively chosen queries with privacy cost proportional to $\tau$, and apply it to solve the learning tasks we consider.

Sequential matching using hand-crafted heuristics has been standard practice in route-based place recognition for enhancing pairwise similarity results for nearly a decade. However, precision-recall performance of these algorithms dramatically degrades when searching on short temporal window (TW) lengths, while demanding high compute and storage costs on large robotic datasets for autonomous navigation research. Here, influenced by biological systems that robustly navigate spacetime scales even without vision, we develop a joint visual and positional representation learning technique, via a sequential process, and design a learning-based CNN+LSTM architecture, trainable via backpropagation through time, for viewpoint- and appearance-invariant place recognition. Our approach, Sequential Place Learning (SPL), is based on a CNN function that visually encodes an environment from a single traversal, thus reducing storage capacity, while an LSTM temporally fuses each visual embedding with corresponding positional data -- obtained from any source of motion estimation -- for direct sequential inference. Contrary to classical two-stage pipelines, e.g., match-then-temporally-filter, our network directly eliminates false-positive rates while jointly learning sequence matching from a single monocular image sequence, even using short TWs. Hence, we demonstrate that our model outperforms 15 classical methods while setting new state-of-the-art performance standards on 4 challenging benchmark datasets, where one of them can be considered solved with recall rates of 100% at 100% precision, correctly matching all places under extreme sunlight-darkness changes. In addition, we show that SPL can be up to 70x faster to deploy than classical methods on a 729 km route comprising 35,768 consecutive frames. Extensive experiments demonstrate the... Baseline code available at https://github.com/mchancan/deepseqslam

The progress in Query-focused Multi-Document Summarization (QMDS) has been limited by the lack of sufficient largescale high-quality training datasets. We present two QMDS training datasets, which we construct using two data augmentation methods: (1) transferring the commonly used single-document CNN/Daily Mail summarization dataset to create the QMDSCNN dataset, and (2) mining search-query logs to create the QMDSIR dataset. These two datasets have complementary properties, i.e., QMDSCNN has real summaries but queries are simulated, while QMDSIR has real queries but simulated summaries. To cover both these real summary and query aspects, we build abstractive end-to-end neural network models on the combined datasets that yield new state-of-the-art transfer results on DUC datasets. We also introduce new hierarchical encoders that enable a more efficient encoding of the query together with multiple documents. Empirical results demonstrate that our data augmentation and encoding methods outperform baseline models on automatic metrics, as well as on human evaluations along multiple attributes.

To address the long-standing data sparsity problem in recommender systems (RSs), cross-domain recommendation (CDR) has been proposed to leverage the relatively richer information from a richer domain to improve the recommendation performance in a sparser domain. Although CDR has been extensively studied in recent years, there is a lack of a systematic review of the existing CDR approaches. To fill this gap, in this paper, we provide a comprehensive review of existing CDR approaches, including challenges, research progress, and future directions. Specifically, we first summarize existing CDR approaches into four types, including single-target CDR, multi-domain recommendation, dual-target CDR, and multi-target CDR. We then present the definitions and challenges of these CDR approaches. Next, we propose a full-view categorization and new taxonomies on these approaches and report their research progress in detail. In the end, we share several promising research directions in CDR.

A fundamental task for artificial intelligence is learning. Deep Neural Networks have proven to cope perfectly with all learning paradigms, i.e. supervised, unsupervised, and reinforcement learning. Nevertheless, traditional deep learning approaches make use of cloud computing facilities and do not scale well to autonomous agents with low computational resources. Even in the cloud, they suffer from computational and memory limitations, and they cannot be used to model adequately large physical worlds for agents which assume networks with billions of neurons. These issues are addressed in the last few years by the emerging topic of sparse training, which trains sparse networks from scratch. This paper discusses sparse training state-of-the-art, its challenges and limitations while introducing a couple of new theoretical research directions which has the potential of alleviating sparse training limitations to push deep learning scalability well beyond its current boundaries. Nevertheless, the theoretical advancements impact in complex multi-agents settings is discussed from a real-world perspective, using the smart grid case study.