1 / 15

Relational Learning: from Yesterday to Tomorrow

Relational Learning: from Yesterday to Tomorrow. Lorenza Saitta Universit à del Piemonte Orientale saitta@mfn.unipmn.it. Why did I choose this topic?. This is how I knew Yves’ existence As a team, we have worked on the topic since its beginning, knowing thus its hopes and deceptions

medlin
Download Presentation

Relational Learning: from Yesterday to Tomorrow

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Relational Learning: from Yesterday to Tomorrow Lorenza Saitta Università del Piemonte Orientale saitta@mfn.unipmn.it

  2. Why did I choose this topic? • This is how I knew Yves’ existence • As a team, we have worked on the topic since its beginning, knowing thus its hopes and deceptions • The topic is fascinating and rich of fundamental issues for understanding learning in both humans and machines Warning: This is NOT an overview of the field, but a collection of personal reflexions

  3. Relation Learning has a peculiar history • Negative point: it is conceptually hard and computationally demanding • Positive point: it is apparently more close to human learning, w.r.t. previous Pattern Recognition approaches (even the syntactic ones) • Michalski’s « Human comprehensibility principle » • Instead of a progression « easy  difficult » in the research topics, we have seen, at the beginning, researchers launching themselves into RL with great enthusiasm, but a scarse sense of the feasible

  4. The power of names • The consequence is a history of déjà vu, of dead ends, and of difficulties periodically re-emerging, that researchers try to solve again and again • Solution = Restart and change the label FOL Learning ILP SRL • It would be unfair to say that at each restart everything is the same. Some novelties are added each time • As restart is an effective technique in search, maybe it will be also effective for RL in the long term

  5. The ambition of the origins • ML started officially in 1980 [Pittsburgh workshop] • RL is much older [~ 1970] • Meltzer Inverting deduction { E1, ¬E1 V E2 } • Morgan «  «  • Plotkin -subsumption • Winston ARCH -> Near-misses • Vere TOTH -> Counterfactuals • Conceptually interesting and still up-to-date today • Computationally infeasible, but, at the time, this was not an issue. The proposed algorithms were not meant to work: they were ideological and explorative in nature. • It is quite surprising that the first learning approaches (except Samuel’s checker) were actually relational. • RL attracted researchers as « honey attract flies » [as we say in Italy]

  6. Keeping feet on the ground • But learning IS meant to work, even if it is relational • Under Michalski’s influence, between 1980 and 1990 many systems have been designed and implemented both in Europe and in the USA • Kodratoff et al. • Giordana et al. [Learning from a relational datbase, 1988] • Esposito et al. • Morik et al. • But not just learning systems but source of conceptual innovations: • Mitchell’s and De Jong’s EBL • Ganascia & Zucker’s « morions » • Carbonell’s learning in planning • Some concrete results were obtained

  7. Generality • Crucial issue: how to define the generality relation if FOL? • Michalski • Buntine • Niblett • Flach -> « Yves lives in France », « Yves lives in Paris » • Kodratoff • Console & Saitta -> Frege’s theory of concepts • Generality ≠ Information content • The discussion died, but it is a pity, because the field got impoverished: received view -subsumption or covering • Relationships with abduction and with abstraction

  8. Inductive Logic Programming Muggleton’s CIGOL Quinlan’s FOIL ILP • Automatic programming • Strongly logic-oriented. Mostly based on -subsumption. High computational complexity • h(x,y) name of a relation (extension -> intension) • Attributes -> Background knowledge • Needs powerful bias or human help • A theory of logical learning more than a practical approach. • Some success in applications. • Almost separated from mainstream ML. • Extensions towards Reinforcement learning, Clustering, Neural Networks.

  9. Plateau and Phase Transitions • The covering test shows a phase transition in a range of parameters interesting for practical learning approaches • Concept with more than 4 chained variables cannot be learned due to the extremely high computational complexity of the test. • Top-down, hypothesis-and-test-based relational learning cannot go beyond stringent limits on the complexity of examples and hypotheses. • Could top-down, data-driven approaches overcome the limits?

  10. Statistical relational learning ILP Probability SRL • Started by considering relations among examples • Evolved toward probabilitic logic. Probabilistic logics (PL) did not produce anything usable in the past. • By putting together two difficult subjects, is it possible that something simple will come out? By interference ? • Several interesting ideas, but no definite solution. Field at the beginning. • Domingos and Richardson (Markov networks) • Kersting and De Raedt (Bayest neworks) • Poole (Lifted inference) • Koller et al. (Probabilistic nertworks - Database-oriented approach)

  11. P(X), Q(x) -> R(X,Y) P(X), Q(x) -> S(X,Y) Q(X), Q(Y) -> V(X,Y) -> R(X,Y) {a, b}

  12. Future?

  13. ”I believe that the world market can be satured by maybe five computers” [Thomas Watson, IBM Chairman, 1943] ”A 640 KB memory should be sufficient for everyone" [Bill Gates, 1981] "Internet will undergo a catastrophic collapse in 1996" [Robert Metcalfe, Ethernet’s inventor]

  14. Guesses • A radically new approach is needed to obtain substantial steps ahead • NO Logic, but get close to (take inspiration from) : • Cognitive Sciences • Human memory and learning • More complex concept representation (Barsalou) • Do the limitations to machine learning also apply to human learning? • Complex Systems • Graphs and networks • Agent Based Modeling • Simulation • Statistical Phisics • Ensemble phenomena • Collective learning (emergent phenomenon) • Abstraction and multi-resolution approaches

  15. Guesses • Investigating the foundations • Phase transitions • Kolmogorov complexity • Chaitin’s theorem - Algorithmic version of the Halt problem • No program of complexity n can generate a number greater than n

More Related